To see the other types of publications on this topic, follow the link: Video surveillance system.
Dissertations / Theses on the topic 'Video surveillance system'
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 'Video surveillance system.'
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
Haida, Maksim, and Максим Володимирович Гайда. "Video surveillance system of target contour." Thesis, National Aviation University, 2021. https://er.nau.edu.ua/handle/NAU/50751.
Full textAbstract:
1. Программирование компьютерного зрения на языке Python / Ян Эрик Солем, пер. с англ. Слинкин А.А. – М.: ДМК Пресс, 2016. – 312.с.: ил.
2. Системи відеоспостереження та методи виділення контурів на зображеннях / K. Гжешчик, Д. Загородня, А. Саченко, Б. Русин – «Управління проектами та розвиток виробництва», 2018, №3(67).
3. Advances in Computer Vision and Pattern Recognition / Giovanni Maria Farinella, Sebastiano Battiato, Roberto Cipolla – Springer-Verlag London 2013.
4. Детекторы углов. URL: https://habr.com/ru/post/244541/ (дата звернення: 23.02.2021).Computer vision is the science and technology of making machines that see. It is concerned with the theory, design and implementation of algorithms that can automatically process visual data to recognize objects, track and recover their shape and spatial layout. When recognizing objects, the most informative part of the image is the contour. An object contour is a part of an object that contains a lot of information about the shape of the object and almost does not depend on the color and texture of the image. You can analyze the shape of the object along the contour. In many cases, information about the shape of the object is sufficient to organize automated or automatic systems. In addition, the transition to object recognition by their contours allows to reduce the amount of processed information by several times, as a plus, the contours are invariant to the brightness transformations.The first element of an intelligent video surveillance system is a video sensor. Examples of video sensors are digital or IP cameras. For ease of use, installation and taking into account the cost of the module, I will use a WEB camera without an ultraviolet filter, with a resolution of 1280×720 pixels and a video recording rate of 25 frames per second.
Комп’ютерне бачення – це наука і технологія виготовлення машин, які бачать. Він займається теорією, розробкою та реалізацією алгоритмів, які можуть автоматично обробляти візуальні дані для розпізнавання об’єктів, відстеження та відновлення їх форми та просторового розташування. При розпізнаванні об’єктів найбільш інформативною частиною зображення є контур. Контур об’єкта - це частина об’єкта, що містить багато інформації про форму об’єкта і майже не залежить від кольору та текстури зображення. Ви можете проаналізувати форму предмета по контуру. У багатьох випадках інформації про форму предмета достатньо для організації автоматизованих або автоматичних систем. Крім того, перехід до розпізнавання об’єктів за їх контурами дозволяє зменшити оброблену інформацію в кілька разів, плюс, контури інваріантні до перетворень яскравості. Першим елементом інтелектуальної системи відеоспостереження є відеодатчик. Прикладами відеосенсорів є цифрові або IP-камери. Для зручності використання, встановлення та врахування вартості модуля я буду використовувати веб-камеру без ультрафіолетового фільтра, з роздільною здатністю 1280 × 720 пікселів та швидкістю запису відео 25 кадрів в секунду.
2
Zou, Zichuan. "Remote Client of Home Video Surveillance System." Case Western Reserve University School of Graduate Studies / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=case1459453065.
Full text
3
Zhou, Han, and 周晗. "Intelligent video surveillance in a calibrated multi-camera system." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2011. http://hub.hku.hk/bib/B45989217.
Full text
4
Luo, Ning. "A Wireless Traffic Surveillance System Using Video Analytics." Thesis, University of North Texas, 2011. https://digital.library.unt.edu/ark:/67531/metadc68005/.
Full textAbstract:
Video surveillance systems have been commonly used in transportation systems to support traffic monitoring, speed estimation, and incident detection. However, there are several challenges in developing and deploying such systems, including high development and maintenance costs, bandwidth bottleneck for long range link, and lack of advanced analytics. In this thesis, I leverage current wireless, video camera, and analytics technologies, and present a wireless traffic monitoring system. I first present an overview of the system. Then I describe the site investigation and several test links with different hardware/software configurations to demonstrate the effectiveness of the system. The system development process was documented to provide guidelines for future development. Furthermore, I propose a novel speed-estimation analytics algorithm that takes into consideration roads with slope angles. I prove the correctness of the algorithm theoretically, and validate the effectiveness of the algorithm experimentally. The experimental results on both synthetic and real dataset show that the algorithm is more accurate than the baseline algorithm 80% of the time. On average the accuracy improvement of speed estimation is over 3.7% even for very small slope angles.
5
Abdelkader, Mohamed F. "Integration and evaluation of a video surveillance system." College Park, Md. : University of Maryland, 2005. http://hdl.handle.net/1903/2817.
Full textAbstract:
Thesis (M.S.) -- University of Maryland, College Park, 2005.Thesis research directed by: Dept. of Electrical and Computer Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
6
Tuvskog, Johanna. "Evaluation of Face Recognition Accuracy in Surveillance Video." Thesis, Linköpings universitet, Datorseende, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166758.
Full textAbstract:
Automatic Face Recognition (AFR) can be useful in the forensic field when identifying people in surveillance footage. In AFR systems it is common to use deep neural networks which perform well if the quality of the images keeps a certain level. This is a problem when applying AFR on surveillance data since the quality of those images can be very poor. In this thesis the CNN FaceNet has been used to evaluate how different quality parameters influence the accuracy of the face recognition. The goal is to be able to draw conclusions about how to improve the recognition by using and avoiding certain parameters based on the conditions. Parameters that have been experimented with are angle of the face, image quality, occlusion, colour and lighting. This has been achieved by using datasets with different properties or by alternating the images. The parameters are meant to simulate different situations that can occur in surveillance footage that is difficult for the network to recognise. Three different models have been evaluated with different amount of embeddings and different training data. The results show that the two models trained on the VGGFace2 dataset performs much better than the one trained on CASIA-WebFace. All models performance drops on images with low quality compared to images with high quality because of the training data including mostly high-quality images. In some cases, the recognition results can be improved by applying some alterations in the images. This could be by using one frontal and one profile image when trying to identify a person or occluding parts of the shape of the face if it gets recognized as other persons with similar face shapes. One main improvement would be to extend the training datasets with more low-quality images. To some extent, this could be achieved by different kinds of data augmentation like artificial occlusion and down-sampled images.
7
Tanase, Cristina-Madalina. "Multi-person tracking system for complex outdoor environments." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-245082.
Full textAbstract:
The thesis represents the research in the domain of modern video tracking systems and presents the details of the implementation of such a system. Video surveillance is a high point of interest and it relies on robust systems that interconnect several critical modules: data acquisition, data processing, background modeling, foreground detection and multiple object tracking. The present work analyzes different state of the art methods that are suitable for each module. The emphasis of the thesis is on the background subtraction stage, as the final accuracy and performance of the person tracking dramatically dependent on it. The experimental results show the performance of four different foreground detection algorithms, including two variations of self-organizing feature maps for background modeling, a machine learning technique. The undertaken work provides a comprehensive view of the actual state of the research in the foreground detection field and multiple object tracking and offers solution for common problems that occur when tracking in complex scenes. The chosen data set for experiments covers extremely different and complex scenes (outdoor environments) that allow a detailed study of the appropriate approaches and emphasize the weaknesses and strengths of each algorithm. The proposed system handles problems like: dynamic backgrounds, illumination changes, camouflage, cast shadows, frequent occlusions and crowded scenes. The tracking obtains a maximum Multiple Object Tracking Accuracy of 92,5% for the standard video sequence MWT and a minimum of 32,3% for an extremely difficult sequence that challenges every method.
8
Sutor, S. R. (Stephan R. ). "Large-scale high-performance video surveillance." Doctoral thesis, Oulun yliopisto, 2014. http://urn.fi/urn:isbn:9789526205618.
Full textAbstract:
Abstract The last decade was marked by a set of harmful events ranging from economical crises to organized crime, acts of terror and natural catastrophes. This has led to a paradigm transformation concerning security. Millions of surveillance cameras have been deployed, which led to new challenges, as the systems and operations behind those cameras could not cope with the rapid growth in number of video cameras and systems. Looking at today’s control rooms, often hundreds or even thousands of cameras are displayed, overloading security officers with irrelevant information. The purpose of this research was the creation of a novel video surveillance system with automated analysis mechanisms which enable security authorities and their operators to cope with this information flood. By automating the process, video surveillance was transformed into a proactive information system. The progress in technology as well as the ever increasing demand in security have proven to be an enormous driver for security technology research, such as this study. This work shall contribute to the protection of our personal freedom, our lives, our property and our society by aiding the prevention of crime and terrorist attacks that diminish our personal freedom. In this study, design science research methodology was utilized in order to ensure scientific rigor while constructing and evaluating artifacts. The requirements for this research were sought in close cooperation with high-level security authorities and prior research was studied in detail. The created construct, the “Intelligent Video Surveillance System”, is a distributed, highly-scalable software framework, that can function as a basis for any kind of high-performance video surveillance system, from installations focusing on high-availability to flexible cloud-based installation that scale across multiple locations and tens of thousands of cameras. First, in order to provide a strong foundation, a modular, distributed system architecture was created, which was then augmented by a multi-sensor analysis process. Thus, the analysis of data from multiple sources, combining video and other sensors in order to automatically detect critical events, was enabled. Further, an intelligent mobile client, the video surveillance local control, which addressed remote access applications, was created. Finally, a wireless self-contained surveillance system was introduced, a novel smart camera concept that enabled ad hoc and mobile surveillance. The value of the created artifacts was proven by evaluation at two real-world sites: An international airport, which has a large-scale installation with high-security requirements, and a security service provider, offering a multitude of video-based services by operating a video control center with thousands of cameras connectedTiivistelmä Viime vuosikymmen tunnetaan vahingollisista tapahtumista alkaen talouskriiseistä ja ulottuen järjestelmälliseen rikollisuuteen, terrori-iskuihin ja luonnonkatastrofeihin. Tämä tilanne on muuttanut suhtautumista turvallisuuteen. Miljoonia valvontakameroita on otettu käyttöön, mikä on johtanut uusiin haasteisiin, koska kameroihin liittyvät järjestelmät ja toiminnot eivät pysty toimimaan yhdessä lukuisien uusien videokameroiden ja järjestelmien kanssa. Nykyajan valvontahuoneissa voidaan nähdä satojen tai tuhansien kameroiden tuottavan kuvaa ja samalla runsaasti tarpeetonta informaatiota turvallisuusvirkailijoiden katsottavaksi. Tämän tutkimuksen tarkoitus oli luoda uusi videovalvontajärjestelmä, jossa on automaattiset analyysimekanismit, jotka mahdollistavat turva-alan toimijoiden ja niiden operaattoreiden suoriutuvan informaatiotulvasta. Automaattisen videovalvontaprosessin avulla videovalvonta muokattiin proaktiiviseksi tietojärjestelmäksi. Teknologian kehitys ja kasvanut turvallisuusvaatimus osoittautuivat olevan merkittävä ajuri turvallisuusteknologian tutkimukselle, kuten tämä tutkimus oli. Tämä tutkimus hyödyttää yksittäisen ihmisen henkilökohtaista vapautta, elämää ja omaisuutta sekä yhteisöä estämällä rikoksia ja terroristihyökkäyksiä. Tässä tutkimuksessa suunnittelutiedettä sovellettiin varmistamaan tieteellinen kurinalaisuus, kun artefakteja luotiin ja arvioitiin. Tutkimuksen vaatimukset perustuivat läheiseen yhteistyöhön korkeatasoisten turva-alan viranomaisten kanssa, ja lisäksi aiempi tutkimus analysoitiin yksityiskohtaisesti. Luotu artefakti - ’älykäs videovalvontajärjestelmä’ - on hajautettu, skaalautuva ohjelmistoviitekehys, joka voi toimia perustana monenlaiselle huipputehokkaalle videovalvontajärjestelmälle alkaen toteutuksista, jotka keskittyvät saatavuuteen, ja päättyen joustaviin pilviperustaisiin toteutuksiin, jotka skaalautuvat useisiin sijainteihin ja kymmeniin tuhansiin kameroihin. Järjestelmän tukevaksi perustaksi luotiin hajautettu järjestelmäarkkitehtuuri, jota laajennettiin monisensorianalyysiprosessilla. Siten mahdollistettiin monista lähteistä peräisin olevan datan analysointi, videokuvan ja muiden sensorien datan yhdistäminen ja automaattinen kriittisten tapahtumien tunnistaminen. Lisäksi tässä työssä luotiin älykäs kännykkäsovellus, videovalvonnan paikallinen kontrolloija, joka ohjaa sovelluksen etäkäyttöä. Viimeksi tuotettiin langaton itsenäinen valvontajärjestelmä – uudenlainen älykäs kamerakonsepti – joka mahdollistaa ad hoc -tyyppisen ja mobiilin valvonnan. Luotujen artefaktien arvo voitiin todentaa arvioimalla ne kahdessa reaalimaailman ympäristössä: kansainvälinen lentokenttä, jonka laajamittaisessa toteutuksessa on korkeat turvavaatimukset, ja turvallisuuspalveluntuottaja, joka tarjoaa moninaisia videopohjaisia palveluja videovalvontakeskuksen avulla käyttäen tuhansia kameroita
9
Sinn, Richard M. Eng Massachusetts Institute of Technology. "Virtual pan-tilt-zoom for a wide-area-video surveillance system." Thesis, Massachusetts Institute of Technology, 2008. http://hdl.handle.net/1721.1/46489.
Full textAbstract:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.Includes bibliographical references (p. 95).
Advancements in the CMOS Image Sensor have enabled very high-performance, high resolution imaging systems to be built at relatively low cost. The availability of high-pixel count video imaging systems that can cover a wide field-of-view enables a surveillance technique called Virtual Pan-Tilt-Zoom. Virtual Pan-Tilt-Zoom provides the same functional properties as a mechanical pan-tilt-zoom setup, but it does not suffer from the physical limitations presented by a mechanical setup. A video system using Virtual Pan-Tilt-Zoom would have immediate continuous access to a high pixel-count image representing a wide coverage area, and it would enable a user to "virtually" pan, tilt, and zoom around the coverage area by reading out only the relevant image data associated with a Region of Interest that is dynamically defined by the user. This paper will examine the various camera electronics readout architectures that are possible to support the Virtual Pan-Tilt-Zoom function. Then, this project will examine and implement a specific implementation of the readout architecture for a high-resolution video camera system developed at MIT Lincoln Laboratory. The Multi-Aperture Sparse Imager Video System (MASIV) developed at MIT Lincoln Laboratory incorporates CMOS imagers to create an 880 Mega pixel image, and was used as the platform to implement the camera electronics for Virtual Pan-Tilt-Zoom functionality.
by Richard Sinn.
M.Eng.
10
Zhao, Wei. "Digital Surveillance Based on Video CODEC System-on-a-Chip (SoC) Platforms." FIU Digital Commons, 2010. http://digitalcommons.fiu.edu/etd/334.
Full textAbstract:
Today, most conventional surveillance networks are based on analog system, which has a lot of constraints like manpower and high-bandwidth requirements. It becomes the barrier for today’s surveillance network development. This dissertation describes a digital surveillance network architecture based on the H.264 coding/decoding (CODEC) System-on-a-Chip (SoC) platform. The proposed digital surveillance network architecture includes three major layers: software layer, hardware layer, and the network layer. The following outlines the contributions to the proposed digital surveillance network architecture. (1) We implement an object recognition system and an object categorization system on the software layer by applying several Digital Image Processing (DIP) algorithms. (2) For better compression ratio and higher video quality transfer, we implement two new modules on the hardware layer of the H.264 CODEC core, i.e., the background elimination module and the Directional Discrete Cosine Transform (DDCT) module. (3) Furthermore, we introduce a Digital Signal Processor (DSP) sub-system on the main bus of H.264 SoC platforms as the major hardware support system for our software architecture. Thus we combine the software and hardware platforms to be an intelligent surveillance node. Lab results show that the proposed surveillance node can dramatically save the network resources like bandwidth and storage capacity.
11
Andersen, Evan D. "A Surveillance System to Create and Distribute Geo-Referenced Mosaics Using SUAV Video." BYU ScholarsArchive, 2008. https://scholarsarchive.byu.edu/etd/1679.
Full textAbstract:
Small Unmanned Aerial Vehicles (SUAVs) are an attractive choice for many surveillance tasks. However, video from an SUAV can be difficult to use in its raw form. In addition, the limitations inherent in the SUAV platform inhibit the distribution of video to remote users. To solve the problems with using SUAV video, we propose a system to automatically create geo-referenced mosiacs of video frames. We also present three novel techniques we have developed to improve ortho-rectification and geo-location accuracy of the mosaics. The most successful of these techniques is able to reduce geo-location error by a factor of 15 with minimal computational overhead. The proposed system overcomes communications limitations by transmitting the mosaics to a central server where there they can easily be accessed by remote users via the Internet. Using flight test results, we show that the proposed mosaicking system achieves real-time performance and produces high-quality and accurately geo-referenced imagery.
12
Mawla, Aya Abdul. "Real time automatic intruder detection system (RAIDS)." Thesis, University of Bristol, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.319332.
Full text
13
Magaia, Lourenco Lazaro. "A video-based traffic monitoring system." Thesis, Stellenbosch : University of Stellenbosch, 2006. http://hdl.handle.net/10019.1/1243.
Full textAbstract:
Thesis (PhD (Mathematical Sciences. Applied Mathematics))--University of Stellenbosch, 2006.This thesis addresses the problem of bulding a video-based traffic monitoring system. We employ clustering, trackiing and three-dimensional reconstruction of moving objects over a long image sequence. We present an algorithms that robustly recovers the motion and reconstructs three-dimensional shapes from a sequence of video images, Magaia et al [91]. The problem ...
14
Andersen, Evan D. "A surveillance system to create and distribute geo-referenced mosaics from SUAV video /." Diss., CLICK HERE for online access, 2008. http://contentdm.lib.byu.edu/ETD/image/etd2416.pdf.
Full text
15
Liu, Junbin. "Distributed low-power image processing in wireless sensor networks for intelligent video surveillance applications." Thesis, Queensland University of Technology, 2012. https://eprints.qut.edu.au/63311/1/Junbin_Liu_Thesis.pdf.
Full textAbstract:
Distributed Wireless Smart Camera (DWSC) network is a special type of Wireless Sensor Network (WSN) that processes captured images in a distributed manner. While image processing on DWSCs sees a great potential for growth, with its applications possessing a vast practical application domain such as security surveillance and health care, it suffers from tremendous constraints. In addition to the limitations of conventional WSNs, image processing on DWSCs requires more computational power, bandwidth and energy that presents significant challenges for large scale deployments. This dissertation has developed a number of algorithms that are highly scalable, portable, energy efficient and performance efficient, with considerations of practical constraints imposed by the hardware and the nature of WSN. More specifically, these algorithms tackle the problems of multi-object tracking and localisation in distributed wireless smart camera net- works and optimal camera configuration determination.
Addressing the first problem of multi-object tracking and localisation requires solving a large array of sub-problems. The sub-problems that are discussed in this dissertation are calibration of internal parameters, multi-camera calibration for localisation and object handover for tracking. These topics have been covered extensively in computer vision literatures, however new algorithms must be invented to accommodate the various constraints introduced and required by the DWSC platform.
A technique has been developed for the automatic calibration of low-cost cameras which are assumed to be restricted in their freedom of movement to either pan or tilt movements. Camera internal parameters, including focal length, principal point, lens distortion parameter and the angle and axis of rotation, can be recovered from a minimum set of two images of the camera, provided that the axis of rotation between the two images goes through the camera's optical centre and is parallel to either the vertical (panning) or horizontal (tilting) axis of the image.
For object localisation, a novel approach has been developed for the calibration of a network of non-overlapping DWSCs in terms of their ground plane homographies, which can then be used for localising objects. In the proposed approach, a robot travels through the camera network while updating its position in a global coordinate frame, which it broadcasts to the cameras. The cameras use this, along with the image plane location of the robot, to compute a mapping from their image planes to the global coordinate frame. This is combined with an occupancy map generated by the robot during the mapping process to localised objects moving within the network.
In addition, to deal with the problem of object handover between DWSCs of non-overlapping fields of view, a highly-scalable, distributed protocol has been designed. Cameras that follow the proposed protocol transmit object descriptions to a selected set of neighbours that are determined using a predictive forwarding strategy. The received descriptions are then matched at the subsequent camera on the object's path using a probability maximisation process with locally generated descriptions.
The second problem of camera placement emerges naturally when these pervasive devices are put into real use. The locations, orientations, lens types etc. of the cameras must be chosen in a way that the utility of the network is maximised (e.g. maximum coverage) while user requirements are met. To deal with this, a statistical formulation of the problem of determining optimal camera configurations has been introduced and a Trans-Dimensional Simulated Annealing (TDSA) algorithm has been proposed to effectively solve the problem.
16
Mehendale, Vikram Prabhakar. "System approach to embedded system design." [Tampa, Fla.] : University of South Florida, 2007. http://purl.fcla.edu/usf/dc/et/SFE0002282.
Full text
17
Sugianto, Nehemia. "Responsible AI for Automated Analysis of Integrated Video Surveillance in Public Spaces." Thesis, Griffith University, 2021. http://hdl.handle.net/10072/409586.
Full textAbstract:
Understanding customer experience in real-time can potentially support people’s safety and comfort while in public spaces. Existing techniques, such as surveys and interviews, can only analyse data at specific times. Therefore, organisations that manage public spaces, such as local government or business entities, cannot respond immediately when urgent actions are needed. Manual monitoring through surveillance cameras can enable organisation personnel to observe people. However, fatigue and human distraction during constant observation cannot ensure reliable and timely analysis. Artificial intelligence (AI) can automate people observation and analyse their movement and any related properties in real-time. Analysing people’s facial expressions can provide insight into how comfortable they are in a certain area, while analysing crowd density can inform us of the area’s safety level. By observing the long-term patterns of crowd density, movement, and spatial data, the organisation can also gain insight to develop better strategies for improving people’s safety and comfort.
There are three challenges to making an AI-enabled video surveillance system work well in public spaces. First is the readiness of AI models to be deployed in public space settings. Existing AI models are designed to work in generic/particular settings and will suffer performance degradation when deployed in a real-world setting. Therefore, the models require further development to tailor them for the specific environment of the targeted deployment setting. Second is the inclusion of AI continual learning capability to adapt the models to the environment. AI continual learning aims to learn from new data collected from cameras to adapt the models to constant visual changes introduced in the setting. Existing continuous learning approaches require long-term data retention and past data, which then raise data privacy issues. Third, most of the existing AI-enabled surveillance systems rely on centralised processing, meaning data are transmitted to a central/cloud machine for video analysis purposes. Such an approach involves data privacy and security risks. Serious data threats, such as data theft, eavesdropping or cyberattack, can potentially occur during data transmission.
This study aims to develop an AI-enabled intelligent video surveillance system based on deep learning techniques for public spaces established on responsible AI principles. This study formulates three responsible AI criteria, which become the guidelines to design, develop, and evaluate the system. Based on the criteria, a framework is constructed to scale up the system over time to be readily deployed in a specific real-world environment while respecting people’s privacy. The framework incorporates three AI learning approaches to iteratively refine the AI models within the ethical use of data. First is the AI knowledge transfer approach to adapt existing AI models from generic deployment to specific real-world deployment with limited surveillance datasets. Second is the AI continuous learning approach to continuously adapt AI models to visual changes introduced by the environment without long-period data retention and the need for past data. Third is the AI federated learning approach to limit sensitive and identifiable data transmission by performing computation locally on edge devices rather than transmitting to the central machine.
This thesis contributes to the study of responsible AI specifically in the video surveillance context from both technical and non-technical perspectives. It uses three use cases at an international airport as the application context to understand passenger experience in real-time to ensure people’s safety and comfort. A new video surveillance system is developed based on the framework to provide automated people observation in the application context. Based on real deployment using the airport’s selected cameras, the evaluation demonstrates that the system can provide real-time automated video analysis for three use cases while respecting people’s privacy. Based on comprehensive experiments, AI knowledge transfer can be an effective way to address limited surveillance datasets issue by transferring knowledge from similar datasets rather than training from scratch on surveillance datasets. It can be further improved by incrementally transferring knowledge from multi-datasets with smaller gaps rather than a one-stage process. Learning without Forgetting is a viable approach for AI continuous learning in the video surveillance context. It consistently outperforms fine-tuning and joint-training approaches with lower data retention and without the need for past data. AI federated learning can be a feasible solution to allow continuous learning in the video surveillance context without compromising model accuracy. It can obtain comparable accuracy with quicker training time compared to joint-training.Thesis (PhD Doctorate)
Doctor of Philosophy (PhD)
Dept Bus Strategy & Innovation
Griffith Business School
Full Text
18
Bai, Yannan. "Video analytics system for surveillance videos." Thesis, 2018. https://hdl.handle.net/2144/30739.
Full textAbstract:
Developing an intelligent inspection system that can enhance the public safety is challenging. An efficient video analytics system can help monitor unusual events and mitigate possible damage or loss. This thesis aims to analyze surveillance video data, report abnormal activities and retrieve corresponding video clips. The surveillance video dataset used in this thesis is derived from ALERT Dataset, a collection of surveillance videos at airport security checkpoints.
The video analytics system in this thesis can be thought as a pipelined process. The system takes the surveillance video as input, and passes it through a series of processing such as object detection, multi-object tracking, person-bin association and re-identification. In the end, we can obtain trajectories of passengers and baggage in the surveillance videos. Abnormal events like taking away other's belongings will be detected and trigger the alarm automatically. The system could also retrieve the corresponding video clips based on user-defined query.
19
Li, Jun-Yi, and 李俊儀. "Object Extraction for Video Surveillance System." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/14121774953888185212.
Full textAbstract:
碩士國立雲林科技大學
電機工程系碩士班
91
The complex computation and quality of video object extraction is one of the main reasons that the object-oriented function of MPEG-4 could not be widely applied.In this paper, we propose a multi-resolution video object extraction to decrease the computation complexity and maintain the stable quality of video extraction. In general, the object contour is still clear in the adequate low resolution, thus we will extract the object in the proper resolution to decrease the computation complexity. However, there exists some problems when video subsamples to the adequate goal resolution and then projects to original resolution. By the more and more subsample layer, the object edge data lose more, so how to decrease the lost of significant edge data in the low resolution will be challengeable. Moreover, we also propose a method to solve the problem of block effect when projecting from low resolution to original resolution. we propose a dynamic-background object extraction algorithm on object extraction of outdoor surveillance system. First, we adopt a method by applying the Motion-vector as the foundation of judging object and then adopt the conception of mean and median filter to suppress the motion vector of background. As a result, the motion vector of object can be presented obviously. Secondly, we use simple formulation to extract the object. Thus, we can solve the problem of the change of background.
20
Ku, Min-Yu, and 古閔宇. "Intelligent Video Surveillance and Recognition System." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/06468539799880242017.
Full textAbstract:
博士國防大學理工學院
國防科學研究所
97
Capabilities of a video-based monitoring and recognizing system can be applied to many categories, for example vision-based vehicle detection system of traffic management, intrusion detection system of security and face recognition access control system of biometrics etc. This thesis proposes an algorithm with a low-cost camera by Taiwan to replace high-priced imports of vision-based vehicle detection system. We propose an algorithm to extract initial color backgrounds from surveillance videos using a probability-based background extraction algorithm. With the proposed algorithm, the initial background can be extracted accurately and quickly, while using relatively little memory. The intrusive objects can then be segmented quickly and correctly by a robust object segmentation algorithm. The segmentation algorithm analyzes the threshold values of the background subtraction from the prior frame to obtain good quality and update while minimizing execution time and maximizing detection accuracy. The segmentation and recognition method uses the length, width, and roof size to classify vehicles, even when occlusive vehicles are continuously merging from one frame to the next. The segmented objects can be recognized and counted in accordance with their varying features, via the proposed recognition and tracking methods. The color background images can be extracted efficiently and quickly from color image sequences and updated in real time to overcome any variation in illumination conditions. Experimental results for various environmental sequences and weather conditions are provided to demonstrate the robustness, accuracy, effectiveness, and memory economy of the proposed algorithm.
21
Chen, Kenny, and 陳坤霖. "RFID Full-Path Video Tracking Surveillance System." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/53279121748302257100.
Full textAbstract:
碩士國立彰化師範大學
電機工程學系
97
Nowadays video surveillance systems just set up several video cameras in those particular positions of indoor space. The rest of process requires man power to monitor and react the event of video immediately. After events, it needs manual operation to survey all video data passively. This not only wastes much time and man power but also makes mistakes easily. To overcome these problems, this thesis proposes a novel full-path video tracking surveillance system using RFID technique. Since the proposed system uses the RFID characteristic of automatic identification, it is worth to develop the novel video surveillance system. This thesis proposes an application system combining RFID with current video surveillance technique. It not only identifies many targets by RFID sensor mechanism but also locates the position by analyzing received the RF signal strength. Determining the target positions at that moment, and then we could know the moving path and time sequence. Using these data to survey the history video files from the video database, and then we could get the serial full-path tracking surveillance video. The average error rate of the experiment results ranges from 16% to 24%. Because RSSI value will be affected in the indoor location, this yields main error in the proposed system. Many environment factors can also affect the RSSI. To reduce the error rate, we will investigate the related factors and make this as our major work in the future.
22
Hsieh, Chia-Jui, and 謝家瑞. "An Implementation of Bluetooth Video Surveillance System." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/05732583513063102930.
Full textAbstract:
碩士國立中正大學
通訊工程研究所
92
The Bluetooth technology is a wireless communication standard which can be applied around the world. It is a multi-function communication protocol with short distance (10 ~ 100 meter), low power and low cost. Bluetooth uses Frequency Hopping Spread Spectrum and Time Division Multi-Access skills, furthermore, a mechanism derived the secret keys from the PIN Code leads Bluetooth technology to maintain its high capability in anti-radio noise and data security. Summarizing the above characteristics, with the demands of “Video Surveillance System” for the channel stability, data confidentiality or the convenience of device maintenance, the Bluetooth technology is adapted to be a solution for the “Video Surveillance System”. Therefore, the purpose of this thesis is to realize image capture, image compress, then transmitting them to the remote Video Server by the Bluetooth module. This thesis will contain the experiments which integrated CCD Sensor, image compressed chip through the Bluetooth technology to realize the “Bluetooth Video Surveillance System”. According to the Bluetooth protocol stack, these experiments will accomplish some regular profiles, such as Serial Port Profile, Service Discovery Application Profile and Generic Access Profile, which are used to build up the upper transmission channel for video data transmission.
23
Tsai, Ming-Shao, and 蔡明劭. "Development of Video Surveillance System for PDA." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/37845116366242540011.
Full textAbstract:
碩士國立成功大學
電機工程學系碩博士班
92
Conventional video surveillance system normally sends the images from the cameras to the monitors, however they are big and heavy, and the ranges of their locations are limited by the length of the connected transmission line. Moreover, the captured images can not be seen in the dynamic situation, and the viewed area is constrained by the camera’s orientation. In this thesis, we develop a novel video surveillance system in a personal digital assistant (PDA) which allows the users to look at the live view of the environment at home; furthermore, this system is capable to be connected to other PCs via internet. The users also can directly control multiple cameras at specified orientation remotely from PDA via wireless. Thus, the directions of the cameras requested by users can be achieved immediately. The captured images from the cameras are saved and sent to PC at home. Via the Internet, users can look at the live image captured from each room at home in PDA to achieve the total solution of home security system.
24
"Real-time surveillance system: video, audio, and crowd detection." Thesis, 2008. http://library.cuhk.edu.hk/record=b6074545.
Full textAbstract:
A learning-based approach to detect abnormal audio information is presented, which can be applied to audio surveillance systems that work alone or as supplements to video surveillance systems.An automatic surveillance system is also presented that can generate a density map with multi-resolution cells and calculate the density distribution of the image by using texture analysis technique. Hosed on the estimated density distribution, the SVM method is used to solve the classification problem of detecting abnormal situations caused by changes in density distribution.
Anti-terrorism has become a global issue, and surveillance has become increasingly popular in public places such as elevators, banks, airports, and casinos. With traditional surveillance systems, human observers inspect the monitor arrays. However, with screen arrays becoming larger as the number of cameras increases, human observers may feel burdened, lose concentration, and make mistakes, which may be significant in such crucial positions as security posts. To solve this problem, I have developed an intelligent surveillance system that can understand human actions in real-time.
I have built a low-cost PC-based real-time video surveillance system that can model and analyze human real-time actions based on learning by demonstration. By teaching the system the difference between normal and abnormal human actions, the computational action models built inside the trained machines can automatically identify whether newly observed behavior requires security interference. The video surveillance system can detect the following abnormal behavior in a crowded environment using learning algorithms: (1) running people in a crowded environment; (2) falling down movements when most people are walking or standing; and (3) a person carrying an abnormally long bar in a square. Even a person running and waving a hand in a very crowded environment can be detected using an optical flow algorithm.
I have developed a real-time face detection and classification system in which the classification problem is defined as differentiating and is used to classify the front of a face as Asian or non-Asian. I combine the selected principal component analysis (PCA) and independent component analysis (ICA) features into a support vector machine (SVM) classifier to achieved a good classification rate. The system can also be used for other binary classifications of face images, such as gender and age classification without much modification.
This thesis establishes a framework for video, audio, and crowd surveillance, and successfully implements it on a mobile surveillance robot. The work is of significance in understanding human behavior and the detection of abnormal events, and has potential applications in areas such as security monitoring in household and public spaces.
To test my algorithms, the video and audio surveillance technology are implemented on a mobile platform to develop a household surveillance robot. The robot can detect a moving target and track it across a large field of vision using a pan/tilt camera platform, and can detect abnormal behavior in a cluttered environment; such as a person suddenly running or falling down on the floor. When abnormal audio information is detected, a camera on the robot is triggered to further confirm the occurrence of the abnormal event.
Wu, Xinyu.
"May 2008."
Adviser: Yangsheng Xu.
Source: Dissertation Abstracts International, Volume: 70-03, Section: B, page: 1915.
Thesis (Ph.D.)--Chinese University of Hong Kong, 2008.
Includes bibliographical references (p. 101-109).
Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Abstracts in English and Chinese.
School code: 1307.
25
Jiang, Yue-Min, and 蔣岳珉. "Large Area Video Surveillance System Using Multiple Cameras." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/41405277915299390050.
Full textAbstract:
碩士中華大學
資訊工程學系(所)
96
With the great demand of constructing a safe and security environment, video surveillance is becoming more and more important. Conventional video surveillance systems often have several shortcomings. First, object detection can’t have high accuracy under the illumination variation environment or clustering background. Especially, the surface reflection and back-lighted problems can influence the object detection seriously. Second, some dynamic textures e.g., moving leaves, water ripples, will influence the reliability of object detection. Third, when an object leaves from the scene of camera A and then appears on the scene of camera B, a handoff scheme is seldom considered. Finally, the tracking efficiency and precision are reduced by the inaccurate foreground detection. In this study, the pixel-wise temporal probability background model, the dynamic texture modeling, color-based difference projection, and handoff between two cameras are proposed to improve the above mentioned problems. Experimental results show that the objects on the crowd scene may be detected correctly and with detecting rate above 10 fps.
26
Huang, Chung-ying, and 黃鐘瑩. "Video Surveillance system based on MPEG-4 coding." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/69828691277161700287.
Full textAbstract:
碩士國立高雄第一科技大學
電腦與通訊工程所
93
In this thesis, we present the content-based video coding, MPEG-4 for video surveillance system using software programming. Due to high computational complexity in MPEG-4 system, we proposed some fast MPEG-4 algorithms for MPEG-4 encoding in order to real-time implementation. The fast algorithms include shape coding, object tracking and DCT (discrete cosine transform) computations. The shape coding employs the differential code consisting of entropy code. The object tracking uses the relativity of shape and content information to reduce computational requirements and time of motion estimation. The DCT computation also occupies heavy work in MPEG-4 encoder. We proposed a simple fast algorithm using row/column approach. By combination of these fast algorithms, under the CPU using Intel Pentium-4, 3.2GHz, the encoder can realize 15~25 frames per second in off-line. As for real-time camera sampling and encoding, the frame rate can achieve about 2~5 frames.
27
Ou, Shu-Ting, and 歐書廷. "Implementation of Digital Video Surveillance System on DSP." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/36879247820160460987.
Full textAbstract:
碩士明志科技大學
電機工程研究所
98
In recent years, due to the vigorous development of information and communication theories, as well as a wide range of applications on digital devices, people desire to enhance the capability and efficiency, and achieve lower operating costs of systems by using digital information. Thus, among digital device applications, digital video surveillance systems have nowadays become a popular topic. In this study, we used Texas Instruments DaVinci series TMS320DM6437 digital signal processor as a computing core, with its high performance, low power consumption advantages for development. The motion estimation, weighted mask and timestamp functions will be added in the H.264 video encoding system architecture provided by Texas Instruments Company to increase versatility. The surveillance system eventually will be able to more accurately detect luminance difference of interested area in the video, using the detected result as a criterion for H.264 video encoding, thereby reducing CPU load and the expenditure of storage space. In addition, the usage of the timestamp method will increase the convenience of event tracking.
28
WU, MING-CHIEH, and 吳明杰. "Secure Video-Based Surveillance System Design For Barrack." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/8buwar.
Full textAbstract:
碩士國防大學理工學院
資訊工程碩士班
106
In recent years, the manpower of the military has been downsizing, resulting in insufficient manpower for patrolling barracks and a rising risk of dangers. The existing monitoring system cannot overcome the interference outside the complex environments. Therefore, it is impossible to practically apply such system to protect barracks due to excessively high false alarm rates. An intelligent surveillance system will apply foreground detection and abnormal behavior detection technologies. However, different monitoring environments need various appropriate detection approaches. In this thesis, we design an intelligent surveillance system to integrate foreground detection and abnormal behavior detection schemes. In the foreground detection step, a fusion method, which can flexibly fuse and substitute various foreground detection technologies, is used to adapt to various monitoring environments and extract foreground objects exactly. In the abnormal behavior detection step, the features of foreground objects are extracted and the support vector machine scheme is use to construct the behavior models. Through the designed interface of the proposed system, the various combinational fusion results can be easily verified, and various abnormal behaviors can be defined and detected conveniently. Furthermore, the workload and manpower of barrack security will be simplify, and there has more sufficient reacting time because of the early warning alarms.
29
HSU, SUNG-TENG, and 徐崧騰. "Application of Video Surveillance System to Criminal Investigation." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/xfmg8f.
Full textAbstract:
碩士國立臺北教育大學
資訊科學系碩士班
107
The police in Taiwan has gradually utilized various types of cutting-edge technologies and tools to investigate criminal cases in the recent years. Among all the types of crime investigation technologies and tools, the Video Surveillance System (VSS) would be the most impressive for citizens in the society. The VSS system has been widely spread to each streets and every corners of the city. The purpose of this thesis contains three aspects to research: the condition of VSS system installed by the police agencies, the effects of the system for the crime prevention and investigation, and the protection of citizens’privacy. In this thesis, document analysis is adopted as the method of research in the first place. With collecting structures of the installment of the VSS system and the theories of crime prevention, the thesis try to figure out the causes of crimes and strategies to prevent them. Secondly, with the method of questionnaire survey, this thesis research the effects of the VSS systems for police work, as the reference to the process of policy - making.According to results of the research, the VSS system is the excellent tool to monitor, to combat and to curb crimes. The system has its dual functions to prevent crimes beforehand and to investigate the evidences of crimes afterwards. In addition, the digital footage collected by the VSS system is regarded as the most powerful evidence of crimes.As a result, the VSS system has become one of the most important tools to combat crimes for the police. However, the research found the lack of regulations of the privacy protection is the major concern of the VSS system. The conclusion of this thesis is the usage of the VSS system may well enhance and improve the quality and the efficiency of crime investigation with the way of adopting,managing,operating and training for the VSS system when the police is conducting crime prevention and investigation. This research suggests police agencies should formulate consistent regulations for the installment, operation and the access of the VSS system while they are utilizing the system to prevent and investigate crimes. For the purpose of privacy protection, avoiding it would be undermined because of the disclosure of the footage for the media reports, the authority should be more cautious and adopt the approach which has the least influence on the rights of civilians.
30
YU, SHUO-WEN, and 余碩文. "The Real-Time Video Stitching System for Surveillance Frames." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/ha9u5v.
Full textAbstract:
碩士國立高雄應用科技大學
電子工程系
105
This paper presents a multi-camera stitching method that can be applied to public plazas or large warehouses. The method operates by video Stitching for Surveillance Frames, So that monitoring personnel can monitor the screen from the monitoring center to see a larger view of the screen, And a single screen monitoring is simpler than the observation from multiple screen, As well as to reduce the monitoring personnel to watch when the space is prone to chaos can also reduce the production of dead ends in the screen. Through the system after processing the results of the video, but also to the relevant computer visual processing of the detection system as a pre-image input, As the screen field of view can be increased to obtain more information and more extensive detection range, it can get better detection results; In this paper, the method has five modules: (1) Image preprocessing: The increase in image information in the picture makes it more time consuming for feature points with higher complexity, So the use of bilinear interpolation method for image reduction sampling. (2) Feature point detection: Feature search by SIFT + RANSAC Then use DBSCAN to filter feature points, (3) Find the best perspective transformation matrix: Select the two groups of the number of feature points in the ratio of the closest parameters for the best perspective transformation matrix. (4) Scene correction and compensation: Obtain the best matrix of storage and then carry on the perspective transformation to carry on the correction action to the target picture.(5)Video Stitching : We divide the image into overlapping and non-overlapping areas, And the overlapping area is subjected to multi-band blending splicing instead of overlapping area. Then, the two regions are merged to obtain the image result after splicing is completed.
31
Lin, Yi-Shin, and 林逸信. "The Application of Digital Video Surveillance System on Ships." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/73528895849238404826.
Full textAbstract:
碩士國立臺灣海洋大學
商船學系所
93
Abstract Digital video surveillance systems have been applied for many years on the land. We can see it all the time on the communities、schools、banks, and buildings etc. Surveillance system can be used for finding the original condition and evidence for many facts. For this reason, some countries put it into an important position. The police in Taiwan also find the key clues to solve a criminal case by this system frequently. Today, ships use the Voyage Data Recorder (VDR) to recode the voice from bridge and voyage information which is similar to the Flight Data Recorder (FDR). After the collision accident, Voyage Data Recorder can provide the data and information which is possible to reconstruct the condition as the FDR. Ying Ming Line built a 5551 TEU ship with Digital Video Surveillance System on board in 2002. The main purpose is to watch the cargo operation. In this thesis, Digital Video Surveillance System is studied for watch keeping, and it is expected to record a complete process of collision case to avoid the misjudgment from the insufficient data and information. Key word: Ship Surveillance System、Digital Video Surveillance System、Video Camera
32
Wang, Chung-Hao, and 王仲豪. "The application of wireless video surveillance system on ships." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/00526796853156751673.
Full text
33
Li, Tsung-Hsi, and 李宗熹. "Scalable and Recoverable Privacy Protection for Video Surveillance System." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/04559180010252496330.
Full textAbstract:
碩士國立交通大學
多媒體工程研究所
100
In recent years, video surveillance system has been widely equipped for crime investigation and deterrence in an attempt to reduce the occurrence of crime events. But the widespread cameras may invade the privacy of innocent persons. In this thesis, we provide a scalable and recoverable video privacy protection system. First, privacy-sensitive regions are segmented. Then, three permutation functions are employed for scalable and recoverable video privacy protection. Users with different authorization levels will get different authentication keys. Thus, users with the lowest authorization level can only watch the video with the privacy-sensitive region scrambled dramatically and users with the highest authorization level can investigate the original video. Furthermore, the proposed video privacy protection system can be embedded in current video standard codecs with the compression rate being reduced slightly.
34
Chang, Chun-Kai, and 張鈞凱. "Design of Smart VoIP Communication and Video Surveillance System." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/91469519013890836537.
Full textAbstract:
碩士國立高雄大學
電機工程學系碩士班
100
The proliferation of Internet technology, the popularity of broadband communication and the Cloud applications make the networks as a necessary pathway for Internet Communication which is the most convenient communication vehicle for data and information exchange. Associated networking applications increase in the proportion to time. For the sake of networking applications for enterprises or residential houses, many IP products are designed to meet the customer’s needs. However, these products are geared to a single purpose, the most common wireless AP router seems to belong to the single purpose category, it provides many applications in a single box. As a next step, the applications can be extended to smart VoIP Communication and Video Surveillance system based on embedded controller system which runs a Real time operating system to provide VoIP and Video Surveillance functions in addition to the WiFi AP router function. A system is designed for motion detection Video Surveillance, VoIP and WiFi router for a multi-facet intelligent communication Device to meet the customer’s needs. The system provides video surveillance through Fire Fox web, and also VoIP to meet the multi function communication goals.
35
Tsai, Wen-kai, and 蔡文凱. "The Study of Embedded Intelligent Video Surveillance System Design." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/27404467002769013352.
Full textAbstract:
博士國立雲林科技大學
工程科技研究所博士班
100
Recently, many international terroristic attacks caused great disturbance in public safety. Therefore, the governments around the world began to construct and strengthen image surveillance system for public safety. Although Taiwan does not encounter any terroristic attack, the surveillance system is used to diminish crime rate and improve public security. Up to now, Taiwan has strived to establish a nationwide security surveillance network to ensure homeland security such that our people can live in a safe environment. In general, the traditional video surveillance system with complex scene can easily produce false-positive detections. Furthermore, it has lower processing speed and larger more memory consumption. In other words, the traditional video surveillance system is unsuitable for implementing in embedded system. As a result, developing an efficient intelligent video surveillance system for embedded system has become an important research topic. For foreground object detection, this dissertation has proposed two background models which are HPB (hybrid pixel-based) and block-based major color background model. As the input sequence appears static and dynamic scenes simultaneously, HPB background model adopts single-layer approach for constructing the static background model and use multi-layer method to establish dynamic background model. Subsequently, homogeneous background subtraction is presented to extract foreground objects. For background update period, static and dynamic backgrounds adopt different running-average update strategies to reduce false-positive rate. From the experimental results, it is revealed that HPB background model has average error rate less than 1% in chaotic or complex scenes. From the detail observation to the background pixels, the adjacent pixels have the similar color information. For each image block, this dissertation proposes the block-based major color background model. Some major colors are adopted to represent the feature of the block. The identical color pixels are not recorded repeatedly. After comparing with other algorithms, the block-based major color background model can decrease at least 37% of memory consumption and improve 3%~55% of similarity value. For object tracking, we extract color textures from foreground objects, and then use MSE method to perform quick matching and track each individual object correctly. Finally, object detection and tracking are integrated and implemented in the embedded platform. From the experiment, two scenario analyses are completed: (1) warning of the intrusive objects, and (2) object tracking and counting to achieve the requirement of the smart surveillance image system. By adopting optimization techniques, the algorithm is realized in TI TMS320DM6446 DaVinci development kit. The performance can achieve 17 frames per second based on display resolution at 768×576.
36
Gabin, KPODA, and 普達. "A Video Surveillance System Based on the Distributed Ommateum." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/45357050310875090021.
Full textAbstract:
碩士國立中興大學
電機工程學系所
101
This work deal with the design of distributed video surveillance system. Our purpose is to realize an embedded video surveillance system capable of video streaming back to a remote server, detecting and tracking any moving object using pan-tilt cameras. The constructed system should be perfectly monitorable from the remote server. We can say that we have achieved this goal by using embedded technology, socket programing, computer vision resources (algorithms) and distributed system design method. The algorithm used for detection is a background subtraction technique namely temporal frame difference. To be able to locate and track the detected object we made use of camshift algorithm. The built system is composed of four client boards and one server PC. Client’s subsystem is based on an embedded processor (Beagleboard xM) and an embedded microcontroller (MSP430F5438). A pan-tilt camera is also part of each client’s subsystem. From the remote server we make use of one two or three cameras to detect and track the same target. We also can form tracking groups each composed of two cameras to track the two different targets. So, the four cameras are considered as a compound eye of our surveillance system. The major contribution of this work is without doubt the cooperative tracking technique we have implemented. In fact, by using a leader election algorithm, we elect a leader. This leader will then select it direct neighbors (followers) and get them involved in the tracking process. With this approach we get a good cooperative tracking results. Moreover the pan–tilt system automation provide a multi-view of the monitoring scene. At last the embedded technology devices we chose give our system good computation capabilities, mobility and real-time ability.
37
Yang, Ti-Hua, and 楊棣華. "A Cooperative Video Surveillance System by Using Multiple Cameras." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/4v56eb.
Full textAbstract:
碩士國立臺北科技大學
資訊工程系研究所
95
The third generation surveillance system had become trends in the surveillance industry after the 911 in 2001. The key concept of it is the fully digitization of the surveillance system. However, it is still using the traditional manner to observe the output by human. Since the spatial relationship between the multi-cameras has not been defined, there will be a defect that the security officer can only watch the individual scene of each camera, but not the overall view for whole monitoring area. Furthermore, once the distribution of the multi-cameras are changed, the work complexity of the surveillance system will increase. Therefore, the purpose of our research is to design a multi-cameras cooperative video surveillance system which can improve the defects mentioned above. We propose a novel model building a graph topology with spatial relationship into our surveillance system, which improves the performance while detecting and tracking an object; controls multi-cameras by one central station; alerts the inspectors for the abnormal events immediately and effectively. After a series of experiments, we can show that the graph topology with spatial relationship in the surveillance system is not only more adaptive for the indoor space but also more flexible for the detection region. Our design provides a basic architecture for multi-points surveillance system in the future.
38
Hsia, Chih-Hsien, and 夏至賢. "A Study on Discrete Wavelet Transform for Video Compression and Intelligent Video Surveillance System." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/02015632170419244338.
Full textAbstract:
博士淡江大學
電機工程學系博士班
98
This thesis attempts to develop a low cost, practical application of a two-dimensional (2-D) discrete wavelet transform (DWT) to an intelligent video surveillance system. The goal is to combine the video compression and computer vision processing used in a wavelet-based system and to adopt DWT to develop a low transpose memory VLSI architecture and a fast object detection algorithm that can meet the specifications of intelligent video surveillance and can also process information easily, in real-time, and with safe functioning. This thesis investigates the fundamental concept behind the wavelet transform and provides an overview of some improved algorithms for lifting-based DWT (LDWT). The video surveillance system is able to detect moving object events, and video compression information is captured by surveillance cameras in real-time. Wavelet transformation has become increasingly important in image compression and processing since wavelets allow both simultaneous spatial and frequency analysis and scalable video processing. This thesis presents two new approaches. First, we propose new hardware architectures to address critical issues in 2-D dual-mode LDWT (supporting 5/3 lossless and 9/7 lossy coding modes). A considerably large transpose memory is the most critical requirement for LDWT. The proposed architecture can support high-resolution videos and reduce the internal memory requirement significantly. In our LDWT approach, the signal flow is revised from row-wise only to mixed row- and column-wise, and a new architecture, called interlaced read scan architecture (IRSA), is used to reduce the transpose memory. With the IRSA approach, the transpose memory size is only 2N or 4N (5/3 or 9/7 mode) for an N´N DWT. In addition, the proposed 2-D LDWT operates with parallel and pipelined schemes that increase its operation speed. It can be applied to real-time video operations for Motion-JPEG2000. Second, we propose the called symmetric mask-based DWT (SMDWT) for an intelligent video surveillance system. SMDWT improves the critical issue of the 2-D LDWT, and then obtains the benefit of low latency, reduced complexity, and low transpose memory. A highly precise and real-time moving object detection algorithm based on a low complexity SMDWT offers a mechanism for the sequential detection of both indoor (all day) and outdoor (all day) scenes. Computer simulations verified that the present algorithm performs well. It has high accuracy rate of more than 89.59% on average and the average frame rate can reach 47.1 frame per second (FPS). The abovementioned two algorithms for the LDWT were improved. The experimental results indicate that the proposed methods can provide low transpose memory and real-time processing for a high resolution intelligent video surveillance system.
39
Wei-Shun, Lee. "A Real Time Video Surveillance System with Wireless Sensor Networks." 2006. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0016-1303200709470874.
Full text
40
Xiao, Hong-Zu, and 蕭宏儒. "Background Model Construction and Maintenance in a Video Surveillance System." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/84553593443767135326.
Full textAbstract:
碩士大葉大學
資訊管理學系碩士班
93
Background subtraction is a useful and effective method for detecting moving objects in computer-vision applications. However, the variant environments make the detection result to be unsatisfactory. In order to improve the detection accuracy, an appropriate background model must be constructed and maintained to accommodate to the changed environment. In this research, a robust background model maintenance mechanism is proposed and used to implement a moving object detection module. The proposed mechanism includes three phases: initial background model construction, sustained background model adjustment, rapid background model replacement. In the first phase, an initial background model is constructed from an unfiltered video stream. In the second phase, the background model is adjusted continually according to the gradual change of environment. If a sudden change of environment occurs, the current background model must be replaced rapidly by a new background model in the third phase. The new background model is trained from some video frames collected in the second phase. Finally, a moving object detection system is performed by applying a background subtraction approach and a shadow elimination technique. By examining in several variant environments, the Fine experimental results illustrate the practicability of the proposed background model maintenance mechanism.
41
Wang, Chih-Kao, and 王志高. "Video Surveillance System Based on Omni-directional and PTZ Cameras." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/64166146370265222580.
Full textAbstract:
碩士國立雲林科技大學
電機工程系碩士班
93
The deterioration of social order, which causes vandalism and terrorism around the world, has increased the importance of security and raised the demand on surveillance system. Therefore, the improvement on the capability of surveillance system is currently attracting a great deal of attention. Although intelligent multi-camera surveillance systems have been developed for some time, most of the systems can not effectively achieve the goal of tracking and positioning in an indoor environment. A functional analysis found that the reason is due to mutual occlusion under multiple people condition. Moreover, given wide surveillance area, the limitation on the image resolution can not offer the effective recognition and understanding. In order to overcome difficulties mentioned above, recent researches proposed intelligent surveillance systems composed of multiple cameras. Among them, some systems use the Pan-Tilt-Zoom camera to trace moving objects and try to zoom in the scene to acquire a higher resolution image. In addition, some systems even combined with omni-directional camera hanged on the ceiling, instead of ordinary flat camera, to obtain an overview of the surveillance region. In this thesis, we will investigate functionalities of one intelligent surveillance system composed of single omni-directional camera and two Pan-Tilt-Zoom cameras. Three key issues will be discussed in respective chapters, they are: (1) the imaging technique of the omni-directional image, (2) the localization of moving objects in the omni-directional image, and (3) the method of using the omni-directional camera to guide the PTZ camera for zooming and tracing the moving objects. Since the resolution of omni-directional images is much lower than that of the regular camera, we adopt a multi-resolution technique which uses thresholding-with-hysteresis to obtain a more complete object in omni-directional images. Furthermore, we not only develop an algorithm which combines template matching and motion history for object recognition, but also employ the motion estimation to improve the object tracking using PTZ camera. This surveillance system has been implemented by Borland C++ in PC, and experimental results show its feasibility of working in the real-time environment.
42
郭家豪. "The Application of Intelligent Video Surveillance System in Criminal Intercept." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/7w436a.
Full text
43
Liao, Yi-Han, and 廖翌涵. "Robust Little Flame Detection on Real-Time Video Surveillance System." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/7xybur.
Full textAbstract:
碩士國立臺北科技大學
資訊工程系研究所
100
In current era, there are various kinds of sensor used to detect the occurrence of fire. When a fire disaster occurs, security needs to go to the place and assesses the situation. In contrast, video-based fire detection system not only gives a faster response time but also provides with some fire information. This information help security to verify the fire alarm. This study proposes a method to detect the little flame in the early stage of fire combustion. The foreground object was extracted by motion detection and YCbCr color clues. To avoid the noise of motion detection in different resolution videos, background edge is used to eliminate noise instead of morphology. Next, with the help of fire characteristics, the foreground object is identified. A fire object is determined by compactness, corner flicker rate, and growth rate. The experiment can be applied to any resolution video and complex scene, both indoors and outdoors, such as squares, where people walk around and vehicles pass by. The outcome of experiment, using this proposed method, can detect the fire object accurately and exclude the undangerous fire.
44
Chen, Sung-Hung, and 陳松鴻. "A Self-adapted Video Surveillance System under Multi-interference Environment." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/k7b8ha.
Full textAbstract:
碩士國立臺北科技大學
電機工程系研究所
101
Among all the visual surveillance systems, most of the algorithms apply the so-called background subtraction approach for the detection of a foreground, i.e., for the detection of a moving target. However, the background subtraction approach is susceptible to making an incorrect judgment for a time-varying environment, such as the change of light source, the interference of waving trees, the change of shadow, and the texture caused by raindrops. To conquer this problem, some of the researches propose the use of a statistical approach for the construction of an adaptive background model, and pixel values with higher probability would be classified as a background. Nevertheless, the problem of a shadow caused by light masking still exists, and a shadow can still be deemed as the foreground, resulting in an incorrect judgment. In addition, when the system is operating in a rainy day, the effect of the raindrops not only reduce visibility but also make the video screen blurred, causing the system hard to function well. To solve these problems, we propose in this dissertation a self-adapted video surveillance algorithm for multi-interference environment. The proposed algorithms can be divided into three parts. The First part is for rainfall interference removal. We find that only the intensity component of a pixel will be affected when a raindrop exists. That is, the illumination tends to be increased but with chrominance components kept unaltered when a raindrop exists. Based on this observation, we propose in this dissertation an algorithm for rainfall interference removal. The second part is in proposing an efficient approach by using statistical methods for the construction of an adaptive background model for time-varying environments. The third part is for shadow detection. Based on the observation that a shadow doesn’t affect the chrominance components of a pixel, we propose in this dissertation an algorithm for shadow detection so that a shadow will be excluded from being regarded as the foreground. Considering the real-time processing requirement in most of the visual surveillance systems, the proposed algorithm has extremely low computational complexity. Experimental results show that the proposed algorithm works very well under various test environments with a variety of interferences, which justifies the superiority of the proposed approach.
45
Chen, Ren-Hao, and 陳人豪. "Using PTZ Camera to Construct a Smart Video Surveillance System." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/71079936511062199566.
Full textAbstract:
碩士國立成功大學
電腦與通信工程研究所
96
Due to the fast development of times and people owning more and more riches but the crime rate increases continuously, the safe demand of the public security will be more and more important. Though the America is a powerful country owning the most developed science and technology, it is also mauled heavily in the 911 attack event, hence other countries in the world focus on video tracking technology as the most research topic. The videos of the cameras are shown on one or plenty of the monitors in the traditional surveillance system and it still needs considerable human input to monitor potential threats and trigger warning according to the abnormal behavior. A great deal of cameras are deployed due to the cameras cost are dropped at present and relatively the loading of monitoring operators grows up along with days passing by, hence it may cause a large number of the key frames to be lost. Therefore this paper will propose a smart video surveillance system to obtain this aim of the detecting, monitoring and warning abnormal events dynamically by combining numerous smart functions including the moving object tracking, the moving object locating, the key frames capturing by adjusting various zoom-in values in the different positions, the lost and found strategy of the losing moving object, the entrance management of the pass in and out, the moving trajectory recording in the surveillance space, and the abnormal behavior detection in the warning section. We expect to eliminate the faults of the man-made interference and the damages of the abnormal event as far as possible.
46
Kuo, Hung Chao, and 郭鴻肇. "Utilization of Video Surveillance and Monitoring System for Security Service." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/90902309529988522195.
Full textAbstract:
碩士元智大學
電機工程學系
97
In this thesis, efforts are made to study image treatment system on a simple platform of PC (Personal Computer) to efficiently construct VSAM ( Video Surveillance and Monitoring ) with advantages of real time feedback, high accuracy, automatic and digital function. As to the chosen of programs, an idea is made in this project to utilize Microsoft Visual C++ 6.0 as the interface software between the image processing system and the user. Images captured by camera are transferred to random-access memory of PC to perform image treatments and analyses. As to the system processing procedures, one normal background image in the monitoring area is firstly captured to build as the standard reference image. Sequential images captured will alter when the background of the monitoring environment changes. After compared with altered images and the standard reference image, the extraordinary status and strange positions are detected. The status of monitored objects can be judged by detections of intruders and the displacements of monitored objects. When the comparing results reveal the appearance of intruders or the disappearance of monitored objects, the system will issue warnings and alerts to call security service personnel to achieve the goal of inhibition of crimes in real time. The disadvantage of simply saving the records in conventional VSAMs can be improved with the subject applications introduced in this thesis.
47
Chi, Chih-Ping, and 季志平. "The Study of Video Surveillance System Privacy on Internet Involvement." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/17727611693361631741.
Full textAbstract:
碩士華梵大學
資訊管理學系碩士班
101
The degrees of popularity of the CCTV(Closed-Circuit Television) have become omnipresent and overbearing. Its meet security needs for the most people. That's why CCTV improves the degree of recognition and dependence. Spread CCTV data is easy in the information technology. Especially it's viewability and peek the nature of privacy. When internet involve CCTV, it is easy to rapid spread on the internet. The popularity of social network makes the way of spread more diversity. In this research we can find that the CCTV is popular, the law can not take into account this spread behavior. It will generate privacy issues. In the information ethics is center of the study. And the point of the view is shown below. 1.Because of the security needs, it makes CCTV and privacy balance. 2.Information ethics perspectives on internet involve CCTV. 3.The question of privacy in CCTV data spread to social network. 4.Information ethics violation causing invasion of privacy or cyberbully.
48
Lee, Wei-Shun, and 李維順. "A Real Time Video Surveillance System with Wireless Sensor Networks." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/88694644483530260145.
Full textAbstract:
碩士國立清華大學
資訊工程學系
95
One goal of surveillance systems is to collect information about the behavior and position of interested targets in sensing environments. These systems can find applications in fire emergency, security, smart home and agriculture. Recently, surveillance systems combining wireless sensor networks with inexpensive web cameras or high quality Pan-Tilt-Zoom (PTZ) cameras have become more and more popular. In traditional video surveillance systems, a number of video cameras are required in order to achieve a desirable system performance. Another shortcoming is that it is not easy to adapt to environmental variations. In this paper, we proposed and implemented an integrated real time video surveillance system consisting of a large number of low cost sensors with a few wireless video cameras. The system allows a group of cooperating sensor devices to detect and track the positions of mobile objects and to report the results to sink nodes in a sensing environment. Then the sink nodes can control the video cameras for taking images of these events to display the present situations. We also propose a camera control scheme to better cover the sensing area and to support coverage allocation of the video cameras. We have implemented the proposed system with 16 sensor nodes and two PTZ wireless video cameras to evaluate the system performance. The result shows that our surveillance system is adaptable to various environments and is capable of providing real time information of the monitored environment
49
Liu, Wei-Chih, and 劉威志. "Multiple objects tracking in a multi-camera video surveillance system." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/34137564245360915484.
Full textAbstract:
碩士大葉大學
資訊管理學系碩士班
95
“Visual” is the most important perceptual system for human, and also most believe the message from visual. The majority of company, organization, community, and in the common house, that can see the “surveillance system” in many place. For the purpose of construct the intelligent environment Of visual Technologies , the focus in our research is multiple Indoor Security Monitoring. In order to detection and tracking the multiple moving object ,we use multi-camera to get the picture at difference position and angle ,and select the clearest picture automatically , recording the moving condition of object .We divide three part of our research, first, if there have multiple moving objects and the occlusion happened , the camera will hand off and get the best picture to track ; the second part , when moving object across two adjacent place , they will be tracked ceaselessly ; the last part is similar to the second part, but they have difference brightness in two adjacent place.
50
Wen, Wu-Sheng, and 溫武盛. "People Tracking and Counting for Applications in Video Surveillance System." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/05253469529568617874.
Full textAbstract:
碩士國立清華大學
電機工程學系
95
This thesis proposes a vision-based people counting system that can count the number of persons getting in or out of the entrance of a building. First, we develop a so-called adaptive AV codebook background model and use background subtraction to divide foreground object from background in RGB color-space. In ROI (range of interest), we use the template matching method to find the objects, and then apply Hough transform to detect head contours to verify whether the object is a person. Second, we use a white rectangle to locate personal location and record the bottom center point as the trajectory point. To track the moving object, we compute the color distance between the previous and current tracked object, and link the center points which belong the same person as the trajectory of movement. Finally we analyze the trajectory to determine whether the person enters or exits or just passes by the entrance. Finally some experimental results are illustrated to verify our system.