To see the other types of publications on this topic, follow the link: YOLOv3.
Dissertations / Theses on the topic 'YOLOv3'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'YOLOv3.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Borngrund, Carl. "Machine vision for automation of earth-moving machines : Transfer learning experiments with YOLOv3." Thesis, Luleå tekniska universitet, Institutionen för system- och rymdteknik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-75169.
Full textAbstract:
This master thesis investigates the possibility to create a machine vision solution for the automation of earth-moving machines. This research was done as without some type of vision system it will not be possible to create a fully autonomous earth moving machine that can safely be used around humans or other machines. Cameras were used as the primary sensors as they are cheap, provide high resolution and is the type of sensor that most closely mimic the human vision system. The purpose of this master thesis was to use existing real time object detectors together with transfer learning and examine if they can successfully be used to extract information in environments such as construction, forestry and mining. The amount of data needed to successfully train a real time object detector was also investigated. Furthermore, the thesis examines if there are specifically difficult situations for the defined object detector, how reliable the object detector is and finally how to use service-oriented architecture principles can be used to create deep learning systems. To investigate the questions formulated above, three data sets were created where different properties were varied. These properties were light conditions, ground material and dump truck orientation. The data sets were created using a toy dump truck together with a similarly sized wheel loader with a camera mounted on the roof of its cab. The first data set contained only indoor images where the dump truck was placed in different orientations but neither the light nor the ground material changed. The second data set contained images were the light source was kept constant, but the dump truck orientation and ground materials changed. The last data set contained images where all property were varied. The real time object detector YOLOv3 was used to examine how a real time object detector would perform depending on which one of the three data sets it was trained using. No matter the data set, it was possible to train a model to perform real time object detection. Using a Nvidia 980 TI the inference time of the model was around 22 ms, which is more than enough to be able to classify videos running at 30 fps. All three data sets converged to a training loss of around 0.10. The data set which contained more varied data, such as the data set where all properties were changed, performed considerably better reaching a validation loss of 0.164 compared to the indoor data set, containing the least varied data, only reached a validation loss of 0.257. The size of the data set was also a factor in the performance, however it was not as important as having varied data. The result also showed that all three data sets could reach a mAP score of around 0.98 using transfer learning.
2
Norling, Samuel. "Tree species classification with YOLOv3 : Classification of Silver Birch (Betula pendula) and Scots Pine (Pinus sylvestris)." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-260244.
Full textAbstract:
Automation of tree species classification during a forest inventory could potentially provide more efficiency and better results for forest companies and stakeholding agencies. This thesis investigates how well a state of the art object detection system, YOLOv3, performs this classification task. A new image dataset with pictures of Silver Birches and Scots Pines, called LilljanNet, was created to train YOLOv3. After training YOLOv3 on half the dataset we performed validation by testing it against the other half. The trained model scored a mean average precision above 0.99. Training was also done with smaller sets of training data and the mean average precision score for these models all achieved mean average precision above 0.95. The results are promising and further research should be done testing this on smartphones and drones.<br>Automatisering av trädslagsklassifiering vid en skogstaxering skulle potentiellt sätt kunna ge mer effektivitet och bättre resultat för skogsbolag och myndigheter som ansvarar för skogen. Denna uppsats undersöker hur väl ett toppmodernt datorseendesystem, YOLOv3, utför denna klassifieringsuppgift. Ett nytt bildbibliotek med bilder av björkar och tallar, som kallas LilljanNet, skapades för att träna YOLOv3. Efter vi tränat YOLOv3 på halva datamängden utförde vi validering mot den andra halvan. Den upptränade modellen uppnådde ett mean average precision över 0.99. Träning gjordes också med mindre mängder träningsdata och mean average precision-resultaten för dessa modeller var alltid över 0.95. Resultaten är lovande och mer forskning bör göras där man testar att implementera detta på smartphones och drönare.
3
Ståhl, Sebastian. "A tracking framework for a dynamic non- stationary environment." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-288955.
Full textAbstract:
As the use of unmanned aerial vehicles (UAVs) increases in popularity across the globe, their fields of application are constantly growing. This thesis researches the possibility of using a UAV to detect, track, and geolocate a target in a dynamic nonstationary environment as the seas. In this case, different projection and apparent size of the target in the captured images can lead to ambiguous assignments of coordinated. In this thesis, a framework based on a UAV, a monocular camera, a GPS receiver, and the UAV’s inertial measurement unit (IMU) is developed to perform the task of detecting, tracking and geolocating targets. An object detection model called Yolov3 was retrained to be able to detect boats in UAV footage. This model was selected due to its capabilities of detecting targets of small apparent sizes and its performance in terms of speed. A model called the kernelized correlation filter (KCF) is adopted as the visual tracking algorithm. This tracker is selected because of its performance in terms of speed and accuracy. A reinitialization of the tracker in combination with a periodic update of the tracked bounding box are implemented which resulted in improved performance of the tracker. A geolocation method is developed to continuously estimate the GPS coordinates of the target. These estimates will be used by the flight control method already developed by the stakeholder Airpelago to control the UAV. The experimental results show promising results for all models. Due to inaccurate data, the true accuracy of the geolocation method can not be determined. The average error calculated with the inaccurate data is 19.5 meters. However, an in- depth analysis of the results indicates that the true accuracy of the method is more accurate. Hence, it is assumed that the model can estimate the GPS coordinates of a target with an error significantly lower than 19.5 meters. Thus, it is concluded that it is possible to detect, track and geolocate a target in a dynamic nonstationary environment as the seas.<br>Användandet av drönare ökar i popularitet över hela världen vilket bidrar till att dess tillämpningsområden växer. I denna avhandling undersöks möjligheten att använda en drönare för att detektera, spåra och lokalisera ett mål i en dynamisk icke- stationär miljö som havet. Målets varierande position och storlek i bilderna leda till tvetydiga uppgifter. I denna avhandlingen utvecklas ett ramverk baserat på en drönare, en monokulär kamera, en GPS- mottagare och drönares IMU sensor för att utföra detektering, spårning samt lokalisering av målet. En objektdetekteringsmodell vid namn Yolov3 tränades för att kunna detektera båtar i bilder tagna från en drönare. Denna modell valdes på grund av dess förmåga att upptäcka små mål och dess prestanda vad gäller hastighet. En modell vars förkortning är KCF används som den visuella spårningsalgoritmen. Denna algoritm valdes på grund av dess prestanda när det gäller hastighet och precision. En återinitialisering av spårningsalgoritmen i kombination med en periodisk uppdatering av den spårade avgränsningsrutan implementeras vilket förbättrar trackerens prestanda. En lokaliseringsmetod utvecklas för att kontinuerligt uppskatta GPS- koordinaterna av målet. Dessa uppskattningar kommer att användas av en flygkontrollmetod som redan utvecklats av Airpelago för att styra drönaren. De experimentella resultaten visar lovande resultat för alla modeller. På grund av opålitlig data kan inte lokaliseringsmetodens precision fastställas med säkerhet. En djupgående analys av resultaten indikerar emellertid att metodens noggrannhet är mer exakt än det genomsnittliga felet beräknat med opålitliga data, som är 19.5 meter. Därför antas det att modellen kan uppskatta GPS- koordinaterna för ett mål med ett fel som är lägre än 19.5 meter. Således dras slutsatsen att det är möjligt att upptäcka, spåra och geolocera ett mål i en dynamisk icke- stationär miljö som havet.
4
Oškera, Jan. "Detekce dopravních značek a semaforů." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2020. http://www.nusl.cz/ntk/nusl-432850.
Full textAbstract:
The thesis focuses on modern methods of traffic sign detection and traffic lights detection directly in traffic and with use of back analysis. The main subject is convolutional neural networks (CNN). The solution is using convolutional neural networks of YOLO type. The main goal of this thesis is to achieve the greatest possible optimization of speed and accuracy of models. Examines suitable datasets. A number of datasets are used for training and testing. These are composed of real and synthetic data sets. For training and testing, the data were preprocessed using the Yolo mark tool. The training of the model was carried out at a computer center belonging to the virtual organization MetaCentrum VO. Due to the quantifiable evaluation of the detector quality, a program was created statistically and graphically showing its success with use of ROC curve and evaluation protocol COCO. In this thesis I created a model that achieved a success average rate of up to 81 %. The thesis shows the best choice of threshold across versions, sizes and IoU. Extension for mobile phones in TensorFlow Lite and Flutter have also been created.
5
Roohi, Masood. "end-point detection of a deformable linear object from visual data." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/21133/.
Full textAbstract:
In the context of industrial robotics, manipulating rigid objects have been studied quite deeply. However, Handling deformable objects is still a big challenge. Moreover, due to new techniques introduced in the object detection literature, employing visual data is getting more and more popular between researchers. This thesis studies how to exploit visual data for detecting the end-point of a deformable linear object. A deep learning model is trained to perform the task of object detection. First of all, basics of the neural networks is studied to get more familiar with the mechanism of the object detection. Then, a state-of-the-art object detection algorithm YOLOv3 is reviewed so it can be used as its best. Following that, it is explained how to collect the visual data and several points that can improve the data gathering procedure are delivered. After clarifying the process of annotating the data, model is trained and then it is tested. Trained model localizes the end-point. This information can be used directly by the robot to perform tasks like pick and place or it can be used to get more information on the form of the object.
6
Svedberg, Malin. "Analys av inskannade arkiverade dokument med hjälp av objektdetektering uppbyggt på AI." Thesis, Högskolan i Gävle, Avdelningen för datavetenskap och samhällsbyggnad, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-32612.
Full textAbstract:
Runt om i världen finns det en stor mängd historiska dokument som endast finns i pappersform. Genom att digitalisera dessa dokument förenklas bland annat förvaring och spridning av dokumenten. Vid digitalisering av dokument räcker det oftast inte att enbart skanna in dokumenten och förvara dem som en bild, oftast finns det önskemål att kunna hantera informationen som dokumenten innehåller på olika vis. Det kan t.ex. vara att söka efter en viss information eller att sortera dokumenten utifrån informationen dem innehåller. Det finns olika sätt att digitalisera dokument och extrahera den information som finns på dem. I denna studie används metoden objektdetektering av typen YOLOv3 för att hitta och urskilja olika områden på historiska dokument i form av gamla registerkort för gamla svenska fordon. Objektdetekteringen tränas på ett egenskapat träningsdataset och träningen av objektdetekteringen sker via ramverket Darknet. Studien redovisar resultat i form av recall, precision och IoU för flera olika objektdetekteringsmodeller tränade på olika träningsdataset och som testats på ett flertal olika testdataset. Resultatet analyseras bland annat utifrån storlek och färg på träningsdatat samt mängden träning av objektdetekteringen.
7
Yesudasu, Santheep. "Cοntributiοn à la manipulatiοn de cοlis sοus cοntraintes par un tοrse humanοïde : applicatiοn à la dépaléttisatiοn autοnοme dans les entrepôts lοgistiques". Electronic Thesis or Diss., Normandie, 2024. https://theses.hal.science/tel-04874770.
Full textAbstract:
Cette thèse de doctorat explore le développement et l'implémentation d'URNik-AI, un système de dépalettisation automatisé basé sur l'intelligence artificielle (IA), conçu pour manipuler des boîtes en carton de tailles et de poids variés à l'aide d'un torse humanoïde à double bras. L'objectif principal est d'améliorer l'efficacité, la précision et la fiabilité des tâches de dépalettisation industrielle grâce à l'intégration de la robotique avancée, de la vision par ordinateur et des techniques d'apprentissage profond.Le système URNik-AI est composé de deux bras robotiques UR10 équipés de capteurs de force/torque à six axes et d'outils de préhension. Une caméra RGB-D ASUS Xtion est montée sur des servomoteurs pan-tilt Dynamixel Pro H42 pour obtenir des images haute résolution et des données de profondeur. Le cadre logiciel comprend ROS Noetic, ROS 2 et le framework MoveIt, permettant une communication fluide et une coordination des mouvements complexes. Ce système assure une haute précision dans la détection, la saisie et la manipulation d'objets dans divers environnements industriels.Une contribution importante de cette recherche est l'implémentation de modèles d'apprentissage profond, tels que YOLOv3 et YOLOv8, pour améliorer les capacités de détection et d'estimation de pose des objets. YOLOv3, entraîné sur un ensemble de données de 807 images, a atteint des scores F1 de 0,81 et 0,90 pour les boîtes à une et plusieurs faces, respectivement. Le modèle YOLOv8 a encore amélioré les performances du système en fournissant des capacités de détection de points clés et de squelettes, essentielles pour la manipulation précise des objets. L'intégration des données de nuage de points pour l'estimation de la pose a assuré une localisation et une orientation précises des boîtes.Les résultats des tests ont démontré la robustesse du système, avec des métriques élevées de précision, rappel et précision moyenne (mAP), confirmant son efficacité. Cette thèse apporte plusieurs contributions significatives au domaine de la robotique et de l'automatisation, notamment l'intégration réussie des technologies robotiques avancées et de l'IA, le développement de techniques innovantes de détection et d'estimation de pose, ainsi que la conception d'une architecture de système polyvalente et adaptable<br>This PhD thesis explores the development and implementation of URNik-AI, an AI-powered automated depalletizing system designed to handle cardboard boxes of varying sizes and weights using a dual-arm humanoid torso. The primary objective is to enhance the efficiency, accuracy, and reliability of industrial depalletizing tasks through the integration of advanced robotics, computer vision, and deep learning techniques.The URNik-AI system consists of two UR10 robotic arms equipped with six-axis force/torque sensors and gripper tool sets. An ASUS Xtion RGB-D camera is mounted on Dynamixel Pro H42 pan-tilt servos to capture high-resolution images and depth data. The software framework includes ROS Noetic, ROS 2, and the MoveIt framework, enabling seamless communication and coordination of complex movements. This system ensures high precision in detecting, grasping, and handling objects in diverse industrial environments.A significant contribution of this research is the implementation of deep learning models, such as YOLOv3 and YOLOv8, to enhance object detection and pose estimation capabilities. YOLOv3, trained on a dataset of 807 images, achieved F1-scores of 0.81 and 0.90 for single and multi-face boxes, respectively. The YOLOv8 model further advanced the system's performance by providing keypoint and skeleton detection capabilities, which are essential for accurate grasping and manipulation. The integration of point cloud data for pose estimation ensured precise localization and orientation of boxes.Comprehensive testing demonstrated the system's robustness, with high precision, recall, and mean average precision (mAP) metrics confirming its effectiveness. This thesis makes several significant contributions to the field of robotics and automation, including the successful integration of advanced robotics and AI technologies, the development of innovative object detection and pose estimation techniques, and the design of a versatile and adaptable system architecture
8
Jacobzon, Gustaf. "Multi-site Organ Detection in CT Images using Deep Learning." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279290.
Full textAbstract:
When optimizing a controlled dose in radiotherapy, high resolution spatial information about healthy organs in close proximity to the malignant cells are necessary in order to mitigate dispersion into these organs-at-risk. This information can be provided by deep volumetric segmentation networks, such as 3D U-Net. However, due to limitations of memory in modern graphical processing units, it is not feasible to train a volumetric segmentation network on full image volumes and subsampling the volume gives a too coarse segmentation. An alternative is to sample a region of interest from the image volume and train an organ-specific network. This approach requires knowledge of which region in the image volume that should be sampled and can be provided by a 3D object detection network. Typically the detection network will also be region specific, although a larger region such as the thorax region, and requires human assistance in choosing the appropriate network for a certain region in the body. Instead, we propose a multi-site object detection network based onYOLOv3 trained on 43 different organs, which may operate on arbitrary chosen axial patches in the body. Our model identifies the organs present (whole or truncated) in the image volume and may automatically sample a region from the input and feed to the appropriate volumetric segmentation network. We train our model on four small (as low as 20 images) site-specific datasets in a weakly-supervised manner in order to handle the partially unlabeled nature of site-specific datasets. Our model is able to generate organ-specific regions of interests that enclose 92% of the organs present in the test set.<br>Vid optimering av en kontrollerad dos inom strålbehandling krävs det information om friska organ, så kallade riskorgan, i närheten av de maligna cellerna för att minimera strålningen i dessa organ. Denna information kan tillhandahållas av djupa volymetriskta segmenteringsnätverk, till exempel 3D U-Net. Begränsningar i minnesstorleken hos moderna grafikkort gör att det inte är möjligt att träna ett volymetriskt segmenteringsnätverk på hela bildvolymen utan att först nedsampla volymen. Detta leder dock till en lågupplöst segmentering av organen som inte är tillräckligt precis för att kunna användas vid optimeringen. Ett alternativ är att endast behandla en intresseregion som innesluter ett eller ett fåtal organ från bildvolymen och träna ett regionspecifikt nätverk på denna mindre volym. Detta tillvägagångssätt kräver dock information om vilket område i bildvolymen som ska skickas till det regionspecifika segmenteringsnätverket. Denna information kan tillhandahållas av ett 3Dobjektdetekteringsnätverk. I regel är även detta nätverk regionsspecifikt, till exempel thorax-regionen, och kräver mänsklig assistans för att välja rätt nätverk för en viss region i kroppen. Vi föreslår istället ett multiregions-detekteringsnätverk baserat påYOLOv3 som kan detektera 43 olika organ och fungerar på godtyckligt valda axiella fönster i kroppen. Vår modell identifierar närvarande organ (hela eller trunkerade) i bilden och kan automatiskt ge information om vilken region som ska behandlas av varje regionsspecifikt segmenteringsnätverk. Vi tränar vår modell på fyra små (så lågt som 20 bilder) platsspecifika datamängder med svag övervakning för att hantera den delvis icke-annoterade egenskapen hos datamängderna. Vår modell genererar en organ-specifik intresseregion för 92 % av organen som finns i testmängden.
9
Ali, Hani, and Pontus Sunnergren. "Scenanalys - Övervakning och modellering." Thesis, Högskolan i Halmstad, Akademin för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-45036.
Full textAbstract:
Självkörande fordon kan minska trafikstockningar och minska antalet trafikrelaterade olyckor. Då det i framtiden kommer att finnas miljontals autonoma fordon krävs en bättre förståelse av omgivningen. Syftet med detta projekt är att skapa ett externt automatiskt trafikledningssystem som kan upptäcka och spåra 3D-objekt i en komplex trafiksituation för att senare skicka beteendet från dessa objekt till ett större projekt som hanterar med att 3D-modellera trafiksituationen. Projektet använder sig av Tensorflow ramverket och YOLOv3 algoritmen. Projektet använder sig även av en kamera för att spela in trafiksituationer och en dator med Linux som operativsystem. Med hjälp av metoder som vanligen används för att skapa ett automatiserat trafikledningssystem utvärderades ett målföljningssystem. De slutliga resultaten visar att systemet är relativt instabilt och ibland inte kan känna igen vissa objekt. Om fler bilder används för träningsprocessen kan ett robustare och mycket mer tillförlitligt system utvecklas med liknande metodik.<br>Autonomous vehicles can decrease traffic congestion and reduce the amount of traffic related accidents. As there will be millions of autonomous vehicles in the future, a better understanding of the environment will be required. This project aims to create an external automated traffic system that can detect and track 3D objects within a complex traffic situation to later send these objects’ behavior for a larger-scale project that manages to 3D model the traffic situation. The project utilizes Tensorflow framework and YOLOv3 algorithm. The project also utilizes a camera to record traffic situations and a Linux operated computer. Using methods commonly used to create an automated traffic management system was evaluated. The final results show that the system is relatively unstable and can sometimes fail to recognize certain objects. If more images are used for the training process, a more robust and much more reliable system could be developed using a similar methodology.
10
Melcherson, Tim. "Image Augmentation to Create Lower Quality Images for Training a YOLOv4 Object Detection Model." Thesis, Uppsala universitet, Signaler och system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-429146.
Full textAbstract:
Research in the Arctic is of ever growing importance, and modern technology is used in news ways to map and understand this very complex region and how it is effected by climate change. Here, animals and vegetation are tightly coupled with their environment in a fragile ecosystem, and when the environment undergo rapid changes it risks damaging these ecosystems severely. Understanding what kind of data that has potential to be used in artificial intelligence, can be of importance as many research stations have data archives from decades of work in the Arctic. In this thesis, a YOLOv4 object detection model has been trained on two classes of images to investigate the performance impacts of disturbances in the training data set. An expanded data set was created by augmenting the initial data to contain various disturbances. A model was successfully trained on the augmented data set and a correlation between worse performance and presence of noise was detected, but changes in saturation and altered colour levels seemed to have less impact than expected. Reducing noise in gathered data is seemingly of greater importance than enhancing images with lacking colour levels. Further investigations with a larger and more thoroughly processed data set is required to gain a clearer picture of the impact of the various disturbances.
11
Núñez-Melgar, Espinoza Erika Pamela, Oré Natali Leonor Reyes, Abad Jorge Raúl Salazar, and Vela Anderson Vásquez. "YOLO." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2018. http://hdl.handle.net/10757/625370.
Full textAbstract:
El siguiente trabajo de investigación pretende comprobar la viabilidad del proyecto denominado YOLO. Este proyecto propone crear un medio virtual para interrelacionar dos segmentos de intereses o necesidades diferentes: un segmento que desea vender productos y otro segmento que desea obtenerlos participando en un proceso de rifa virtual a precios accesibles.
En la encuesta virtual realizada para conocer el interés del servicio en el mercado, los resultados que se obtuvieron fueron que, un 72% estaría dispuesto a participar en juegos de azar virtuales y que un 52% ha vendido algún producto nuevo o usado por internet.
Para este proyecto se requiere una inversión aproximada de 141,000.00 nuevos soles de los cuales el 60% corresponde a capital de los accionistas y el 40% restante será financiado por una entidad financiera.
El proyecto YOLO que presentamos contiene el plan estratégico, el plan de marketing, el plan de operaciones, recursos humanos, y el plan económico-financiero. En la evaluación de los flujos de caja que genera el proyecto nos indican que el 100% de la inversión inicial se recupera en el primer año. Asimismo, los accionistas, desde el primer año ya tienen libre disposición de efectivo, el cual crece 23% cada año. Por último, el VAN, para ambos flujos, son positivos y la TIR, para ambos flujos, generan tasas mayores al COK de los accionistas.
Concluimos que le proyecto de negocio genera valor a los accionistas, es viable y rentable.<br>The following research work pretends to test out the viability of the project named YOLO. This project proposes to create a virtual setting to interrelate two segments of different interests or needs: a segment that wants to sell products such as technology, clothing or accessories and another segment that wish to get those items participating in a virtual raffle at affordable prices.
In a virtual survey conducted to know the interest and value of the service in the market, the results were that 72% of the people would be willing to participate in virtual games of chance and 52% has sold some new or used product by the Internet.
Afterward, the proposal was validated through the raffle of a product in which the interest and participation of the users were astounding because it surpassed the expectations.
For this project, it is required an investment of approximately S/141,000.00 of which the 60% corresponds to the shareholders capital and the remaining 40% will be financed by a financial institution.
Finally, we present for your revision, the assessment process of project YOLO, it contains the strategic plan, the marketing plan, the operations plan, human resources, and the economic-financial plan. For that reason, in this summary more reference has been made to the financial aspect basing us in the evaluation of cash flows that create the project and which indicate that 100% of the initial outlay it is regained during the first year, all the same, happens to the shareholders who have already free disposition of cash on the first year, which grows 23% every year. Additionally, Net Present Value (NPV), for both flows, is positive and the Internal Rate of Return (IRR), for both flows, generates higher rates than the shareholder's opportunity cost of capital
It concludes that the business project generates value to the stockholders, it is viable and profitable.<br>Trabajo de investigación
12
Ye, Fanjie. "A Method of Combining GANs to Improve the Accuracy of Object Detection on Autonomous Vehicles." Thesis, University of North Texas, 2020. https://digital.library.unt.edu/ark:/67531/metadc1752364/.
Full textAbstract:
As the technology in the field of computer vision becomes more and more mature, the autonomous vehicles have achieved rapid developments in recent years. However, the object detection and classification tasks of autonomous vehicles which are based on cameras may face problems when the vehicle is driving at a relatively high speed. One is that the camera will collect blurred photos when driving at high speed which may affect the accuracy of deep neural networks. The other is that small objects far away from the vehicle are difficult to be recognized by networks. In this paper, we present a method to combine two kinds of GANs to solve these problems. We choose DeblurGAN as the base model to remove blur in images. SRGAN is another GAN we choose for solving small object detection problems. Due to the total time of these two are too long, we still do the model compression on it to make it lighter. Then we use the Yolov4 to do the object detection. Finally we do the evaluation of the whole model architecture and proposed a model version 2 based on DeblurGAN and ESPCN which is faster than previous one but the accuracy may be lower.
13
Wang, Chen. "2D object detection and semantic segmentation in the Carla simulator." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-291337.
Full textAbstract:
The subject of self-driving car technology has drawn growing interest in recent years. Many companies, such as Baidu and Tesla, have already introduced automatic driving techniques in their newest cars when driving in a specific area. However, there are still many challenges ahead toward fully autonomous driving cars. Tesla has caused several severe accidents when using autonomous driving functions, which makes the public doubt self-driving car technology. Therefore, it is necessary to use the simulator environment to help verify and perfect algorithms for the perception, planning, and decision-making of autonomous vehicles before implementation in real-world cars. This project aims to build a benchmark for implementing the whole self-driving car system in software. There are three main components including perception, planning, and control in the entire autonomous driving system. This thesis focuses on two sub-tasks 2D object detection and semantic segmentation in the perception part. All of the experiments will be tested in a simulator environment called The CAR Learning to Act(Carla), which is an open-source platform for autonomous car research. Carla simulator is developed based on the game engine(Unreal4). It has a server-client system, which provides a flexible python API. 2D object detection uses the You only look once(Yolov4) algorithm that contains the tricks of the latest deep learning techniques from the aspect of network structure and data augmentation to strengthen the network’s ability to learn the object. Yolov4 achieves higher accuracy and short inference time when comparing with the other popular object detection algorithms. Semantic segmentation uses Efficient networks for Computer Vision(ESPnetv2). It is a light-weight and power-efficient network, which achieves the same performance as other semantic segmentation algorithms by using fewer network parameters and FLOPS. In this project, Yolov4 and ESPnetv2 are implemented into the Carla simulator. Two modules work together to help the autonomous car understand the world. The minimal distance awareness application is implemented into the Carla simulator to detect the distance to the ahead vehicles. This application can be used as a basic function to avoid the collision. Experiments are tested by using a single Nvidia GPU(RTX2060) in Ubuntu 18.0 system.<br>Ämnet självkörande bilteknik har väckt intresse de senaste åren. Många företag, som Baidu och Tesla, har redan infört automatiska körtekniker i sina nyaste bilar när de kör i ett specifikt område. Det finns dock fortfarande många utmaningar inför fullt autonoma bilar. Detta projekt syftar till att bygga ett riktmärke för att implementera hela det självkörande bilsystemet i programvara. Det finns tre huvudkomponenter inklusive uppfattning, planering och kontroll i hela det autonoma körsystemet. Denna avhandling fokuserar på två underuppgifter 2D-objekt detektering och semantisk segmentering i uppfattningsdelen. Alla experiment kommer att testas i en simulatormiljö som heter The CAR Learning to Act (Carla), som är en öppen källkodsplattform för autonom bilforskning. Du ser bara en gång (Yolov4) och effektiva nätverk för datorvision (ESPnetv2) implementeras i detta projekt för att uppnå Funktioner för objektdetektering och semantisk segmentering. Den minimala distans medvetenhets applikationen implementeras i Carla-simulatorn för att upptäcka avståndet till de främre bilarna. Denna applikation kan användas som en grundläggande funktion för att undvika kollisionen.
14
Ferrer, Bustamante Claudia Mariela, Llanos Víctor Hugo Ibarra, and Flores Carlos Rafael Prialé. "Plataforma virtual de Rifa Yolo." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2018. http://hdl.handle.net/10757/625450.
Full textAbstract:
El presente proyecto de negocio ha sido trabajado con la finalidad de atender la necesidad de las personas que son usuarias del comercio electrónico ofreciéndoles una manera innovadora de obtener productos por un costo mínimo.
El objetivo de este plan es aproximar productos a los consumidores que tienen el deseo de tenerlos pero que por diversas razones no han podido conseguirlos.
En esta propuesta elaborada para cumplir el deseo de nuestro cliente elegido, se ha trabajado en la identificación de sus principales motivaciones al momento de comprar por internet como son: el ahorro de tiempo, la conveniencia y la búsqueda del mejor precio, lo cual se contrastó con los principales problemas que enfrentan al momento de hacer compras en un espacio físico: prolongada espera para ser atendido y pagar, precios altos de los productos y mala atención. Además, se logró evidenciar sus temores respecto a la experiencia de comprar por internet.
El proyecto de negocio plantea el servicio de sortear productos de marcas reconocidas por nuestro cliente por lo cual se pondrá a la venta boletos de rifas durante un tiempo establecido para cada sorteo, esto se realizará a través de una plataforma virtual ágil y confiable donde el cliente podrá comprar cuantas opciones desee para ganar. Nuestra propuesta de valor propone el envío del producto libre de costo, transmisiones en vivo y notificaciones de todos los sorteos que serán debidamente validados, variedad de productos, garantía, medios de pago sencillos, bonificaciones.<br>This business project has been developed with the purpose of meeting the needs of people who are users of electronic commerce by offering an innovative way to obtain products for a minimal cost.
The objective of this plan is to bring products closer to consumers who have the desire to have them but for various reasons have not been able to get them.
In this proposal developed to fulfill the desire of our chosen client, we have worked on identifying their main motivations when buying online such as: saving time, convenience and searching for the best price, which was contrasted with the main problems they face when making purchases in a physical space: prolonged waiting to be attended and paid, high prices of products and poor attention. In addition, it was possible to highlight their fears regarding the experience of shopping online.
The business project raises the service of raffling products of brands recognized by our client, for which raffle tickets will be sold for a set time for each draw, this will be done through an agile and reliable virtual platform where the customer can buy as many options as he wants in order to win the raffle. Our value proposition proposes sending the product free of cost, live broadcasts and notifications of all the draws that will be duly validated, variety of products, guarantee, simple means of payment, bonuses.<br>Trabajo de investigación
15
Kharel, Subash. "POTHOLE DETECTION USING DEEP LEARNING AND AREA ASSESSMENT USING IMAGE MANIPULATION." OpenSIUC, 2021. https://opensiuc.lib.siu.edu/theses/2825.
Full textAbstract:
Every year, drivers are spending over 3 billions to repair damage on vehicle caused by potholes. Along with the financial disaster, potholes cause frustration in drivers. Also, with the emerging development of automated vehicles, road safety with automation in mind is being a necessity. Deep Learning techniques offer intelligent alternatives to reduce the loss caused by spotting pothole. The world is connected in such a way that the information can be shared in no time. Using the power of connectivity, we can communicate the information of potholes to other vehicles and also the department of Transportation for necessary action. A significant number of research efforts have been done with a view to help detect potholes in the pavements. In this thesis, we have compared two object detection algorithms belonging to two major classes i.e. single shot detectors and two stage detectors using our dataset. Comparing the results in the Faster RCNN and YOLOv5, we concluded that, potholes take a small portion in image which makes potholes detection with YOLOv5 less accurate than the Faster RCNN, but keeping the speed of detection in mind, we have suggested that YOLOv5 will be a better solution for this task. Using the YOLOv5 model and image processing technique, we calculated approximate area of potholes and visualized the shape of potholes. Thus obtained information can be used by the Department of Transportation for planning necessary construction tasks. Also, we can use these information to warn the drivers about the severity of potholes depending upon the shape and area.
16
Hasanaj, Enis, Albert Aveler, and William Söder. "Cooperative edge deepfake detection." Thesis, Jönköping University, JTH, Avdelningen för datateknik och informatik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-53790.
Full textAbstract:
Deepfakes are an emerging problem in social media and for celebrities and political profiles, it can be devastating to their reputation if the technology ends up in the wrong hands. Creating deepfakes is becoming increasingly easy. Attempts have been made at detecting whether a face in an image is real or not but training these machine learning models can be a very time-consuming process. This research proposes a solution to training deepfake detection models cooperatively on the edge. This is done in order to evaluate if the training process, among other things, can be made more efficient with this approach. The feasibility of edge training is evaluated by training machine learning models on several different types of iPhone devices. The models are trained using the YOLOv2 object detection system. To test if the YOLOv2 object detection system is able to distinguish between real and fake human faces in images, several models are trained on a computer. Each model is trained with either different number of iterations or different subsets of data, since these metrics have been identified as important to the performance of the models. The performance of the models is evaluated by measuring the accuracy in detecting deepfakes. Additionally, the deepfake detection models trained on a computer are ensembled using the bagging ensemble method. This is done in order to evaluate the feasibility of cooperatively training a deepfake detection model by combining several models. Results show that the proposed solution is not feasible due to the time the training process takes on each mobile device. Additionally, each trained model is about 200 MB, and the size of the ensemble model grows linearly by each model added to the ensemble. This can cause the ensemble model to grow to several hundred gigabytes in size.
17
Mikulský, Petr. "Detekce pohybujících se objektů ve videu s využitím neuronových sítí." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2021. http://www.nusl.cz/ntk/nusl-442377.
Full textAbstract:
This diploma thesis deals with the detection of moving objects in a video recording using neural networks. The aim of the thesis was to detect road users in video recordings. Pre-trained YOLOv5 object detection model was used for a practical part of the thesis. As part of the solution, an own dataset of traffic road video recordings was created and annotated with following classes: a car, a bus, a van, a motorcycle, a truck and a trailer truck. Final version of this dataset comprise 5404 frames and 6467 annotated objects in total. After training, the YOLOv5 model achieved 0.995 mAP, 0.995 precision and 0.986 recall on the dataset. All steps leading to the final form of the dataset are described in the conclusion chapter.
18
Marmayohan, Nivethan, and Abdirahman Farah. "Scene analysis using Tensorflow & YOLO algorithms on Raspberry pi 4." Thesis, Högskolan i Halmstad, Akademin för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-45540.
Full textAbstract:
Objektdetektion är en av de viktigaste mjukvarukomponenterna i nästa generation trafikövervakning. Deep learnings-algoritmer för objektdetektion, exempelvis YOLO (You Only Look Once), är snabba och noggranna algoritmer i realtid. Realtidsdetektion och igenkänning av objekt är viktiga uppgifter för bildbehandling. I denna studie presenteras ett inbäddat system för detektion och igenkänning av objekt i normal videohastighet (realtid). Indata är följaktligen en videoström som härstammar från en trafikmiljö i Halmstad. Hårdvaran är Raspberry pi 4 i vilken programvarupaketen Tensorflow, YOLO samt träningskonceptet ”Transfer learning” har implementerats. Resultaten presenteras i form av kvantifiering av realtidskörning på FPS (frames per second), detektion noggrannhet, CPU-temperatur och CPU-frekvens i olika experiment. En slutsats är att Raspberry pi 4 kan utföra objektklassificering och detektion med hög noggrannhet i en del scenarier för trafikövervakning med YOLO-algoritmer. Ett scenario för att klassificera objekt med långsam hastighet till exempel gående, skulle det vara genomförbar med att klassificera och detektera med en högnoggrannhet. För objekt med höghastighet som bilar och cyklister så har Raspberry pi 4 svårt att detektera och klassificera objekter.<br>Object detection is one of the essential software components in the next generation of traffic monitoring. Real-time detection and recognition of objects are essential tasks for image processing. Therefore, deep learning algorithms for object detection such as YOLO (You Only Look Once) are increasingly used in image analysis, since they run in normal video frame rate (real-time) and are reasonably accurate. This study presents an embedded system and its results for detecting and recognizing objects in real-time. Results are based on a video stream originating from a traffic environment in the city of Halmstad (Sweden). The embedded system is implemented in Raspberry pi 4 using the software Tensorflow and different deep learning algorithms of the YOLO software package. Real-time analyses on frames per second, accuracy in mean average precision, CPU temperature, and CPU frequency are reported for experiments comprising transfer learning. A main conclusion is that Raspberry pi 4 can perform object classification and detection with high accuracy in certain scenarios for traffic monitoring with YOLO algorithms. For example, classifying objects with the speed of a pedestrian would be feasible with classifying and detecting with high accuracy. On the other hand, with high-speed objects such as cars and cyclists, it is a more challenging task for Raspberry pi 4 to detect and classify objects.
19
Al, Hakim Ezeddin. "3D YOLO: End-to-End 3D Object Detection Using Point Clouds." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-234242.
Full textAbstract:
For safe and reliable driving, it is essential that an autonomous vehicle can accurately perceive the surrounding environment. Modern sensor technologies used for perception, such as LiDAR and RADAR, deliver a large set of 3D measurement points known as a point cloud. There is a huge need to interpret the point cloud data to detect other road users, such as vehicles and pedestrians. Many research studies have proposed image-based models for 2D object detection. This thesis takes it a step further and aims to develop a LiDAR-based 3D object detection model that operates in real-time, with emphasis on autonomous driving scenarios. We propose 3D YOLO, an extension of YOLO (You Only Look Once), which is one of the fastest state-of-the-art 2D object detectors for images. The proposed model takes point cloud data as input and outputs 3D bounding boxes with class scores in real-time. Most of the existing 3D object detectors use hand-crafted features, while our model follows the end-to-end learning fashion, which removes manual feature engineering. 3D YOLO pipeline consists of two networks: (a) Feature Learning Network, an artificial neural network that transforms the input point cloud to a new feature space; (b) 3DNet, a novel convolutional neural network architecture based on YOLO that learns the shape description of the objects. Our experiments on the KITTI dataset shows that the 3D YOLO has high accuracy and outperforms the state-of-the-art LiDAR-based models in efficiency. This makes it a suitable candidate for deployment in autonomous vehicles.<br>För att autonoma fordon ska ha en god uppfattning av sin omgivning används moderna sensorer som LiDAR och RADAR. Dessa genererar en stor mängd 3-dimensionella datapunkter som kallas point clouds. Inom utvecklingen av autonoma fordon finns det ett stort behov av att tolka LiDAR-data samt klassificera medtrafikanter. Ett stort antal studier har gjorts om 2D-objektdetektering som analyserar bilder för att upptäcka fordon, men vi är intresserade av 3D-objektdetektering med hjälp av endast LiDAR data. Därför introducerar vi modellen 3D YOLO, som bygger på YOLO (You Only Look Once), som är en av de snabbaste state-of-the-art modellerna inom 2D-objektdetektering för bilder. 3D YOLO tar in ett point cloud och producerar 3D lådor som markerar de olika objekten samt anger objektets kategori. Vi har tränat och evaluerat modellen med den publika träningsdatan KITTI. Våra resultat visar att 3D YOLO är snabbare än dagens state-of-the-art LiDAR-baserade modeller med en hög träffsäkerhet. Detta gör den till en god kandidat för kunna användas av autonoma fordon.
20
Yevsieiev, V., O. Tokarieva, and S. Starikova. "Research of Object Recognition in the Workspace of A Mobile Robot Based on the Yolo Method." Thesis, Кременчуцький національний університет імені Михайла Остроградського, 2022. https://openarchive.nure.ua/handle/document/20421.
Full textAbstract:
One of the hallmarks of the advent of the new industrial revolution, Industry 5.0, is the synergy between autonomous robots and humans. All this is possible with the introduction of collaborative robots into all spheres of human activity.
21
Pini, Mattia. "Sviluppo di un Prototipo di Video Sorveglianza Indoor con Tecnologie YOLO ed OpenCV." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18178/.
Full textAbstract:
In questa tesi viene effettuato uno studio sulla reale efficienza delle Reti Neurali Artificiali e più in particolare delle Convolutional Neural Network nel settore del riconoscimento immagini e della velocità con cui è possibile ottenere informazioni dettagliate da esse.
Viene presentato quindi un Prototipo di Video Sorveglianza per Ambienti Indoor che sfrutta queste tecnologie in maniera efficiente coniugando lo stato dell'arte per il riconoscimento degli oggetti con algoritmi noti per il riconoscimento facciale.
Con un attento studio si è dimostrato inoltre perchè la rete scelta è risultata ottimale per l'obiettivo della tesi, mostrandone peculiarità e prestazioni.
Vengono inoltre affrontate le problematiche che gli algoritmi di riconoscimento facciale classici possiedono, di come l'inclinazione di un volto possa portare a un non riconoscimento della figura dello stesso, e le soluzioni proposte.
Importante inoltre la scelta del dataset per il riconoscimento facciale, poichè una scelta errata potrebbe portare a falsi positivi.
Il risultato è un sistema che attraverso acquisizione immagini da videocamera e attraverso l'uso di reti neurali riesce a verificare se un determinato oggetto o una persona sono realmente presenti o meno all'interno di un ambiente.
22
Sommer, Ted Robert. "The aquatic ecology of the Yolo Bypass floodplain : evaluation at the species and landscape scales /." For electronic version search Digital dissertations database. Restricted to UC campuses. Access is free to UC campus dissertations, 2002. http://uclibs.org/PID/11984.
Full text
23
Головатий, Ігор Богданович, та Ihor Holovatiy. "Комп'ютерна система на основі нейромережі для виявлення зіткнення автомобілів". Bachelor's thesis, Тернопільський національний технічний університет імені Івана Пулюя, 2021. http://elartu.tntu.edu.ua/handle/lib/35429.
Full textAbstract:
Кваліфікаційна робота присвячена розробці системи, що дозволяє визначати серйозні автомобільні зіткнення на відеоряді, записаному камерами дорожнього спостереження. Проведено огляд існуючих систем детектування дорожньо-транспортних пригод. Запропоновано спосіб вирішення проблеми за допомогою нейромережі, Наведено опис алгоритму детектування автокатастроф, здійснено пошук і підготовка вибірки. Проаналізовано алгоритми детектування об'єктів. Для детектування автомобіля на відео вибрано YOLOv3-детектор.
Здійснено порівняння детекторів об'єктів для з'ясування впливу на кінцеву ефективність роботи системи в цілому. Реалізовано алгоритм детектування зіткнення автомобілів в режимі реального часу. Розроблювана система була протестована на реальних даних для визначення зіткнень автомобілів. Отримані практичні результати дозволяють стверджувати про ефективність використання розробки..<br>The qualification work deals with the development of a system that allows you to identify serious car collisions on a video recorded by surveillance cameras. A review of existing road accident detection systems was conducted. The way of the decision of a problem by means of a neural network is offered, the description of algorithm of detection of car accidents is given, search and preparation of sampling is carried out. Object detection algorithms are analyzed. A YOLOv3 detector is selected to detect the car on video.
The object detectors are compared to determine the impact on the final efficiency of the system as a whole. The algorithm of car collision detection in real time is implemented. The developed system was tested on real data to determine car collisions. The obtained practical results allow us to assert the effectiveness of the development.<br>Вступ. 1. Аналіз технічного завдання. 1.1 Огляд систем детектування ДТП. 1.2. Поняття
ДТП. 2. Проектна частина. 2.1. Згорткові нейронні мережі. 2.2. Спосіб вирішення проблеми.
за допомогою згорткових нейронних мереж. 2.3. Опис алгоритму детектування
автокатастроф. 2.4. Пошук і підготовка вибірки. 2.5. Аналіз алгоритмів детектування об'єктів.
3. Практична частина. 3.1. Порівняння детекторів об'єктів для з'ясування впливу на кінцеву
ефективність роботи системи в цілому. 3.2. Реалізація алгоритму детектування зіткнення
автомобілів в режимі реального часу. 3.3. Отримані результати експериментів.
4. Безпека життєдіяльності, основи хорони праці. Висновки. Список використаних джерел
24
Nikue, Amassah Djahlin. "Analyse vidéo pour la détection, le suivi et la reconnaissance du comportement pour l'animal en situation d'élevage." Electronic Thesis or Diss., Orléans, 2024. http://www.theses.fr/2024ORLE1011.
Full textAbstract:
La reconnaissance d'activités, également connue sous le nom de reconnaissance d'actions, est un domaine de recherche en vision par ordinateur et en apprentissage automatique, avec diverses applications. L'application la plus courante est l'identification et la compréhension des activités humaines à partir de données visuelles, telles que des images ou des vidéos. Les techniques de reconnaissance d'actions peuvent être appliquées également à la surveillance du bétail, où elles contribuent à améliorer le bien-être des animaux, la productivité et les pratiques de gestion agricole. Ainsi, les travaux réalisés dans ce document se situent dans le cadre de l'analyse vidéo pour la détection, le suivi et la reconnaissance du comportement animal en situation d'élevage. Ces travaux sont réalisés au sein de ANIMOV « Animal Movements Observation from Videos », un projet de recherche pluridisciplinaire mis en œuvre sur la période 2019-2023 par un consortium régional en Centre-Val-de-Loire. Ce projet porte principalement sur deux espèces animales : les éléphants et les chèvres. Dans ce mémoire, nos recherches portent sur l'analyse des activités chez les chèvres. Afin de construire notre système d'analyse du comportement, nous avons mis en place un système de détection et de suivi d'objets. Pour la détection nous avons testé et comparé deux méthodes populaires de la littérature : YOLOv4 et Faster R-CNN, sur des bases de données créées par nos soins. Parmi les deux méthodes de détection, YOLOv4 présente de meilleures performances en terme de précision moyenne et est 2.5 fois plus rapide que le Faster R-CNN. Pour le suivi des chèvres, nous avons testé et comparé également deux méthodes populaires de la littérature : SORT et Deep SORT. L'évaluation des deux méthodes de suivi sur les vidéos de test montre une légère amélioration de Deep SORT par rapport à SORT en terme d'association des données. Cependant, SORT reste plus rapide et plus adapté à un système temps réel. Le système de détection et de suivi mis en place, nous permet de réaliser, en temps réel, l'analyse de l'activité générale du troupeau, avec des indicateurs assez proches de la réalité. La principale faiblesse dans notre système est la perte de détection sur certaines images de la vidéo, qui entraîne des échecs dans le suivi. Ainsi, pour améliorer les performances, nous avons proposé une approche qui fusionne les informations des détections précédentes et de l'image courante, dans une nouvelle architecture de détection (YOLOX), afin de mieux détecter tous les objets sans perdre les anciens<br>Activity recognition, also known as action recognition, is a field of research in computer vision and machine learning, with a variety of applications. One of the most common applications is the identification and understanding of human activities from visual data, such as images or videos. Action recognition techniques can also be applied to livestock monitoring, where they can help improve animal welfare, productivity, and farm management practices. Thus, the work conducted in this document falls within the context of video analysis for the detection, monitoring, and recognition of animal behavior in livestock situations. This work is being achieved within ANIMOV "Animal Movements Observation from Videos", a multidisciplinary research project being implemented over the period 2019-2023 by a regional consortium in Centre-Val-de-Loire. This project concerns two main animal species: elephants and goats. In this thesis, our research focuses on activity analysis for goats. We have built an object detection and tracking system to implement our behavior analysis system. For detection, we tested and compared two popular methods from the literature: YOLOv4 and Faster R-CNN, on self-created datasets. Of the two detection methods, YOLOv4 performs better in average accuracy and is 2.5 times faster than Faster R-CNN. For goat tracking, we also tested and compared two popular methods from the literature: SORT and Deep SORT. Evaluation of both tracking methods on test videos shows a slight improvement of Deep SORT over SORT regarding data association. However, SORT is faster and better suited to a real-time system. The detection and tracking system we have set up enables us to analyze the general activity of the livestock in real-time, with indicators that are fairly close to reality. The main limitation of our system is the loss of detection on certain video images, which leads to tracking failures. So, to improve the performance, we proposed an approach that merges information from previous detections and the current image, in a new detection architecture (YOLOX), to better detect all objects without losing the old ones
25
Noman, Md Kislu. "Deep learning-based seagrass detection and classification from underwater digital images." Thesis, Edith Cowan University, Research Online, Perth, Western Australia, 2023. https://ro.ecu.edu.au/theses/2648.
Full textAbstract:
Deep learning is the most popular branch of machine learning and has achieved great success in many real-life applications. Deep learning algorithms, in particular Convolutional Neural Networks (CNNs), have rapidly become a method of choice for analysing seagrass image data. Deep learning-based seagrass classification and detection are very challenging due to the limited labelled data, intraclass similarities between species, lighting conditions, and complex shapes and structures in the underwater environment, which make them different from large-scale dataset objects. The light propagating through water is attenuated and scattered selectively, causing severe effects on the quality of underwater images. Besides low contrast, colour distortion and bright specks affect the quality of underwater images. In this thesis, we focus on the problem of single to multi-species seagrass classification and detection from underwater digital images. We investigated the existing seagrass classification and detection models and systematically attempted to improve the performance of seagrass classification and detection by developing different models on several seagrass datasets.
CNNs are a class of artificial neural networks commonly used in deep learning architectures for image recognition, object localization or mapping tasks. CNN-based models are gaining popularity in seagrass identification or mapping due to their automatic feature extraction ability and higher performance over machine learning techniques. Making a deep learning-based model for all domain users (not only computer vision experts or engineers) is also a challenging task because CNNs development requires architectural engineering and hyperparameter tuning.
This thesis investigates the effective development of CNNs on multi-species seagrass datasets to minimise the requirement of architectural engineering and manual hyperparameter tuning for CNN models. This thesis develops a novel metaheuristic algorithm called Opposition-based Flow Direction Algorithm (OFDA) by leveraging the power of the Opposition-based learning technique into the Flow Direction Algorithm to tune and automate the development of CNNs. The proposed deep neuroevolutionary algorithm (OFDA-CNN) outperformed other eight popular optimisation-based neuroevolutionary algorithms on a newly developed multi-species seagrass dataset. The OFDA-CNN algorithm also outperformed the state-of-the-art multi-species seagrass classification performances on publicly available seagrass datasets. This thesis also proposes another novel metaheuristic algorithm called Boosted Atomic Orbital Search (BAOS) to optimize the architecture and tune the hyperparameter of a CNN. The proposed BAOS algorithm improved the search capability of the original version of the Atomic Orbital Search algorithm by incorporating the L´evy flight technique. The optimized deep neuroevolutionary (BAOS-CNN) algorithm achieved the highest accuracy among seven popular optimisation-based CNNs. The BAOS-CNN algorithm also outperformed the state-of-the-art multi-species seagrass classification performances.
This thesis proposes also a two-stage semi-supervised framework for leveraging huge unlabelled seagrass data. We propose an EfficientNet-B5-based semi-supervised framework that leverages a large collection of unlabelled seagrass data with the guidance of a small, labelled seagrass dataset. We introduced a multi-species seagrass classifier based on EfficientNet-B5 that outperformed the state-of-the-art multi-species seagrass classification performances. This thesis also developed a two and half times larger multi-species dataset than the largest publicly available ‘DeepSeagrass’ dataset.
To evaluate the performance of all the proposed models, we trained and tested them on the newly developed and some publicly available challenging seagrass datasets. Our rigorous experiments demonstrated how our models were capable of producing state-of-the-art performances of seagrass classification and detection in both single and multi-species scenarios.
26
Güven, Jakup. "Investigating techniques for improving accuracy and limiting overfitting for YOLO and real-time object detection on iOS." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-19999.
Full textAbstract:
I detta arbete genomförs utvecklingen av ett realtids objektdetekteringssystem för iOS. För detta ändamål används YOLO, en ett-stegs objektdetekterare och ett s.k. ihoplänkat neuralt nätverk vilket åstadkommer betydligt bättre prestanda än övriga realtidsdetek- terare i termer av hastighet och precision. En dörrdetekterare baserad på YOLO tränas och implementeras i en systemutvecklingsprocess. Maskininlärningsprocessen sammanfat- tas och praxis för att undvika överträning eller “overfitting” samt för att öka precision och hastighet diskuteras och appliceras. Vidare genomförs en rad experiment vilka pekar på att dataaugmentation och inkludering av negativ data i ett dataset medför ökad precision. Hyperparameteroptimisering och kunskapsöverföring pekas även ut som medel för att öka en objektdetekringsmodells prestanda. Författaren lyckas öka modellens mAP, ett sätt att mäta precision för objektdetekterare, från 63.76% till 86.73% utifrån de erfarenheter som dras av experimenten. En modells tendens för överträning utforskas även med resultat som pekar på att träning med över 300 epoker rimligen orsakar en övertränad modell.<br>This paper features the creation of a real time object detection system for mobile iOS using YOLO, a state-of-the-art one stage object detector and convoluted neural network far surpassing other real time object detectors in speed and accuracy. In this process an object detecting model is trained to detect doors. The machine learning process is outlined and practices to combat overfitting and increasing accuracy and speed are discussed. A series of experiments are conducted, the results of which suggests that data augmentation, including negative data in a dataset, hyperparameter optimisation and transfer learning are viable techniques in improving the performance of an object detection model. The author is able to increase mAP, a measurement of accuracy for object detectors, from 63.76% to 86.73% based on the results of experiments. The tendency for overfitting is also explored and results suggest that training beyond 300 epochs is likely to produce an overfitted model.
27
Сторожук, Б. В. "Система розпізнавання об‘єктів на ділянках автошляху за допомогою оглядових камер відеоспостережень". Thesis, Чернігів, 2020. http://ir.stu.cn.ua/123456789/23420.
Full textAbstract:
Сторожук, Б. В. Система розпізнавання об‘єктів на ділянках автошляху за допомогою оглядових камер відеоспостережень : випускна кваліфікаційна робота : 123 "Комп’ютерна інженерія" / Б. В. Сторожук ; керівник роботи Є. В. Нікітенко ; НУ "Чернігівська політехніка", кафедра інформаційних і комп’ютерних систем. – Чернігів, 2020. – 106 с.<br>Об'єктом розробки була інтелектуальна система розпізнавання об‘єктів на
ділянках автошляху за допомогою оглядових камер відеоспостережень.
Метою кваліфікаційної роботи є створення системи, яка зможе прийняти,
обробити та розпізнати об’єкти на зображенні. Під час розробки та проектування,
були розглянуті ШНМтрументи для створення системи та їх недоліки.
Результати даної роботи можуть бути використанні для отримання
статистичних даних по кількості та типу транспорту на ділянці автошляху.
Можливе подальше вдосконалення системи шляхом покращення методів
розпізнавання об’єктів на зображеннях використовуючи нейронну мережу
характерно новітньої архітектури, що дозволяє у свою чергу покращити метод
класифікації та підвищити показник точності розпізнавання об‘єктів на ділянках
автошляху<br>The object of the development was an intelligent system for recognition of
objects on the road sections with the help of overview cameras of video surveillance.
The purpose of qualifying work is to create a system that can receive, process
and recognize objects in an image. During development and design, the tools for
creating the system and their disadvantages were considered.
The results of this work can be used for obtaining statistics on the amount and
type of transport on the road section.
Possible further Improvement of the system by improving the methods for
recognizing objects to be saved using the neural venter is characteristic of the latest
architecture, which allows it to improve its classification method in its queue and
improve the accuracy of the object recognition on the road sections.
28
Alsalehy, Ahmad, and Ghada Alsayed. "Scenanalys av trafikmiljön." Thesis, Högskolan i Halmstad, Akademin för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-44936.
Full textAbstract:
Antalet vägtrafikanter ökar varje år, och med det ökar trängseln. Man har därför gjort undersökningar med hjälp av objektdetektionsalgoritmer på videoströmmar. Genom att analysera data resultat är det möjligt att bygga en bättre infrastruktur, för att minska trafikstockning samt olyckor. Data som analyseras kan till exempel vara att räkna hur många trafikanter som vistas på en viss väg (Slottsbron i Halmstad) under en viss tid. Detta examensarbete undersöker teoretiskt hur en YOLO algoritm samt TensorFlow kan användas för att detektera olika trafikanter. Utvärderingsmetoder som användes i projektet för att få resultatet och dra slutsatser är mAP, träning och testning av egna och andras YOLO modeller samt övervakning av FPS- och temperatur-värden. För att möjliggöra detekteringen av trafikflöde i realtid nyttjades Jetson nano toolkit. Flera olika jämförelser har skapats för att avgöra vilken YOLO modell som är lämpligast. Resultaten från tester av olika YOLO modeller visar att YOLO-TensorFlows implementationer kan detektera trafikanter med en godtagbar noggrannhet. Slutsatsen är att Jetson nano har tillräckligt med processorkraft för att detektera olika trafikanter i realtid med hjälp av original YOLO implementation. Metoderna för att detektera trafikanter är standard och fungerande för analysering av trafikflöden.Testning av mer varierande trafikmiljö under längre tidsperioder krävs för att ytterligare verifiera om Jetson nanos lämplighet.
29
Стахив, Ю. Н., та М. Г. Заворотна. "Классификация объектов в режиме реального времени". Thesis, ХНУРЕ, 2019. http://openarchive.nure.ua/handle/document/8478.
Full textAbstract:
An important and urgent task in machine learning is the introduction and optimization of the technology for classifying objects in real time. For this project, completely local solutions were needed, for none of the existing ones in this area met the requirements of the planned one. Yolo - is an advanced object detection system in real time. It has a wide variety of configurations for any requirements. One of the tasks was the choice of configuration, which we will adapt to meet the objectives of the project. A suitable one was found among them, one that could work quickly even on smartphones or the Raspberry Pi - Tiny YOLO.
30
Mehta, Rinav. "COMPARISON OF REFUSE DECOMPOSITION IN THE PRESENCE AND ABSENCE OF LEACHATE RECIRCULATION AT THE YOLO COUNTY, CALIFORNIA TEST CELLS." NCSU, 2000. http://www.lib.ncsu.edu/theses/available/etd-20001219-110441.
Full textAbstract:
<p>MEHTA, RINAV C. Comparison of Refuse Decomposition in the Presence and Absence of Leachate Recirculation at the Yolo County, California Test Cells. (Under the direction of Morton A. Barlaz.)A side by side comparison of two 8,000-metric ton test cells, one operated with (enhanced) and one without (control) leachate recirculation, was performed to evaluate the effects of leachate recirculation on refuse decomposition at Yolo County, CA. After about three years of operation, refuse was excavated in three borings of the enhanced cell (E1, E2 and E3) and two borings in the control cell (C1 and C2). The objective of this study was to present a comparison of test cell performance with respect to moisture content, settlement, methane production and solids decomposition. Refuse moisture content data show that leachate recirculation resulted in an increase in refuse moisture content, but also show that the refuse in the enhanced cell was not uniformly wet. The average moisture content in E1, E2 and E3 was 38.8, 31.7 and 34.8%, respectively, while the average moisture content in C1 and C2 was 14.6 and 19.2%, respectively. The extent of decomposition was determined by the biochemical methane potential (BMP) and the ratio of cellulose plus hemicellulose to lignin ((C+H)/L). BMP analysis showed the average methane potential in the enhanced and control cells to be 24.0 and 30.9 mL CH4/dry-gm, respectively, and the (C+H)/L of 1.09 and 1.44. These data correlates well with the measured methane production in the enhanced and control cell of 54 and 26 L CH4/wet-kg, respectively. Thus, laboratory and field data shows more decomposition in the enhanced cell relative to the control cell. While the overall averages may not appear significantly different, a closer look at the performance of E1 shows a difference in both moisture content and solids decomposition when compared to the control cell. Hence, the extent of decomposition varies within the enhanced cell. The sampling program conducted for the Yolo County test cells, in concert with data on settlement, methane production and the volume of liquid actually recycled, represents perhaps the most complete set of data available to date on a field-scale leachate recirculation landfill.<P>
31
Sun, Ruiwen. "Detecting Faulty Tape-around Weatherproofing Cables by Computer Vision." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-272108.
Full textAbstract:
More cables will be installed owing to setting up more radio towers when it comes to 5G. However, a large proportion of radio units are constructed high in the open space, which makes it difficult for human technicians to maintain the systems. Under these circumstances, automatic detections of errors among radio cabinets are crucial. Cables and connectors are usually covered with weatherproofing tapes, and one of the most common problems is that the tapes are not closely rounded on the cables and connectors. This makes the tape go out of the cable and look like a waving flag, which may seriously damage the radio systems. The thesis aims at detecting this flagging-tape and addressing the issues. This thesis experiments two methods for object detection, the convolutional neural network as well as the OpenCV and image processing. The former uses YOLO (You Only Look Once) network for training and testing, while in the latter method, the connected component method is applied for the detection of big objects like the cables and line segment detector is responsible for the flagging-tape boundary extraction. Multiple parameters, structurally and functionally unique, were developed to find the most suitable way to meet the requirement. Furthermore, precision and recall are used to evaluate the performance of the system output quality, and in order to improve the requirements, larger experiments were performed using different parameters. The results show that the best way of detecting faulty weatherproofing is with the image processing method by which the recall is 71% and the precision reaches 60%. This method shows better performance than YOLO dealing with flagging-tape detection. The method shows the great potential of this kind of object detection, and a detailed discussion regarding the limitation is also presented in the thesis.<br>Fler kablar kommer att installeras på grund av installation av fler radiotorn när det gäller 5G. En stor del av radioenheterna är dock konstruerade högt i det öppna utrymmet, vilket gör det svårt för mänskliga tekniker att underhålla systemen. Under dessa omständigheter är automatiska upptäckter av fel bland radioskåp avgörande. Kablar och kontakter täcks vanligtvis med väderbeständiga band, och ett av de vanligaste problemen är att banden inte är rundade på kablarna och kontakterna. Detta gör att tejpen går ur kabeln och ser ut som en viftande flagga, vilket allvarligt kan skada radiosystemen. Avhandlingen syftar till att upptäcka detta flaggband och ta itu med frågorna. Den här avhandlingen experimenterar två metoder för objektdetektering, det invändiga neurala nätverket såväl som OpenCV och bildbehandling. Den förstnämnda använder YOLO (You Only Look Once) nätverk för träning och testning, medan i den senare metoden används den anslutna komponentmetoden för detektering av stora föremål som kablarna och linjesegmentdetektorn är ansvarig för utvinning av bandbandgränsen. Flera parametrar, strukturellt och funktionellt unika, utvecklades för att hitta det mest lämpliga sättet att uppfylla kravet. Dessutom används precision och återkallande för att utvärdera prestandan för systemutgångskvaliteten, och för att förbättra kraven utfördes större experiment med olika parametrar. Resultaten visar att det bästa sättet att upptäcka felaktigt väderbeständighet är med bildbehandlingsmetoden genom vilken återkallelsen är 71% och precisionen når 60%. Denna metod visar bättre prestanda än YOLO som hanterar markering av flaggband. Metoden visar den stora potentialen för denna typ av objektdetektering, och en detaljerad diskussion om begränsningen presenteras också i avhandlingen.
32
Матлахов, В. І. "Інтелектуальна система розпізнавання образів у Web-контексті". Master's thesis, Сумський державний університет, 2020. https://essuir.sumdu.edu.ua/handle/123456789/82177.
Full text
33
Zeng, Xing. "One Stage Fine- Grained Classification." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301055.
Full textAbstract:
Fine- grained Visual Classification (FGVC) is a rapidly growing field in image classification. However, it is a challenging task due to subcategories sharing subtle differences. Existing approaches tackle this problem by firstly extracting discriminative regions using part localization or object localization or Region Proposal Networks (RPN), then applying Convolutional Neural Network (CNN) or SVM classifier on those regions. In this work, with the purpose of simplifying the above complicated pipeline while keeping high accuracy, we get inspired by the one- stage object detection model YOLO and design a one- stage end- to- end object detector model for FGVC. Specifically, we apply YOLOv5 as a baseline model and replace its Path Aggregation Network (PANet) structure with Weighted Bidirectional Feature Pyramid Network (BiFPN) structure to efficiently fuse information from different resolutions. We conduct experiments on different classification and localization weight ratios to guide choosing loss weights in different scenarios. We have proved the viability of the one- stage detector model YOLO on FGVC, which has 87.1 % top1 accuracy on the FGVC dataset CUB2002011. Furthermore, we have designed a more accurate one- stage model, achieving 88.1 % accuracy, which is the most accurate method compared to the existing localization state- of- the- art models. Finally, we have shown that the higher the classification loss weight, the faster the convergence speed, while increasing slightly localization loss weight can help achieve a more accurate classification but resulting in slower convergence.<br>Finkornad visuell klassificering (FGVC) är ett snabbt växande fält inom bildklassificering. Det är dock en utmanande uppgift på grund av underkategorier som delar subtila skillnader. Befintliga tillvägagångssätt hanterar detta problem genom att först extrahera diskriminerande regioner med dellokalisering eller objektlokalisering eller Region Proposal Networks (RPN) och sedan tillämpa Convolutional Network eller SVM- klassificering på dessa regioner. I det här arbetet, med syftet att förenkla ovanstående komplicerade rörledning samtidigt som vi håller hög noggrannhet, blir vi inspirerade av enstegs objektdetekteringsmodellen YOLO och designar en enstegs end- to- end objektdetektormodell för FGVC. Specifikt tillämpar vi YOLOv5 som basmodell och ersätter dess Path Aggregation Network (PANet) struktur med en viktad dubbelriktad funktionspyramidnätverk (BiFPN) struktur för att effektivt smälta information från olika upplösningar. Vi utför experiment på olika klassificerings och lokaliseringsviktsförhållanden för att vägleda valet av förlustvikter i olika scenarier. Vi har bevisat livskraften hos enstegsdetektormodellen YOLO på FGVC, som har 87,1 % topp1noggrannhet i FGVC- dataset CUB2002011. Dessutom har vi utformat en mer exakt enstegsmodell som uppnår 88,1 % noggrannhet, vilket är den mest exakta metoden jämfört med befintliga lokaliseringsmodeller. Slutligen har vi visat att ju högre klassificeringsförlustvikten är, desto snabbare är konvergenshastigheten, medan en ökning av lokaliseringsförlustvikten ökar något kan bidra till en mer exakt klassificering men resulterar i långsammare konvergens.
34
Uhrín, Peter. "Počítání unikátních aut ve snímcích." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2021. http://www.nusl.cz/ntk/nusl-445493.
Full textAbstract:
Current systems for counting cars on parking lots usually use specialized equipment, such as barriers at the parking lot entrance. Usage of such equipment is not suitable for free or residential parking areas. However, even in these car parks, it can help keep track of their occupancy and other data. The system designed in this thesis uses the YOLOv4 model for visual detection of cars in photos. It then calculates an embedding vector for each vehicle, which is used to describe cars and compare whether the car has changed over time at the same parking spot. This information is stored in the database and used to calculate various statistical values like total cars count, average occupancy, or average stay time. These values can be retrieved using REST API or be viewed in the web application.
35
Charvát, Michal. "System for People Detection and Localization Using Thermal Imaging Cameras." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2020. http://www.nusl.cz/ntk/nusl-432478.
Full textAbstract:
V dnešním světě je neustále se zvyšující poptávka po spolehlivých automatizovaných mechanismech pro detekci a lokalizaci osob pro různé účely -- od analýzy pohybu návštěvníků v muzeích přes ovládání chytrých domovů až po hlídání nebezpečných oblastí, jimiž jsou například nástupiště vlakových stanic. Představujeme metodu detekce a lokalizace osob s pomocí nízkonákladových termálních kamer FLIR Lepton 3.5 a malých počítačů Raspberry Pi 3B+. Tento projekt, navazující na předchozí bakalářský projekt "Detekce lidí v místnosti za použití nízkonákladové termální kamery", nově podporuje modelování komplexních scén s polygonálními okraji a více termálními kamerami. V této práci představujeme vylepšenou knihovnu řízení a snímání pro kameru Lepton 3.5, novou techniku detekce lidí používající nejmodernější YOLO (You Only Look Once) detektor objektů v reálném čase, založený na hlubokých neuronových sítích, dále novou automaticky konfigurovatelnou termální jednotku, chráněnou schránkou z 3D tiskárny pro bezpečnou manipulaci, a v neposlední řadě také podrobný návod instalace detekčního systému do nového prostředí a další podpůrné nástroje a vylepšení. Výsledky nového systému demonstrujeme příkladem analýzy pohybu osob v Národním muzeu v Praze.
36
Kohmann, Erich. "Tecniche di deep learning per l'object detection." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19637/.
Full textAbstract:
L’object detection è uno dei principali problemi nell’ambito della computer vision. Negli ultimi anni, con l’avvento delle reti neurali e del deep learning, sono stati fatti notevoli progressi nei metodi per affrontare questo problema.
Questa tesi intende fornire una rassegna dei principali modelli di object detection basati su deep learning, di cui si illustrano le caratteristiche fondamentali e gli elementi che li contraddistinguono dai modelli precedenti.
Dopo un infarinatura iniziale sul deep learning e sulle reti neurali in genere, vengono presentati i modelli caratterizzati da tecniche innovative che hanno portato ad un miglioramento significativo, sia nella precisione e nell’accuratezza delle predizioni, che in termini di consumo di risorse.
Nella seconda parte l’elaborato si concentra su YOLO e sui suoi sviluppi. YOLO è un modello basato su reti neurali convoluzionali, con il quale i problemi di localizzazione e classificazione degli oggetti in un’immagine sono stati trattati per la prima volta come un unico problema di regressione. Questo cambio di prospettiva apportato dagli autori di YOLO ha aperto la strada verso un nuovo approccio all’object detection, facilitando il successivo sviluppo di modelli sempre più precisi e performanti.
37
Norén, Aron. "Enhancing Simulated Sonar Images With CycleGAN for Deep Learning in Autonomous Underwater Vehicles." Thesis, KTH, Matematisk statistik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301326.
Full textAbstract:
This thesis addresses the issues of data sparsity in the sonar domain. A data pipeline is set up to generate and enhance sonar data. The possibilities and limitations of using cycleGAN as a tool to enhance simulated sonar images for the purpose of training neural networks for detection and classification is studied. A neural network is trained on the enhanced simulated sonar images and tested on real sonar images to evaluate the quality of these images.The novelty of this work lies in extending previous methods to a more general framework and showing that GAN enhanced simulations work for complex tasks on field data.Using real sonar images to enhance the simulated images, resulted in improved classification compared to a classifier trained on solely simulated images.<br>Denna rapport ämnar undersöka problemet med gles data för djupinlärning i sonardomänen. Ett dataflöde för att generera och höja kvalitén hos simulerad sonardata sätts upp i syfte att skapa en stor uppsättning data för att träna ett neuralt nätverk. Möjligheterna och begränsningarna med att använda cycleGAN för att höja kvalitén hos simulerad sonardata studeras och diskuteras. Ett neuralt nätverk för att upptäcka och klassificera objekt i sonarbilder tränas i syfte att evaluera den förbättrade simulerade sonardatan.Denna rapport bygger vidare på tidigare metoder genom att generalisera dessa och visa att metoden har potential även för komplexa uppgifter baserad på icke trivial data.Genom att träna ett nätverk för klassificering och detektion på simulerade sonarbilder som använder cycleGAN för att höja kvalitén, ökade klassificeringsresultaten markant jämfört med att träna på enbart simulerade bilder.
38
Тарасов, О. Є. "Інтелектуальна система автоматичного керування автомобілем у віртуальній моделі навколишнього середовища". Thesis, Чернігів, 2021. http://ir.stu.cn.ua/123456789/25133.
Full textAbstract:
Тарасов, О. Є. Інтелектуальна система автоматичного керування автомобілем у віртуальній моделі середовища : випускна кваліфікаційна робота : 121 "Інженерія програмного забезпечення" / О. Є. Тарасов ; керівник роботи О. В. Трунова ; НУ "Чернігівська політехніка", кафедра технологій та програмної інженерії. – Чернігів, 2021. – 82 с.<br>Кваліфікаційна робота передбачає дослідження сучасного стану розвитку галузі безпілотних автомобілів, а також основних технологій, які в ній застосовуються; дослідження можливостей використання віртуальних середовищ для перевірки ефективності роботи систем автоматичного керування автомобілем; розробку системи автоматичного керування автомобілем та оцінку ефективності її роботи у віртуальній моделі навколишнього середовища.
Віртуальне середовище повинно являти собою модель реального світу зі змінними довколишніми умовами: погодою, ландшафтом, часом доби. При виборі перевага має надаватися тим варіантам, в яких дорожня інфраструктура реалізована більш детально та реалістично.
Розроблювана система має складатися з частин, що повинні виконувати наступні функції:
- підсистема збору даних: отримання даних з віртуального середовища, їх зберігання у сховищі даних;
- підсистема обробки даних: підготовка зібраних даних для реалізації системи автоматичного керування; реалізація обраних технологій на основі зібраних даних;
- підсистема керування: інтеграція реалізованої системи автоматичного керування до віртуального середовища.<br>Qualification work involves the study of the current state of development of the unmanned vehicle industry, as well as the main technologies used in it; research of possibilities of use of virtual environments for check of efficiency of work of systems of automatic control of the car; development of an automatic car control system and evaluation of its efficiency in a virtual model of the environment.
The virtual environment should be a model of the real world with changing environmental conditions: weather, landscape, time of day. When choosing, preference should be given to those options in which the road infrastructure is implemented in more detail and realistically.
The developed system should consist of parts that must perform the following functions:
- data collection subsystem: obtaining data from the virtual environment, storing them in the data warehouse;
- data processing subsystem: preparation of collected data for the implementation of automatic control system; implementation of selected technologies based on collected data;
- control subsystem: integration of the implemented automatic control system into the virtual environment.
39
Venkatesh, Anirudh. "Object Tracking in Games using Convolutional Neural Networks." DigitalCommons@CalPoly, 2018. https://digitalcommons.calpoly.edu/theses/1845.
Full textAbstract:
Computer vision research has been growing rapidly over the last decade. Recent advancements in the field have been widely used in staple products across various industries. The automotive and medical industries have even pushed cars and equipment into production that use computer vision. However, there seems to be a lack of computer vision research in the game industry. With the advent of e-sports, competitive and casual gaming have reached new heights with regard to players, viewers, and content creators. This has allowed for avenues of research that did not exist prior.
In this thesis, we explore the practicality of object detection as applied in games. We designed a custom convolutional neural network detection model, SmashNet. The model was improved through classification weights generated from pre-training on the Caltech101 dataset with an accuracy of 62.29%. It was then trained on 2296 annotated frames from the competitive 2.5-dimensional fighting game Super Smash Brothers Melee to track coordinate locations of 4 specific characters in real-time. The detection model performs at a 68.25% accuracy across all 4 characters. In addition, as a demonstration of a practical application, we designed KirbyBot, a black-box adaptive bot which performs basic commands reactively based only on the tracked locations of two characters. It also collects very simple data on player habits. KirbyBot runs at a rate of 6-10 fps.
Object detection has several practical applications with regard to games, ranging from better AI design, to collecting data on player habits or game characters for competitive purposes or improvement updates.
40
Khlif, Wafa. "Multi-lingual scene text detection based on convolutional neural networks." Thesis, La Rochelle, 2022. http://www.theses.fr/2022LAROS022.
Full textAbstract:
Cette thèse propose des approches de détection de texte par des techniques d'apprentissage profond pour explorer et récupérer des contenus faiblement structurés dans des images de scène naturelles. Ces travaux proposent, dans un premier temps, une méthode de détection de texte dans des images de scène naturelle basée sur une analyse multi-niveaux des composantes connexes (CC) et l'apprentissage des caractéristiques du texte par un réseau de neurones convolutionnel (CNN), suivie d'un regroupement des zones de texte détectées par une méthode à base de graphes. Les caractéristiques des composantes texte brut/non-texte obtenues à différents niveaux de granularité sont apprises via un CNN. Une deuxième méthode est présentée dans cette thèse inspirée du système YOLO. Le système réalise la détection du texte et l'identification du script simultanément. Nous considérons la tâche de détection de texte multi script comme un problème de détection d'objets, où l'objet est le script du texte. La détection de texte et l'identification des scripts sont réalisées avec une approche holistique en utilisant un réseau neuronal convolutionnel unique. Les évaluations expérimentales de ces approches sont réalisées sur le jeu de données MLT (Multi-Lingual Text dataset), nous avons contribué à la création de ce nouveau jeu de données. Il est composé d'images de scènes naturelles et synthétiques contenant du texte, tels que des panneaux de circulation et publicitaires, des noms de magasins, d'images extraites des réseaux sociaux. Ce type d'images représente l'un des types d'images les plus fréquemment rencontrés sur Internet, à savoir les images avec du texte incorporé dans les réseaux sociaux<br>This dissertation explores text detection approaches via deep learning techniques towards achieving the goal of mining and retrieval of weakly structured contents in scene images. First, this dissertation presents a method for detecting text in scene images based on multi-level connected component (CC) analysis and learning text component features via convolutional neural networks (CNN), followed by a graph-based grouping of overlapping text boxes. The features of the resulting raw text/non-text components of different granularity levels are learned via a CNN. The second contribution is inspired from YOLO: Real-Time Object Detection system. Both methods perform text detection and script identification simultaneously. The system presents a joint text detection and script identification approach based on casting the multi-script text detection task as an object detection problem, where the object is the script of the text. Joint text detection and script identification strategy is realized in a holistic approach using a single convolutional neural network where the input data is the full image and the outputs are the text bounding boxes and their script. Textual feature extraction and script classification are performed jointly via a CNN. The experimental evaluation of these methods are performed on the Multi-Lingual Text MLT dataset. We contributed in building this new dataset. It is constituted of natural scene images with embedded text, such as street signs and advertisement boards, passing vehicles, user photos in microblog. This kind of images represents one of the mostly encountered image types on the internet which are the images with embedded text in social media
41
Barbazza, Sigfrido. "Deep-learning applicato all'identificazione automatica di frutta in immagini." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2016. http://amslaurea.unibo.it/11526/.
Full textAbstract:
Analisi delle fasi per la realizzazione di uno strumento di supporto gli agricoltori, dalla creazione di un dataset, all'addestramento e test di una rete neurale artificiale, con obiettivo la localizzazione del prodotto agricolo all'interno delle immagini.
42
Acharya, Pradip. "DETECTION AND SEGMENTATION OF DEFECTS IN X-RAY COMPUTED TOMOGRAPHY IMAGE SLICES OF ADDITIVELY MANUFACTURED COMPONENT USING DEEP LEARNING." OpenSIUC, 2021. https://opensiuc.lib.siu.edu/theses/2834.
Full textAbstract:
Additive manufacturing (AM) allows building complex shapes with high accuracy. The X-ray Computed Tomography (XCT) is one of the promising non-destructive evaluation techniques for the evaluation of subsurface defects in an additively manufactured component. Automatic defect detection and segmentation methods can assist part inspection for quality control. However, automatic detection and segmentation of defects in XCT data of AM possess challenges due to contrast, size, and appearance of defects. In this research different deep learning techniques have been applied on publicly available XCT image datasets of additively manufactured cobalt chrome samples produced by the National Institute of Standards and Technology (NIST). To assist the data labeling image processing techniques were applied which are median filtering, auto local thresholding using Bernsen’s algorithm, and contour detection. A convolutional neural network (CNN) based state-of-art object algorithm YOLOv5 was applied for defect detection. Defect segmentation in XCT slices was successfully achieved applying U-Net, a CNN-based network originally developed for biomedical image segmentation. Three different variants of YOLOv5 which are YOLOv5s, YOLOv5m, and YOLOV5l were implemented in this study. YOLOv5s achieved defect detection mean average precision (mAP) of 88.45 % at an intersection over union (IoU) threshold of 0.5. And mAP of 57.78% at IoU threshold 0.5 to 0.95 using YOLOv5M was achieved. Additionally, defect detection recall of 87.65% was achieved using YOLOv5s, whereas a precision of 71.61 % was found using YOLOv5l. YOLOv5 and U-Net show promising results for defect detection and segmentation respectively. Thus, it is found that deep learning techniques can improve the automatic defect detection and segmentation in XCT data of AM.
43
Jurečka, Tomáš. "Detekce a klasifikace létajících objektů." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2021. http://www.nusl.cz/ntk/nusl-442512.
Full textAbstract:
The thesis deals with the detection and classification of flying objects. The work can be divided into three parts. The first part describes the creation of dataset of flying objects. The reverse image search is used to create the dataset. The next part is a research of algorithms for detection, tracking and classification. Subsequently, the individual algorithms are applied and evaluated. In the last part, the design of hardware components is performed.
44
Ciocarlan, Alina. "Small target detection using deep learning." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASG102.
Full textAbstract:
La détection de petits objets dans les images infrarouges (IR) est une tâche complexe mais cruciale en défense, surtout lorsqu'il s'agit de distinguer ces cibles d'un fond texturé. Les méthodes de détection d'objets classiques peinent à trouver un équilibre entre un taux de détection élevé et un faible taux de fausses alarmes. Bien que certaines approches aient amélioré les réponses des cartes de caractéristiques pour les petits objets, elles restent tout de même sensibles aux fausses alarmes induites par les éléments du fond. Pour résoudre ce problème, la première partie de cette thèse introduit un critère de décision a contrario dans l'entraînement des réseaux de neurones. Cette méthode statistique améliore les réponses des cartes de caractéristiques tout en contrôlant le nombre de fausses alarmes (NFA) et peut être intégrée dans n'importe quel réseau de segmentation sémantique. Le module NFA améliore la détection des petits objets et renforce la robustesse dans des contextes d'apprentissage frugal en données. Cependant, les réseaux de segmentation peuvent entraîner une fragmentation des objets, causant ainsi des fausses alarmes et faussant les métriques de comptage. Pour atténuer cela, le critère a contrario a été intégré dans la tête de détection d'un YOLO. La deuxième partie de la thèse aborde les défis posés par le manque de données annotées grâce à l'apprentissage auto-supervisé (SSL). Nous avons réalisé une étude des catégories de SSL existantes, en mettant l'accent sur les méthodes adaptées à la détection de petits objets. Nous avons ensuite évalué plusieurs stratégies SSL sur différents jeux de données, y compris les datasets de détection de petites cibles en IR. Cette étude nous permet de proposer une feuille de route pour aider à la sélection d'une stratégie de SSL adéquate selon plusieurs paramètres. Enfin, la combinaison du SSL et du paradigme a contrario a donné des résultats impressionnants sur la détection de petites cibles en IR<br>Detecting small objects in infrared images is a challenging yet critical task in defense, especially when it comes to differentiating these targets from a noisy or textured background. Conventional object detection methods have difficulties in finding the balance between high detection rate and low false alarm rate. While some existing approaches have improved feature map responses for small objects, they frequently fail to manage false alarms caused by background elements. To address this, we introduce an a contrario decision criterion into neural network training. This statistical test enhances feature map responses while controlling the number of false alarms (NFA) and can be integrated into any semantic segmentation network. The NFA module improves infrared small target detection (IRSTD) and increases robustness in few-shot settings. However, segmentation networks can lead to object fragmentation, causing false alarms and distorting counting metrics. To mitigate this, the a contrario criterion has been integrated into the YOLO detection head. The second part of the thesis focuses on overcoming the challenges of limited annotated samples through self-supervised learning (SSL). To this end, we conduct a survey on SSL strategies for image representation learning, with an emphasis on methods adapted for small object detection. We then benchmark several SSL strategies across different datasets, including IRSTD datasets. This study allows us to provide a roadmap to guide future practitioners in selecting an appropriate SSL strategy based on various parameters. Finally, combining both a contrario and SSL paradigms has led to impressive performance for IRSTD
45
Valentini, Alice. "Evaluation of deep learning techniques for object detection on embedded systems." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/15478/.
Full textAbstract:
Area surveying is an important tool used to inspect and study in detail a given area, it is especially useful to monitor the movements and the settlement of populations located in a developing country.
Unmanned Aerial Vehicles (UAV), given the recent developments, could represent a suitable technology in order to carry out this task in an easier and cheaper way.
The use of UAV based surveys techniques poses many challenges in terms of accuracy, speed and efficiency.
The target is to build an autonomous flight system which is able to define optimal flight paths using the gathered information from the environment.
In this thesis we will focus on the development of the perception system which has to capture the desired information with accurate and fast detections.
More in detail, we will explore and evaluate the use of object detection models based on Deep Learning techniques who will sense and collect data which will later use for on-board elaboration. The object detection model has to be accurate in order to detect all the objects encountered on the ground and fast in order to not introduce too much latency into the on-board decision system. Fast and accurate decisions could permit an efficient coverage of the area.
Different embedded platforms will be considered and examined in order to meet the model's computational requirements and to provide an efficient use in terms of battery consumption.
Different training configurations will be tested in order to maximize our detection accuracy metric, minimum average precision (mAP).
The detection speed will be then evaluated on our board using Frame Per Second (FPS) metric. In addition to YOLO we also tested TinyYOLO, a smaller and faster network. Results will be then compared in order to find the best configuration in terms of accuracy/speed.
We will show that our system is able to meet all the requirements even if we do not achieve our ideal detection speed.
46
Кушнір, Іван Ярославович. "Мультисервісна комп’ютерна мережа навчального курсового комбінату". Бакалаврська робота, Хмельницький національний університет, 2021. http://elar.khnu.km.ua/jspui/handle/123456789/10443.
Full text
47
Кучерук, Владислав Русланович. "Програмована схема керування світлофорами на базі мікро-ЕОМ для навчального макета, що моделює ситуації на перехресті вулиці". Бакалаврська робота, Хмельницький національний університет, 2021. http://elar.khnu.km.ua/jspui/handle/123456789/10423.
Full text
48
Taurone, Francesco. "3D Object Recognition from a Single Image via Patch Detection by a Deep CNN." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18669/.
Full textAbstract:
This thesis describes the development of a new technique for recognizing the 3D pose of an object via a single image. The whole project is based on a CNN for recognizing patches on the object, that we use for estimating the pose given an a priori model.
The positions of the patches, together with the knowledge of their coordinates in the model, make the estimation of the pose possible through a solution of a PnP problem. The CNN chosen for this project is Yolo.
In order to build the training dataset for the network, a new approach is used. Instead of labeling each individual training image as for the standard supervised learning, the initial coordinates of the patches are propagated on all the other images making use of the pose of the camera for all the pictures.
49
Rehnholm, Jonas. "Battery Pack Part Detection and Disassembly Verification Using Computer Vision." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-54852.
Full textAbstract:
Developing the greenest battery cell and establishing a European supply of batteries is the main goal for Northvolt. To achieve this, the recycling of batteries is a key enabler towards closing the loop and enabling the future of energy.When it comes to the recycling of electric vehicle battery packs, dismantling is one of of the main process steps.Given the size, weight and high voltage of the battery packs, automatic disassembly using robots is the preferred solution. The work presented in this thesis aims to develop and integrate a vision system able to identify and verify the battery pack dismantling process. To achieve this, two cameras were placed in the robot cell and the object detectors You Only Look Once (YOLO) and template matching were implemented, tested and compared. The results show that YOLO is the best object detector out of the ones implemented. The integration of the vision system with the robot controller was also tested and showed that with the results from the vision system, the robot controller can make informed decisions regarding the disassembly.
50
Donini, Massimo. "Algoritmi di stitching per il rilevamento dell'occupazione di aule in un contesto smart campus." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19063/.
Full textAbstract:
L'obiettivo di questo progetto è studiare un sistema con dispositivi a basso costo in grado di determinare l'occupazione corrente di un'aula, pensato principalmente per ottimizzare la gestione degli spazi universitari o di grandi edifici, implementandone un prototipo.
A supporto di ciò verranno presentati algoritmi di image stitching per fornire una visione ottimale anche degli ambienti più ampi.
In questo progetto è stato implementato un algoritmo di rilevamento dell'occupazione utilizzando componenti hardware economici che seguono una logica programmata appositamente. L'approccio impiegato si basa sull'utilizzo di camere in posizione prospettica, affidando ad una rete neurale l'elaborazione delle immagini. La motivazione di questa scelta deriva dal fatto che le tecnologie basate su camere sono attualmente più accurate ed utilizzarle in posizione prospettica si è rivelato più adeguato, sulla base della conformazione delle aule con più ingressi.
La rete neurale utilizzata è stata YOLOv3, estremamente veloce ed accurata, mentre l'hardware che è stato scelto dopo averlo confrontato con altri simili è il Raspberry Pi 2 Model B, uno dei single-board computer più venduti al mondo. Questa scelta è stata motivata dalla capacità computazionale richiesta e dall'obiettivo di limitare i costi.
Per poter applicare l'algoritmo di occupancy detection anche a stanze più ampie è stato necessario adottare un metodo di image stitching, col quale si è potuto combinare immagini provenienti da più camere per produrre una foto panoramica. In questo caso si è preferito sviluppare un metodo ad hoc invece di utilizzare software già presenti sul mercato in quanto essi necessitano di una capacità computazionale e di risorse elevate.