To see the other types of publications on this topic, follow the link: Real-time Localization.
Dissertations / Theses on the topic 'Real-time Localization'
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 'Real-time Localization.'
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
Huang, Yiteng (Arden). "Real-time acoustic source localization with passive microphone arrays." Diss., Georgia Institute of Technology, 2001. http://hdl.handle.net/1853/15024.
Full text
2
Lee, Young Jin. "Real-Time Object Motion and 3D Localization from Geometry." The Ohio State University, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=osu1408443773.
Full text
3
Dinh, Christoph [Verfasser]. "Brain Monitoring : Real-Time Localization of Neuronal Activity / Christoph Dinh." Aachen : Shaker, 2015. http://d-nb.info/1075437946/34.
Full text
4
Akhoury, Sharat Saurabh. "Real-Time Localization of Planar Targets on Power-Constrained Devices." Thèse, Université d'Ottawa / University of Ottawa, 2013. http://hdl.handle.net/10393/26162.
Full textAbstract:
In this thesis we present a method for detecting planar targets in real-time on power-constrained, or low-powered, hand-held devices such as mobile phones. We adopt the feature recognition (also referred to as feature matching) approach and employ fast-to-compute local feature descriptors to establish point correspondences. To obtain a satisfactory localization accuracy, most local feature descriptors seek a transformation of the input intensity patch that is invariant to various geometric and photometric deformations. Generally, such transformations are computationally intensive, hence are not ideal for real-time applications on limited hardware platforms. On the other hand, descriptors which are fast to compute are typically limited in their ability to provide invariance to a vast range of deformations. To address these shortcomings, we have developed a learning-based approach which can be applied to any local feature descriptor to increase the system’s robustness to both affine and perspective deformations. The motivation behind applying a learning-based approach is to transfer as much of the computational burden (as possible) onto an offline training phase, allowing a reduction in cost during online matching. The approach comprises of identifying keypoints which remain stable under artificially induced perspective transformations, extracting the corresponding feature vectors, and finally aggregating the feature vectors of coincident keypoints to obtain the final descriptors. We strictly focus on objects which are planar, thus allowing us to synthesize images of the object in order to capture the appearance of keypoint patches under several perspectives.
5
Greene, W. Nicholas (William Nicholas). "Real-time dense simultaneous localization and mapping using monocular cameras." Thesis, Massachusetts Institute of Technology, 2016. http://hdl.handle.net/1721.1/107051.
Full textAbstract:
Thesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2016.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 91-100).
Cameras are powerful sensors for robotic navigation as they provide high-resolution environment information (color, shape, texture, etc.), while being lightweight, low-power, and inexpensive. Exploiting such sensor data for navigation tasks typically falls into the realm of monocular simultaneous localization and mapping (SLAM), where both the robot's pose and a map of the environment are estimated concurrently from the imagery produced by a single camera mounted on the robot. This thesis presents a monocular SLAM solution capable of reconstructing dense 3D geometry online without the aid of a graphics processing unit (GPU). The key contribution is a multi-resolution depth estimation and spatial smoothing process that exploits the correlation between low-texture image regions and simple planar structure to adaptively scale the complexity of the generated keyframe depthmaps to the quality of the input imagery. High-texture image regions are represented at higher resolutions to capture fine detail, while low-texture regions are represented at coarser resolutions for smooth surfaces. This approach allows for significant computational savings while simultaneously increasing reconstruction density and quality when compared to the state-of-the-art. Preliminary qualitative results are also presented for an adaptive meshing technique that generates dense reconstructions using only the pixels necessary to represent the scene geometry, which further reduces the computational requirements for fully dense reconstructions.
by W. Nicholas Greene.
S.M.
6
Gironés, Sancho Xavier. "Real-Time Localization of Multi-Oriented Text in Natural Scene Images." Doctoral thesis, Universitat Rovira i Virgili, 2021. http://hdl.handle.net/10803/671518.
Full textAbstract:
Aquesta tesi es centra en el problema de la localització de textos en imatges d'escenes naturals des de la perspectiva de l'eficiència. Amb aquesta finalitat, s'introdueix un mètode de localització de text multiorientat en imatges naturals adequat per al processament en temps real de vídeo d'alta definició en dispositius portàtils i mòbils. El mètode proposat es basa en components connectats (CCs): Primer, els CCs s'aïllen convolucionant la imatge a múltiples escales amb un filtre espacial lineal dissenyat específicament, seguit de binarització amb histèresi. A continuació, els CCs no textuals es filtren emprant una cascada de classificadors locals que operen sobre descriptors expandits incrementalment, on la propietat d'ample de traç s'estima eficientment calculant els quadrats màxims inscrits en els CCs. Els CCs candidats i els seus veïns es verifiquen posteriorment amb un classificador amb context que té en compte els CC de destinació i el seu entorn. Finalment, s'extreuen seqüències de text de totes les escales i després es fusionen utilitzant programació dinàmica. El mètode proposat és capaç de processar vídeo HD de 1080p a gairebé 30 quadres per segon en un ordinador portàtil estàndard sense requerir GPU. A més, en comparatives realitzades en les bases de dades de lectura robusta de ICDAR 2013 i de text d'escena incidental de ICDAR 2015, la solució proposada va rendir més del doble de ràpid que l'estat de la tècnica, a banda de demostrar resultats competitius en termes de precisió i exhaustivitat.
A més, aquesta tesi introdueix una nova família d'aproximacions racionals de la funció arctangent vàlides en el rang [0, π / 2] que es pot ampliar fàcilment a dos i quatre quadrants, i una nova tècnica per a la localització de matrícules de vehicles en imatges naturals.Esta tesis se centra en el problema de la localización de textos en imágenes de escenas naturales desde la perspectiva de la eficiencia. Con este fin, se introduce un método de localización de texto multiorientado en imágenes naturales adecuado para el procesamiento en tiempo real de video de alta definición en dispositivos portátiles y móviles. El método propuesto se basa en el enfoque de componentes conectados (CCs): Primero, los CCs se aíslan convolucionando la imagen a múltiples escalas con un filtro espacial lineal diseñado específicamente, seguido de binarización con histéresis. A continuación, los CCs no textuales se filtran empleando una cascada de clasificadores locales que operan sobre descriptores expandidos incrementalmente, donde la propiedad de ancho de trazo se estima eficientemente calculando los cuadrados máximos inscritos en los CCs. Los CCs candidatos y sus vecinos se verifican posteriormente con un clasificador con contexto que tiene en cuenta los CC de destino y su entorno. Por último, se extraen secuencias de texto en todas las escalas y después se fusionan utilizando programación dinámica. El método propuesto es capaz de procesar video HD de 1080p a casi 30 cuadros por segundo en una computadora portátil estándar sin requerir una GPU. Además, en comparativas realizadas en las bases de datos de lectura robusta de ICDAR 2013 y de texto de escena incidental de ICDAR 2015, la solución propuesta desempeñó más del doble de rápido que el estado de la técnica, aparte de demostrar resultados competitivos en términos de precisión y exhaustividad. Además, esta tesis introduce una nueva familia de aproximaciones racionales de la función arcotangente válida en el rango [0, π / 2] que se puede ampliar fácilmente a dos y cuatro cuadrantes, y una nueva técnica para la localización de matrículas de vehículos en imágenes naturales.
This thesis focuses on the problem of text localization in natural scene images from the perspective of time-efficiency. Towards this end, a multi-oriented text localization method in natural images suitable for real-time processing of high-definition video on portable and mobile devices is introduced. The proposed method is based on the connected component (CC) approach: First, CCs are isolated by convolving a multi-scale pyramid with a specifically designed linear spatial filter, followed by hysteresis thresholding. Next, non-textual CCs are pruned employing a cascade of local classifiers fed with increasingly extended feature vectors, where the stroke width feature is estimated in linear time complexity by computing the maximal inscribed squares in the CCs. Candidate CCs and their neighbors are subsequently checked with a context-aware classifier that takes into account the target CCs and their vicinity. Lastly, text sequences are extracted in all pyramid levels and fused using dynamic programming. The proposed method is capable of processing 1080p HD video at nearly 30 frames per second on a standard laptop without requiring a GPU. Furthermore, when benchmarked on the ICDAR 2013 Robust Reading and on the ICDAR 2015 Incidental Scene Text datasets, it performed more than twice faster than the state-of-the-art, while still delivering competitive results in terms of precision and recall. Additionally, this thesis introduces a new family or rational approximations of the arctangent function valid in the [0, π/2] range that can be easily extended to two and four quadrants, and a new technique for vehicle license plate localization in unconstrained environments is presented as a practical use case leveraging the text localization system described in this research.
7
Raja, Asad Khalid. "Fine-grain Indoor Localization Infrastructure for Real-time Inspectionof Large Buildings." Thesis, KTH, Reglerteknik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-176870.
Full textAbstract:
This master thesis project is about the systems integration of an indoor localizationsystem using Ultra Wideband Impulse Radio and a drone platform which uses theParrot AR.DRONE 2.0 along with the Robot Operating System (ROS). The goal wasto use o-the-shelf components to integrate an indoor localization system which can beused for energy modelling, indoor environmental panoramas and visual inspection oflarge buildings. The system architecture is explored, implemented and then subjectedto extensive testing. Experimental results of the openRTLS UWB system illustrateaccurate readings down to 2cm for Tag positions. The Parrot AR.DRONE 2.0 waschosen due to its low cost and agility; the open source drivers of ROS ensured modularsystem software, which has room for upgrades. The drone system can be used withoptional additional sensors, either attached internally or externally, to scan indoorareas and form environmental panoramas which can quantify ambient environmentalparameters such as temperature, humidity or pressure in harsh or hard to reach areas.The live video feed from the camera facilitates navigation in NLOS conditions. Thereal time ight path of the Parrot AR.DRONE 2.0 combined with the real time positiondata of the openRTLS UWB-IR system oers a unique insight into ne-grain data oflarge buildings.
8
Klüber, Viktor. "Development of a BCI based on real-time neural source localization." Master's thesis, Pontificia Universidad Católica del Perú, 2016. http://tesis.pucp.edu.pe/repositorio/handle/123456789/9519.
Full textAbstract:
Brain-Computer-Interfaces (BCIs) provide a novel way of communication by interpreting
different types of brain states. This principle of reading minds makes BCIs a
challenging but at the same time fascinating topic among the different disciplines of
electrophysiology and biomedical-signal-processing.
This work describes the development of a non-invasive BCI approach using steadystate-
visual-evoked-potentials (SSVEP) as a mental strategy. SSVEP based BCIs require
an external visual stimulation, which in this work is transmitted by a LCD-screen.
Consequently, a visual reactive BCI is integrated as a plug-in into the open source
project MNE-CPP, which provides an extensive library for brain monitoring and processing.
MNE-Scan, as a standalone software from MNE-CPP, contains the necessary
real-time source localization and is used as a framework for the BCI. Moreover, an
expansion with a screen keyboard device shows the BCI’s practicability.
The work’s result delivers a functioning SSVEP BCI approach with an average detection
accuracy of 86 %. However, it is shown, that a transition from a BCI on sensor
level to a BCI on source level is challenging and requires a certain pre-development,
whereby a first approach of the BCI only was realized on sensor level in this work.Tesis
9
Марченко, Ігор Олександрович, Игорь Александрович Марченко, Ihor Oleksandrovych Marchenko, Сергій Олександрович Петров, Сергей Александрович Петров, Serhii Oleksandrovych Petrov, and A. A. Pidkuiko. "Usage of keypoint descriptors based algorithms for real-time objects localization." Thesis, Центральноукраїнський національний технічний університет, 2018. http://essuir.sumdu.edu.ua/handle/123456789/68603.
Full textAbstract:
In order to achieve high level of security in our everyday life we produce huge amount of data. Significant part of information is presented by videos, sounds or images. A computer is used to extract useful information from raw data [1]. Pattern recognition is branch of computer vision, which allows us to get information from images [2] and videos. Information extraction is crucial problem of pattern recognition. This problem is divided into next branches: object presence; object localization; object classification.
10
GARRAFFA, Giovanni. "Real Time Localization Systems for autonomous navigation: Modelling, Analysis and Control." Doctoral thesis, Università degli Studi di Palermo, 2021. http://hdl.handle.net/10447/514955.
Full textAbstract:
Questo lavoro di tesi riguarda la derivazione di osservatori ibridi dello stato, analisi e controllo, di sistemi di localizzazione e navigazione in tempo reale (RTLS). In particolare, il framework dei sistemi ibridi è stato utilizzato per tener conto delle dinamiche continue e discrete coinvolte nel processo di stima e della natura sporadica e tempo randomica delle misure provenienti da vari sensori di distanza e/o inerziali. Analisi di convergenza sono state effettuate per dimostrare la stabilità delle soluzioni proposte e la capacità di filtraggio dei rumori presenti nelle misure. Il presente lavoro è corredato dai risultati delle prove sperimentali di laboratorio a conferma della validità delle soluzioni proposte.This thesis work concerns the derivation of hybrid state observers, analysis and control, of real-time localization and navigation systems (RTLS). In particular, the hybrid systems framework was used to take into account the continuous and discrete dynamics involved in the estimation process and the sporadic and time-random nature of the measurements from various distance and / or inertial sensors. Convergence analyzes were carried out to demonstrate the stability of the proposed solutions and the filtering capacity of the noises present in the measurements. This work is accompanied by the results of the experimental laboratory tests confirming the validity of the proposed solutions.
11
Zaharans, Eriks. "Indoor robot localization and collaboration." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-102604.
Full textAbstract:
The purpose of this thesis is to create an indoor rescue scenario with multiple self-localizing robots that are able to collaborate for a victim search. Victims are represented by RFID tags and detecting them combined with an accurate enough location data is considered as a successful finding. This setup is created for use in a laboratory assignment at Linköping University. We consider the indoor localization problem by trying to use as few sensors as possible and implement three indoor localization methods - odometry based, passive RFID based, and our approach by fusing both sensor data with particle filter.The Results show that particle filter based localization performs the best in comparison to the two other implemented methods and satisfies the accuracy requirements stated for the scenario. The victim search problem is solved by an ant mobility (pheromone-based) approach which integrates our localization method and provides a collaborative navigation through the rescue area. The purpose of the pheromone mobility approach is to achieve a high coverage with an acceptable resource consumption.Experiments show that area is covered with approximately 30-40% overhead in traveled distance comparing to an optimal path.
12
Amiranashvili, Vazha. "Robust real-time localization and mapping in single and multi-robot systems." [S.l.] : [s.n.], 2007. http://deposit.ddb.de/cgi-bin/dokserv?idn=984365869.
Full text
13
Muhammad, Asim, and Akbar Ali. "Source Localization and Speech Enhancement for Speech Recognition for Real time Environment." Thesis, Blekinge Tekniska Högskola, Sektionen för ingenjörsvetenskap, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4130.
Full textAbstract:
Popularity of speech communication is rapidly increasing in various contexts such as conferencing systems, mobile/fixed electronic devices and laptops thus leading to a heightened demand for new services and improved speech quality. Dictaphones used for dictations usually have one microphone. Single microphone does not give enough degree of freedom to allow estimation of location of the source. Microphone array makes use of multiple microphones for spatial filtering suppressing the background noise. This report aims for speech enhancement utilizing the benefits inherited with microphone arrays to find direction of desired speaker and focus the listening beam in that direction. A comparison is made between Generalized Cross Correlation (GCC) methods for locating the source in real office environment. Beamforming is implemented to make the microphone array listen in the desired direction thus reducing the interference from other sources. Minimum Variance Distortion-less Response (MVDR) approach is shown to give better results compared to more simplistic techniques. Perceptual based Eigen filter incorporating human hearing models in subspace incorporated in the suppressor eliminates the residual noise. Objective system performance is evaluated by estimating Signal-to-Noise-Ratio improvement (SNRI), segmental SNR, signal degradation and noise suppression. Perpetual Evaluation of Speech Quality (PESQ) gives Mean Opinion Score for subjective evaluation.asim_zolo@yahoo.com, akbarali45@gmail.com
14
Assad, Muhammad Ali. "A real-time laboratory testbed for evaluating localization performance of WIFI RFID technologies." Worcester, Mass. : Worcester Polytechnic Institute, 2007. http://www.wpi.edu/Pubs/ETD/Available/etd-050407-112549/.
Full textAbstract:
Thesis (M.S.) -- Worcester Polytechnic Institute.Keywords: RSS localization; WiFi localization; WIFI RFID; Performance Evaluation Testbed; Channel modeling. Includes bibliographical references (leaves 100-102).
15
LaPenta, Jason Michael. "Real-time 3-d localization using radar and passive surface acoustic wave transponders." Thesis, Massachusetts Institute of Technology, 2007. http://hdl.handle.net/1721.1/41738.
Full textAbstract:
Thesis (S.M.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2007.Includes bibliographical references (p. 141-150).
This thesis covers ongoing work into the design, fabrication, implementation, and characterization of novel passive transponders that allow range measurements at short range and at high update rates. Multiple RADAR measurement stations use phase-encoded chirps to selectively track individual transponders by triangulation of range and/or angle measurements. Nanofabrication processes are utilized to fabricate the passive surface acoustic wave transponders used in this thesis. These transponders have advantages over existing solutions with their small size (mm x mm), zero-power, high-accuracy, and kilohertz update rates. Commercial applications such as human machine interfaces, virtual training environments, security, inventory control, computer gaming, and biomedical research exist. A brief review of existing tracking technologies including a discussion of how their shortcomings are overcome by this system is included. Surface acoustic wave (SAW) device design and modeling is covered with particular attention paid to implementation of passive transponders. A method under development to fabricate SAW devices with features as small as 300nm is then covered in detail. The electronic design of the radar chirp transmitter and receiver are covered along with the design and implementation of the test electronics. Results from experiments conducted to characterize device performance are given.
by Jason Michael LaPenta.
S.M.
16
Winkel, Reik, and Matthias Rabel. "Mine Digitalization: Automation and Collision Avoidance by Radar-tag Localization and Radar-scan Mapping (UPNS4D+)." Technische Universitaet Bergakademie Freiberg Universitaetsbibliothek "Georgius Agricola", 2018. http://nbn-resolving.de/urn:nbn:de:bsz:105-qucosa-231178.
Full textAbstract:
Motivation
Mine digitization is a consequent approach to establish industry 4.0 / IoT related mine operation models based on various dimensions: flexibility, coverage, real-time capability and analytics. Networking technology, wired and wireless, can be easily deployed large scale. Miniaturized sensors, thus can be placed anywhere.
Laser technology has been successfully used for more than a decade in the manufacturing industry. However, due to restrictions found in challenging heavy industry environments, such as dust, fog, rain or snow, laser technology can only rarely be found in mining applications. At the same time, technology-supported geometrical environmental scanning is essential for the control of mining machines. GPS in open pit mining is the state of the art technology for machine allocation and dispatch, whereby an underground equivalent is still missing.
Because of this technology gap, many machines are frequently operated beyond their original design boundaries, and not according to the production planning which may result in significant safety impacts and collisions. Recent breakthroughs in radar technology both in 2D/3D passive scanning as well as /3D Active localization is bound to trigger a revolution in mining. In close collaboration with major universities, radar technology has been developed to mature and ruggedized industrial sensors by indurad.
The public funded project “UPNS4D+” which stands for “Underground 4D+ Positioning, Navigation and Mapping System“, funded by BMBF (FKZ: 033R126), focuses on fully autonomous operated vehicles, including navigation, orientation, collision avoidance by driving autonomously around obstacles whether detected with the radar-tag system or by environmental Radar-scan.
Asset and Personnel Localization
Radar-tags are suitable to detect any tagged object or person. Vehicle based Radar-radios are used to measure distances and angles to radar-tags, relative to the vehicle. Any other machinery, person helmets, equipment can be tagged and thus can be localized. Based on this information, collision avoidance systems can be realized, by informing the vehicles operator or as break assistance system. Next to important localizations “geotags”, e.g. at crushers, the system can be used to exactly position vehicles, like LHDs to perfectly dump the moved material. Virtual fences can be realized to stop machinery if anyone enters a secured area. This enables fast operation e.g. at drill rigs, where manual work is required, when drill pipes have to be added. In room and pillar environments road crossings can be secured, by detecting exactly the own position at the crossing and observation other vehicles.
Environmental Face and Rib Mapping
Radar-scan Mapping is further, very advanced radar based technology to measure 2D planes or even the complete 3D environment around vehicles. As well infrastructure based usage might be considered, e.g. at crossings or crushers. Autonomous mapping radar scans algorithms are developed to reconstruct the surrounding and to detect the own driven trajectory including 3D translation, rotation.
17
Shah, Zubin. "SIMULATION AND ANALYSIS OF RFID LOCALIZATION ALGORITHMS." Wright State University / OhioLINK, 2006. http://rave.ohiolink.edu/etdc/view?acc_num=wright1164732791.
Full text
18
Wahdan, Mahmoud A. "New motion planning and real-time localization methods using proximity for autonomous mobile robots." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 1996. http://handle.dtic.mil/100.2/ADA322506.
Full textAbstract:
Dissertation (Ph.D. in Computer Science) Naval Postgraduate School, September 1996.Dissertation supervisor(s): Yutaka Kanayama. "September 1996." Includes bibliographical references (p. 217-221). Also available online.
19
Stuntebeck, Erich Peter. "An analysis of the domestic power line infrastructure to support indoor real-time localization." Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/34678.
Full textAbstract:
The vision of ubiquitous computing is to seamlessly integrate information processing into everyday objects and activities. Part of this integration is an awareness on the part of a system of its user's context. Context can be composed of several variables --- such as a user's current activity, goals, or state of mind --- but location (both past and present) is almost always a key component.
Determining location outdoors has become quite simple and pervasive with today's low-cost handheld Global Positioning System (GPS) receivers. Technologies enabling the location of people and objects to be determined while indoors, however, have lagged due to their extensive infrastructure requirements and associated cost. Just as GPS receivers utilize radio signals from satellites to triangulate their position, an indoor real-time locating system (RTLS) must also make use of some feature of the environment to determine the location of mobile units. Since the signal from GPS satellites is not sufficiently strong to penetrate the structure of a building, indoor RTLS systems must either use some existing feature of the environment or generate a new one. This typically requires a large amount of infrastructure (e.g. specialized RF receivers, additional 802.11 access points, RFID readers, etc.) to be deployed, making indoor RTLSs impractical for the home. While numerous techniques have been proposed for locating people and objects within a building, none of these has yet proven to be a viable option in terms of cost, complexity of installation, and accuracy for home users.
This dissertation builds on work by Patel et al. in which the home power lines are used to radiate a low-frequency wireless RF signal that mobile tags use for location fingerprinting. Leveraging the existing power line permits this system to operate on far less additional infrastructure than existing solutions such as cellular (GSM and CDMA), 802.11b/g, and FM radio based systems.
The contributions of this research to indoor power line-based RTLS are threefold. First, I examine the temporal stability of a power line based RTLS system's output. Fingerprinting-based RTLS relies upon some feature of the environment, such as the amplitude of an RF signal, to be stable over time at a particular location (temporal stability), but to change in space (spatial differentiability). I show that a power line-based RTLS can be made much more resistant to temporal instability in individual fingerprint components by utilizing a wide-band RF fingerprint. Next, I directly compare the temporal stability of the raw features used by various fingerprinting based indoor RTLSs, such as cellular, 802.11b/g, and FM radio. In doing so, I show that a power line based indoor RTLS has an inherent advantage in temporal stability over these other methods. Finally, I characterize the power line as a receiving antenna for low-powered wireless devices within the home, thus allowing the power line to not only transmit the RF signals used for fingerprinting, but also to receive the sensed features reported by location tags. Here, I show that the powerline is a viable receiver for these devices and that the globally available 27.12 MHz ISM band is a good choice of frequency for communications.
20
Ormoš, Michal. "Infrastruktura pro testování a nasazení real-time lokalizační platformy." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2020. http://www.nusl.cz/ntk/nusl-417266.
Full textAbstract:
Táto práca je prípadovou štúdiou postupného vývoja a nasadzovania lokačného softwaru v reálnom čase. Cieľom tejto práce je zrýchliť tento proces. Zvolený problém bol vyriešený s konvenčnými testovacími nastrojmi, vlastným nástrojom pre generovanie sieťovej prevádzky lokalizačnej platformy a nástrojmi CI/CD Gitlab. Prínosom tejto práce je zrýchlenie vývoja, zaručenie kvality vyvijaného softwaru a predstavenie spôsobu ako platformu pre lokalizáciu v reálnom čase testovať.
21
Sagboze, Konzi Olivier. "Real-time detection of attendance at a venue using mobile devices." Thesis, Cape Peninsula University of Technology, 2017. http://hdl.handle.net/20.500.11838/2676.
Full textAbstract:
Thesis (MTech (Information Technology))--Cape Peninsula University of Technology, 2017.The implosion of the mobile phones, mobile applications and social media in recent years has triggered a great interest for more dedicated user-generated contents. Mobile users being the focal point, these modern virtual platforms depend on and live for collecting, structuring and manipulating the very fine-grained details about users' day-to-day activities. Since every human activity takes place in a geographical context, location information ranks high among the set of data to gather about user's daily life. User's specific location details can help filter content to serve and retrieve from them. Therefore, location-based services have been developed and successfully integrated into most virtual platforms in the quest for these precious data. However, location-based services do not fulfil all requirements. They depend on a range of positioning systems which show numerous limitations. None of the existing positioning systems is perfectly accurate. Today, it is therefore difficult to pinpoint a user in a venue using location-based services. Nevertheless, with the set of existing technology and techniques, it is possible to estimate and track users’ whereabouts in real-time. Providing the best possible estimation of user's position within a given venue can help achieve better user engagement. Depending on the gap of accuracy, the end result may actually match the outcome expected from perfectly accurate positioning systems. In this work, the focus is to develop a prototype positioning system which provides the best estimation of user's position in real-time in relation to a targeted venue or location. Through a series of research and comparison study, the most suited technology and techniques are objectively selected to build the intended prototype. The challenge of indoor positioning is also addressed in this work – bearing in mind the fact that this prototype is set to work accurately and efficiently in any geographical location and structure. The prototype is evaluated according to a set of predefined standard metrics, and theories are extracted to grow knowledge about this trending topic.
22
Elgort, Daniel Robert. "Real-Time Catheter Tracking and Adaptive Imaging for Interventional Cardiovascular MRI." Case Western Reserve University School of Graduate Studies / OhioLINK, 2005. http://rave.ohiolink.edu/etdc/view?acc_num=case1111437062.
Full text
23
Winkel, Reik, and Matthias Rabel. "Mine Digitalization: Automation and Collision Avoidance by Radar-tag Localization and Radar-scan Mapping (UPNS4D+)." TU Bergakademie Freiberg, 2017. https://tubaf.qucosa.de/id/qucosa%3A23180.
Full textAbstract:
Motivation
Mine digitization is a consequent approach to establish industry 4.0 / IoT related mine operation models based on various dimensions: flexibility, coverage, real-time capability and analytics. Networking technology, wired and wireless, can be easily deployed large scale. Miniaturized sensors, thus can be placed anywhere.
Laser technology has been successfully used for more than a decade in the manufacturing industry. However, due to restrictions found in challenging heavy industry environments, such as dust, fog, rain or snow, laser technology can only rarely be found in mining applications. At the same time, technology-supported geometrical environmental scanning is essential for the control of mining machines. GPS in open pit mining is the state of the art technology for machine allocation and dispatch, whereby an underground equivalent is still missing.
Because of this technology gap, many machines are frequently operated beyond their original design boundaries, and not according to the production planning which may result in significant safety impacts and collisions. Recent breakthroughs in radar technology both in 2D/3D passive scanning as well as /3D Active localization is bound to trigger a revolution in mining. In close collaboration with major universities, radar technology has been developed to mature and ruggedized industrial sensors by indurad.
The public funded project “UPNS4D+” which stands for “Underground 4D+ Positioning, Navigation and Mapping System“, funded by BMBF (FKZ: 033R126), focuses on fully autonomous operated vehicles, including navigation, orientation, collision avoidance by driving autonomously around obstacles whether detected with the radar-tag system or by environmental Radar-scan.
Asset and Personnel Localization
Radar-tags are suitable to detect any tagged object or person. Vehicle based Radar-radios are used to measure distances and angles to radar-tags, relative to the vehicle. Any other machinery, person helmets, equipment can be tagged and thus can be localized. Based on this information, collision avoidance systems can be realized, by informing the vehicles operator or as break assistance system. Next to important localizations “geotags”, e.g. at crushers, the system can be used to exactly position vehicles, like LHDs to perfectly dump the moved material. Virtual fences can be realized to stop machinery if anyone enters a secured area. This enables fast operation e.g. at drill rigs, where manual work is required, when drill pipes have to be added. In room and pillar environments road crossings can be secured, by detecting exactly the own position at the crossing and observation other vehicles.
Environmental Face and Rib Mapping
Radar-scan Mapping is further, very advanced radar based technology to measure 2D planes or even the complete 3D environment around vehicles. As well infrastructure based usage might be considered, e.g. at crossings or crushers. Autonomous mapping radar scans algorithms are developed to reconstruct the surrounding and to detect the own driven trajectory including 3D translation, rotation.
24
Åkerlund, Rasmus. "Real-time localization of balls and hands in videos of juggling using a convolutional neural network." Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-81204.
Full textAbstract:
Juggling can be both a recreational activity that provides a wide variety of challenges to participants and an art form that can be performed on stage. Non-learning-based computer vision techniques, depth sensors, and accelerometers have been used in the past to augment these activities. These solutions either require specialized hardware or only work in a very limited set of environments. In this project, a 54 000 frame large video dataset of annotated juggling was created and a convolutional neural network was successfully trained that could locate the balls and hands with high accuracy in a variety of environments. The network was sufficiently light-weight to provide real-time inference on CPUs. In addition, the locations of the balls and hands were recorded for thirty-six common juggling pattern, and small neural networks were trained that could categorize them almost perfectly. By building on the publicly available code, models and datasets that this project has produced jugglers will be able to create interactive juggling games for beginners and novel audio-visual enhancements for live performances.
25
Holland, William S. "Development of an Indoor Real-time Localization System Using Passive RFID Tags and Artificial Neural Networks." Ohio University / OhioLINK, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1249062541.
Full text
26
Uhercik, Marian. "Surgical tools localization in 3D ultrasound images." Phd thesis, INSA de Lyon, 2011. http://tel.archives-ouvertes.fr/tel-00735702.
Full textAbstract:
This thesis deals with automatic localization of thin surgical tools such as needles or electrodes in 3D ultrasound images. The precise and reliable localization is important for medical interventions such as needle biopsy or electrode insertion into tissue. The reader is introduced to basics of medical ultrasound (US) imaging. The state of the art localization methods are reviewed in the work. Many methods such as Hough transform (HT) or Parallel Integral Projection (PIP) are based on projections. As the existing PIP implementations are relatively slow, we suggest an acceleration by using a multiresolution approach. We propose to use model fitting approach which uses randomized sample consensus (RANSAC) and local optimization. It is a fast method suitable for real-time use and it is robust with respect to the presence of other high-intensity structures in the background. We propose two new shape and appearance models of tool in 3D US images. Tool localization can be improved by exploiting its tubularity. We propose a tool model which uses line filtering and we incorporated it into the model fitting scheme. The robustness of such localization algorithm is improved at the expense of additional time for pre-processing. The real-time localization using the shape model is demonstrated by implementation on the 3D US scanner Ultrasonix RP. All proposed methods were tested on simulated data, phantom US data (a replacement for a tissue) and real tissue US data of breast with biopsy needle. The proposed methods had comparable accuracy and the lower number of failures than the state of the art projection based methods.
27
Gomes, Rui Pedro Lebreiro. "Fine-Grained localization system for indoor environments." Master's thesis, Universidade de Aveiro, 2014. http://hdl.handle.net/10773/13534.
Full textAbstract:
Mestrado em Engenharia Electrónica e de TelecomunicaçõesThe increasing demand for tracking solutions in indoor environments has led to the development of many indoor location systems based in the most diverse technologies. They are trying to fill a market niche left by the current available location systems such as the well-known Global Positioning System (GPS). These systems are limited to an outdoor usage due to the drastic attenuation of the GPS signals in closed areas and they cannot provide enough resolution to meet the requirements of certain applications. Therefore, it’s here proposed the conception of a system capable of locating a mobile module in indoor environments with an accuracy of a few centimeters. The system’s concept is based in measuring the time difference of arrival (TDOA) between a radio frequency signal and an ultrasonic burst in order to measure distances. The huge difference between the propagation velocities of RF waves comparatively to sound waves allows the system to accurately measure the time difference between the two arrivals and use that value to estimate the distance that separates the source from the destination. This document describes the development of all the necessary hardware for the conception of a final prototype and all the aspects regarding the software implementation. This system is composed by two types of devices that can be divided in Ultrasonic (US) transmitters and receivers. Each device is equipped with a RF module that allows them to communicate through a wireless network based in the IEEE802.15.4 protocol. In the end, a functional prototype was achieved that was subsequently submitted to several tests in order to evaluate its performance. These tests corroborated the viability of this localization method with the prototype achieving a remarkable precision level.
A crescente demanda por soluções de rastreamento em ambientes interiores levou ao desenvolvimento de vários sistemas de localização baseados nas mais diversas tecnologias. Eles vêm tentar colmatar um nicho de mercado deixado pelos sistemas de localização actualmente disponíveis como o caso do bem conhecido Sistema de Posicionamento Global (GPS). Estes sistemas estão limitados ao uso exterior devido à drástica atenuação dos sinais GPS em áreas fechadas e eles não oferecem resolução suficiente para cumprir os requisitos de certas aplicações. Por conseguinte, é aqui proposta a concepção de um sistema capaz de localizar um módulo móvel em ambientes interiores com uma resolução de alguns centímetros. O conceito do sistema é baseado na medição da diferença dos tempos de chegada entre um sinal de radiofrequência e um sinal de ultra-sons de forma a calcular distâncias. A enorme diferença entre as velocidades de propagação das ondas RF comparativamente às ondas sonoras permitem ao sistema medir com precisão a diferença entre o tempo de chegada dos dois sinais e usar esse valor para estimar a distância que separa a fonte do destino. Este documento descreve o desenvolvimento de todo o hardware necessário para a concepção de um protótipo bem como todos os aspectos relativos à implementação de software. Este sistema é composto por dois tipos de dispositivos que podem ser divididos em transmissores e receptores de sinais ultrassónicos. Cada dispositivo está equipado com um módulo de radiofrequência que lhes permite comunicar através de uma rede sem fios baseada no protocolo IEEE802.15.4. No final, foi alcançado um protótipo funcional que posteriormente foi submetido a vários testes de forma a avaliar o seu desempenho. Estes testes vieram corroborar a viabilidade deste método de localização com o protótipo a atingir um notável nível de precisão.
28
Urban, Steffen [Verfasser], and S. [Akademischer Betreuer] Hinz. "Real-Time Multi-Fisheye Camera Self-Localization and Egomotion Estimation in Complex Indoor Environments / Steffen Urban ; Betreuer: S. Hinz." Karlsruhe : KIT-Bibliothek, 2016. http://d-nb.info/1122461453/34.
Full text
29
BOTTIGLIERO, STEFANO. "A Real Time Locating System based on TDOA estimation of UWB pulse sequences." Doctoral thesis, Politecnico di Torino, 2022. http://hdl.handle.net/11583/2966337.
Full text
30
WAN, JINGFANG. "In Situ Optically Trapped Probing System for Molecular Recognition and Localization." The Ohio State University, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=osu1250626752.
Full text
31
Costin, Aaron M. "Integration of passive RFID location tracking for real-time visualization in building information models (BIM)." Thesis, Georgia Institute of Technology, 2013. http://hdl.handle.net/1853/50395.
Full textAbstract:
Navigation through large and unfamiliar facilities with labyrinths of corridors and rooms is difficult and often results in a person being lost. Additionally, locating a specific utility within a facility is often a tough task. The hypothesis tested in this research is that integrating real-time automated sensing technology and a Building Information Model will provide real time visualization that can assist in localization and navigation of a facility. The scope of this research is facility maintenance management during the Operation and Maintenance (O&M) phase of a facility. The thesis demonstrates how the integration of passive Radio Frequency Identification (RFID) tracking technology and Building Information Modeling (BIM) can assist in facilities maintenance management. The objectives of this research included 1) developing a framework that utilizes the integration of commercially-available RFID and a BIM model; 2) evaluating the framework for real-time resource location tracking within an indoor environment; and 3) developing an algorithm for real-time localization and visualization in a BIM model. A prototype application has been developed that simultaneously connects the RFID readers, a database, and a BIM model. The goal of this system is to have a real-time localization accuracy of 3 meters at 95% confidence. Testing was conducted in laboratory conditions, and the results show that the system error was within the 3 meters goal.
32
Shah, Ghalib Asadullah. "Energy-efficient Real-time Coordination And Routing Framework For Wireless Sensor And Actor Networks." Phd thesis, METU, 2007. http://etd.lib.metu.edu.tr/upload/12608239/index.pdf.
Full textAbstract:
In Wireless Sensor Actor Networks (WSANs), sensor nodes perform the sensing task and actor nodes take action based on the sensed phenomenon. The presence of actors in this configuration can not be benefited from, unless they are able to execute actions at right place and right time in the event region. The right place can be related to the accurate position of the sensor nodes. While, the right time is related to delivering the packets directly to the appropriate actors within the event specific response times. Hence, the efficient localization of sensor nodes, sensor-actor/actor-actor coordination and real-time routing is indispensable in WSANs. Furthermore, the limited energy levels and bandwidth of the state of art sensor nodes currently impose stringent requirements for low-complexity, low-energy, distributed coordination and cooperation protocols and their implementation.
In this study, we propose an integrated framework which addresses the issues of sensors localization, network configuration, data aggregation, real-time data delivery, sensor-actor/actor-actor coordination and energy saving mechanisms. The proposal incorporates novel approaches on three fronts(1) timing-based sensors localization (TSL) algorithm to localize the sensor nodes relative to actors, (2) real-time coordination and routing protocols and (3) energy conservation. The distributed real-time coordination and routing is implemented in addressing and greedy modes routing. A cluster-based real-time coordination and routing (RCR) protocol operates in addressing mode. The greedy mode routing approach (Routing by Adaptive Targeting, RAT) is a stateless shortest path routing. In dense deployment, it performs well in terms of delay and energy consumption as compared to RCR. To keep the traffic volume under control, the framework incorporates a novel real-time data aggregation (RDA) approach in RCR such that the packets deadlines are not affected. RDA is adaptive to the traffic conditions and provides fairness among the farther and nearer cluster-heads. Finally, framework incorporates a power management scheme that eliminates data redundancy by exploiting the spatial correlation of sensor nodes. Simulation results prove that the framework provides the real-time guarantees up to 95 % of the packets with lesser energy consumption of up to 33 % achieved using MEAC as compared to LEACH and SEP. The packet delivery ratio is also 60 % higher than that of semi-automated architecture. Furthermore the action accuracy is supported by TSL which restricts the localization errors less than 1 meter by tuning it according to the expected velocity of nodes and required accuracy.
33
Roussillon, Cyril. "Une solution opérationnelle de localisation pour des véhicules autonomes basée sur le SLAM." Thesis, Toulouse, INSA, 2013. http://www.theses.fr/2013ISAT0050/document.
Full textAbstract:
Les applications de la robotique mobile autonome en environnements extérieurs sont nombreuses : surveillance de site à la recherche d’anomalies, campagne d’acquisition de données,exploration, recherche de victimes sur des lieux de catastrophes, etc, et l’intérêt de la robotique pour ces applications est d’autant plus grand que les environnements peuvent être dangereux ou risqués pour l’homme. La localisation des robots est une fonction clé dans ces contextes car elle est indispensable à de nombreuses autres fonctions, particulièrement la construction de modèles d’environnement, l’exécution des trajectoires, ou la supervision des missions. Ces travaux présentent la construction d’une solution de localisation pour des robots autonomes,conçue pour être à la fois un outil générique de recherche et un outil opérationnel pour localiser nos robots lors de leurs missions de navigation autonome, capable de gérer de fortes dynamiques de mouvement. En partant d’une solution de localisation et cartographie simultanées (SLAM) basée sur l’utilisation d’une simple caméra, différentes solutions sont successivement construites en ajoutant progressivement des capteurs afin de pallier les difficultés rencontrées lors des évaluations, et ce jusqu’à obtenir un système robuste et précis combinant plusieurs caméras, une centrale inertielle et l’odométrie, et ayant en outre la possibilité d’intégrer des estimations de positions absolues quand elles peuvent être produites (par un récepteur GPS ou un algorithme exploitant une carte initiale). Une analyse profonde des capacités et limitations des différents systèmes est systématiquement effectuée, en considérant notamment l’intérêt d’estimer enligne les calibrages extrinsèques et biais des capteurs. Un accent particulier est mis sur l’exécution temps réel des algorithmes à bord du robot et sur leur robustesse : cela implique la résolution de nombreux problèmes, portant notamment sur les aspects temporels de la gestion des données. Une large évaluation sur différents jeux de données réalistes permet d’évaluer et de valider les différents développements proposés tout au long du manuscritThere are numerous applications of outdoor autonomous mobile robots : surveillance of areas to detect anomalies, data acquisition campaigns, exploration, search of victims in disaster areas, etc. Robot localization is a key function in these contexts because it is necessary fora lot of essential robotics tasks, in particular to build environment models, follow paths or supervise the execution of the missions.This work presents the development of a localization solution for autonomous robots, designedto be both a generic research tool and an effective tool to localize robots navigating with highlydynamic movements.Starting with a simultaneous localization and mapping (SLAM) solution using a single camera,several solutions are successively built by gradually adding sensors, until obtaining a robust and precise system combining several cameras, an inertial sensor and odometry, which is inaddition able to integrate absolute position measures when available (e.g. as provided byGPS or a map-based localization scheme). A in-depth analysis of the abilities and limitations of the different systems is systematically made, in particular considering the advantages of estimating online extrinsic calibration parameters and sensor biases. A particular emphasisis set on real time execution of the algorithms on board the robots and on their robustness,requiring to address various problems related to temporal aspects of data management.Thorough evaluations using different realistic datasets allows to evaluate and validate the proposed work throughout the manuscript
34
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.
35
Ceccarelli, Matteo. "Analisi sperimentale di un sistema di localizzazione UWB per applicazioni robotiche." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2022. http://amslaurea.unibo.it/25365/.
Full textAbstract:
Data la pervasività dell’elettronica nella vita moderna, sempre più interesse è stato posto nelle applicazioni di localizzazione. In ambienti indoor e outdoor, dove sono richieste precisioni dell’ordine delle decine di centimetri, i classici servizi GNSS non sono applicabili. Una tecnologia promettente è quella a banda ultra-larga (UWB), affermata recentemente sul mercato. Un’alternativa potrebbe essere l’utilizzo di sensori ottici con marker di riferimento, però la presenza di fumo e idrometeore presenti nell’ambiente potrebbero andare ad oscurare i marker, rendendo impossibile la localizzazione. Lo scopo della tesi è volto a studiare un sistema di localizzazione UWB, progettato dall’Università di Bologna, ora sviluppato e commercializzato, in un’applicazione robotica. In particolare, l’idea è quella di porre il sistema di localizzazione sopra un elemento mobile, per esempio nella parte terminale di un braccio meccanico, al fine di localizzare un oggetto dotato di nodo UWB, ricavando dinamicamente la posizione relativa tra il braccio e l’oggetto. La tesi si concentra inizialmente a livello teorico sulle caratteristiche delle principali tecnologie coinvolte, in particolare i sistemi UWB e il filtraggio Bayesiano, per poi trattare i limiti teorici della localizzazione, nei concetti di Cramér-Rao lower bound (CRLB) e geometric dilution of precision (GDOP). Da questi, si motiva l’utilizzo della tecnica two-way ranging (TWR) come principio di raccolta delle misure per la localizzazione, per poi ricavare le curve teoriche dell’errore di localizzazione, tenendo conto dei limiti geometrici imposti, utilizzate come riferimento per l’analisi dell’errore ottenuto con il sistema reale. La tecnologia viene testata in tre campagne di misura. Nelle prime due si osserva la presenza di un piano metallico parallelo alla direzione di propagazione, per esaminare gli effetti delle riflessioni sulla localizzazione, mentre nella terza campagna si considera la presenza di acqua dolce.
36
Rube, Martin. "Novel tools for interventional magnetic resonance imaging." Thesis, University of Dundee, 2014. https://discovery.dundee.ac.uk/en/studentTheses/7e3feb72-0102-431f-982a-b3cdd393994e.
Full textAbstract:
Magnetic Resonance Imaging (MRI) provides unique advantages such as superior soft tissue contrast, true multiplanar imaging, variable contrast mechanisms, measurement of temperature changes, perfusion and diffusion, and no ionizing radiation. Despite considerable research efforts in the field of interventional MRI, numerous challenges remain including restricted access to the patient, high acoustic noise and a shortage of MRI-safe devices. Novel methods and devices are presented in this thesis with the primary objective of enabling effective MRI-guided interventions, particularly abdominal needle and common catheter-based endovascular interventions. Firstly, a set of MRI-safe devices (guidewires, micro guidewires, catheters and micro catheters) were developed with passive or inductively coupling resonant markers for MRI visualisation. Secondly, a method was implemented for wireless tracking and dynamic guidance of instruments. Thirdly, a framework of technologies was developed for in-room display, wireless MRI remote control and multi-user communication along with a dedicated user interface and imaging protocol. These implementations were assessed in regards to MRI-safety, performance and usability and evaluated for MRI-guided liver biopsies, balloon angioplasty procedures and also for mechanical thrombolysis. Flow phantoms, Thiel soft-embalmed human cadavers with partially re-established perfusion and a porcine model were used for in vitro, ex vivo and in vivo validation, respectively. The results demonstrate that these interventions are experimentally feasible and practical when using the presented developments: automated device tracking and equipment designed for MRI-guided interventions streamlined procedural workflow. Specifically, it was shown that fast and accurate needle placements along complex trajectories were feasible using a wireless interactive display and control device with a dedicated user interface for interventions. Moreover, safe and efficacious balloon angioplasties of the iliac artery were practical using the described framework of technologies along with a dedicated MRI protocol. Finally, it was demonstrated that these developments could be adapted and applied to MRI-guided endovascular mechanical thrombolysis of the middle cerebral artery. The technologies, described in this thesis have been shown to overcome many of the present limitations and should therefore be useful for enabling MRI-guided interventions while not further constraining the operating physician in an already complex environment. Nevertheless, it is acknowledged that many crucial issues remain to be solved in the field of iMRI and in the context of the presented research. In particular further device optimisations, improvements of the tracking implementation along with further in vivo evaluations are required before moving towards clinical evaluation. This thesis sets the groundwork for moving ahead with the eventual clinical realisation of optimised MRI-guided interventions.
37
Charmette, Baptiste. "Localisation temps-réel d'un robot par vision monoculaire et fusion multicapteurs." Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2012. http://tel.archives-ouvertes.fr/tel-00828573.
Full textAbstract:
Ce mémoire présente un système de localisation par vision pour un robot mobile circulant dans un milieu urbain. Pour cela, une première phase d'apprentissage où le robot est conduit manuellement est réalisée pour enregistrer une séquence vidéo. Les images ainsi acquises sont ensuite utilisées dans une phase hors ligne pour construire une carte 3D de l'environnement. Par la suite, le véhicule peut se déplacer dans la zone, de manière autonome ou non, et l'image reçue par la caméra permet de le positionner dans la carte. Contrairement aux travaux précédents, la trajectoire suivie peut être différente de la trajectoire d'apprentissage. L'algorithme développé permet en effet de conserver la localisation malgré des changements de point de vue importants par rapport aux images acquises initialement. Le principe consiste à modéliser les points de repère sous forme de facettes localement planes, surnommées patchs plan, dont l'orientation est connue. Lorsque le véhicule se déplace, une prédiction de la position courante est réalisée et la déformation des facettes induite par le changement de point de vue est reproduite. De cette façon la recherche des amers revient à comparer des images pratiquement identiques, facilitant ainsi leur appariement. Lorsque les positions sur l'image de plusieurs amers sont connues, la connaissance de leur position 3D permet de déduire la position du robot. La transformation de ces patchs plan est complexe et demande un temps de calcul important, incompatible avec une utilisation temps-réel. Pour améliorer les performances de l'algorithme, la localisation a été implémentée sur une architecture GPU offrant de nombreux outils permettant d'utiliser cet algorithme avec des performances utilisables en temps-réel. Afin de prédire la position du robot de manière aussi précise que possible, un modèle de mouvement du robot a été mis en place. Il utilise, en plus de la caméra, les informations provenant des capteurs odométriques. Cela permet d'améliorer la prédiction et les expérimentations montrent que cela fournit une plus grande robustesse en cas de pertes d'images lors du traitement. Pour finir ce mémoire détaille les différentes performances de ce système à travers plusieurs expérimentations en conditions réelles. La précision de la position a été mesurée en comparant la localisation avec une référence enregistrée par un GPS différentiel.
38
Kechkar, Mohamed Adel. "Méthodes de reconstruction et de quantification pour la microscopie de super-résolution par localisation de molécules individuelles." Thesis, Bordeaux 2, 2013. http://www.theses.fr/2013BOR22130/document.
Full textAbstract:
Le domaine de la microscopie de fluorescence a connu une réelle révolution ces dernières années, permettant d'atteindre des résolutions nanométriques, bien en dessous de la limite de diffraction prédite par Abbe il y a plus d’un siècle. Les techniques basées sur la localisation de molécules individuelles telles que le PALM (Photo-Activation Light Microscopy) ou le (d)STORM (direct Stochastic Optical Reconstruction Microscopy) permettent la reconstruction d’images d’échantillons biologiques en 2 et 3 dimensions, avec des résolutions quasi-moléculaires. Néanmoins, même si ces techniques nécessitent une instrumentation relativement simple, elles requièrent des traitements informatiques conséquents, limitant leur utilisation en routine. En effet, plusieurs dizaines de milliers d’images brutes contenant plus d’un million de molécules doivent être acquises et analysées pour reconstruire une seule image. La plupart des outils disponibles nécessitent une analyse post-acquisition, alourdissant considérablement le processus d’acquisition. Par ailleurs la quantification de l’organisation, de la dynamique mais aussi de la stœchiométrie des complexes moléculaires à des échelles nanométriques peut constituer une clé déterminante pour élucider l’origine de certaines maladies. Ces nouvelles techniques offrent de telles capacités, mais les méthodes d’analyse pour y parvenir restent à développer. Afin d’accompagner cette nouvelle vague de microscopie de localisation et de la rendre utilisable en routine par des expérimentateurs non experts, il est primordial de développer des méthodes de localisation et d’analyse efficaces, simples d’emploi et quantitatives. Dans le cadre de ce travail de thèse, nous avons développé dans un premier temps une nouvelle technique de localisation et reconstruction en temps réel basée sur la décomposition en ondelettes et l‘utilisation des cartes GPU pour la microscopie de super-résolution en 2 et 3 dimensions. Dans un second temps, nous avons mis au point une méthode quantitative basée sur la visualisation et la photophysique des fluorophores organiques pour la mesure de la stœchiométrie des récepteurs AMPA dans les synapses à l’échelle nanométriqueThe field of fluorescence microscopy has witnessed a real revolution these last few years, allowing nanometric spatial resolutions, well below the diffraction limit predicted by Abe more than a century ago. Single molecule-based super-resolution techniques such as PALM (Photo-Activation Light Microscopy) or (d)STORM (direct Stochastic Optical Reconstruction Microscopy) allow the image reconstruction of biological samples in 2 and 3 dimensions, with close to molecular resolution. However, while they require a quite straightforward instrumentation, they need heavy computation, limiting their use in routine. In practice, few tens of thousands of raw images with more than one million molecules must be acquired and analyzed to reconstruct a single super-resolution image. Most of the available tools require post-acquisition processing, making the acquisition protocol much heavier. In addition, the quantification of the organization, dynamics but also the stoichiometry of biomolecular complexes at nanometer scales can be a key determinant to elucidate the origin of certain diseases. Novel localization microscopy techniques offer such capabilities, but dedicated analysis methods still have to be developed. In order to democratize this new generation of localization microscopy techniques and make them usable in routine by non-experts, it is essential to develop simple and easy to use localization and quantitative analysis methods. During this PhD thesis, we first developed a new technique for real-time localization and reconstruction based on wavelet decomposition and the use of GPU cards for super-resolution microscopy in 2 and 3 dimensions. Second, we have proposed a quantitative method based on the visualization and the photophysics of organic fluorophores for measuring the stoichiometry of AMPA receptors in synapses at the molecular scale
39
Birem, Merwan. "Localisation et détection de fermeture de boucle basées saillance visuelle : algorithmes et architectures matérielles." Thesis, Clermont-Ferrand 2, 2015. http://www.theses.fr/2015CLF22558/document.
Full textAbstract:
Dans plusieurs tâches de la robotique, la vision est considérée comme l’élément essentiel avec lequel la perception de l’environnement ou l’interaction avec d’autres utilisateurs peut se réaliser. Néanmoins, les artefacts potentiellement présents dans les images capturées rendent la tâche de reconnaissance et d’interprétation de l’information visuelle extrêmement compliquée. Il est de ce fait, très important d’utiliser des primitives robustes, stables et ayant un taux de répétabilité élevé afin d’obtenir de bonnes performances. Cette thèse porte sur les problèmes de localisation et de détection de fermeture de boucle d’un robot mobile en utilisant la saillance visuelle. Les résultats en termes de précision et d’efficacité des applications de localisation et de détection de fermeture sont évalués et comparés aux résultats obtenus avec des approches de l’état de l’art sur différentes séquences d’images acquises en milieu extérieur. Le principal inconvénient avec les modèles proposés pour l’extraction de zones de saillance est leur complexité de calcul, ce qui conduit à des temps de traitement important. Afin d’obtenir un traitement en temps réel, nous présentons dans ce mémoire l’implémentation du détecteur de régions saillantes sur la plate forme reconfigurable DreamCamIn several tasks of robotics, vision is considered to be the essential element by which the perception of the environment or the interaction with other users can be realized. However, the potential artifacts in the captured images make the task of recognition and interpretation of the visual information extremely complicated. It is therefore very important to use robust, stable and high repeatability rate primitives to achieve good performance. This thesis deals with the problems of localization and loop closure detection for a mobile robot using visual saliency. The results in terms of accuracy and efficiency of localization and closure detection applications are evaluated and compared to the results obtained with the approaches provided in literature, both applied on different sequences of images acquired in outdoor environnement. The main drawback with the models proposed for the extraction of salient regions is their computational complexity, which leads to significant processing time. To obtain a real-time processing, we present in this thesis also the implementation of the salient region detector on the reconfigurable platform DreamCam
40
Szentandrási, István. "Určení pozice kamery v reálném čase pro rozšířenou realitou." Doctoral thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2016. http://www.nusl.cz/ntk/nusl-412551.
Full textAbstract:
Definované markery tvoří základ určování polohy kamery pro velké množství aplikací s rozšířenou realitou, v případě že jsou přísné požadavky na rychlost a robustnost. Tato práce popisuje účinnou metodu pro určení pózy kamery pomocí Uniformního pole markerů a několik realistických aplikací na bázi popsané metody. Metoda je velice výpočetně levná a poskytuje spolehlivou detekci pro několik výpočetních platforem, včetně běžných chytrých telefonů. Markery jako část zobrazené informace na monitorech jsou použité v této práci pro určení relativní orientaci mezi poskytovatelem obsahu a užívatelským zařízením, sloužícím pro výběr prvků užívatelského rozhraní při interakci a migraci úkolů. Ve filmařském průmyslu poskytuje popsaná metoda pro zjištění polohy kamery jako součást klíčovaní pozadí filmářům živý náhled virtuální scény. Výsledky ukazují, že popsaná metoda pro detekci pole markerů má srovnatelnou úspěšnost a přesnost v porovnání s ostatními metodami na bázi markerů a je několikrát rýchlejší. Aplikace zahrnuté v této práci podle výsledků testů jsou životaschopné - rychlejší a levnější - alternativy k existujícím řešením.
41
Herman, David. "Lokální navigace autonomního mobilního robota." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2010. http://www.nusl.cz/ntk/nusl-237248.
Full textAbstract:
This paper deals with the topic of design of a navigation system for an autonomous mobile robot in a park-like environment. Precisely, designing methods for road detection using available sensoric system, designing a mathematical model for fusion of these data, and suggesting a representation of an environment suitable for planning and local navigation.
42
Berro, Soumaya. "Identification of muscle activation schemes by inverse methods applied on HD-sEMG signals." Electronic Thesis or Diss., Compiègne, 2022. http://www.theses.fr/2022COMP2708.
Full textAbstract:
L'identification rapide ou en temps réel de l'activation spatio-temporelle des unités motrices (UM) qui représentent les unités fonctionnelles du système neuromusculaire est fondamentale dans les applications de contrôle des prothèses et en réhabilitation fonctionnelle. Cependant, cette procédure demande un temps de calcul énorme. Par conséquent, le travail de cette thèse a été consacré à fournir un algorithme permettant l'identification en temps réel des stratégies d'activation spatiale et temporelle des UMs en appliquant des méthodes inverses sur les signaux HD-sEMG (électromyogramme de surface à haute densité) à partir d'une grille placée sur le Biceps Brachial (BB). À cette fin, nous proposons une approche innovante, qui implique l'utilisation de la méthode inverse classique de minimisation de norme et une interpolation de courbe en 3D, à savoir l'approche est nommée CFB-MNE. Cette méthode, fondée sur l'identification inverse (estimation de la norme minimale) couplée à un dictionnaire des potentiels d'action des unités motrices simulées (MUAP) d'un modèle récent et testée sur des simulations, a permis la localisation en temps réel des unités motrices individuelles simulées. Une analyse de robustesse (modifications anatomiques, physiologiques et instrumentales) a ensuite été effectuée pour vérifier l'efficacité de l'algorithme proposé. Enfin, l'algorithme proposé a été testé sur des UMs avec des schémas de recrutement réalistes donnant des résultats prometteurs et encourageants en identification spatiale et temporelle sur trois scenarios. Pour conclure, en perspectives, les résultats prometteurs obtenus suggèrent l'utilisation de l'apprentissage automatique et de l'intelligence artificielle (IA) pour améliorer encore les performances de l'algorithme proposéFast or real-time identification of the spatiotemporal activation of Motor Units (MUs), functional units of the neuromuscular system, is fundamental in applications as prosthetic control and rehabilitation guidance but often dictates expensive computational times. Therefore, the thesis work was devoted to providing an algorithm that enables the real-time identification of MU spatial and temporal activation strategies by applying inverse methods on HD-sEMG (high-density surface electromyogram) signals from a grid placed over the Biceps Brachii (BB). For this purpose, we propose an innovative approach, that involves the use of the classical minimum norm inverse method and a 3D fitting curve interpolation, namely CFB-MNE approach. This method, based on inverse identification (minimum norm estimation) coupled to simulated motor unit action potential (MUAP) dictionary from a recent model and tested on simulations, allowed the real time localization of simulated individual motor units. A robustness analysis (anatomical, physiological, and instrumental modifications) was then performed to verify the efficiency of the proposed algorithm. Finally, the proposed algorithm was tested on MUs with realistic recruitment patterns giving promising results in both spatial and temporal identification. To conclude, a door to future perspectives was opened, according to the obtained promising results, suggesting the use of machine learning and artificial intelligence (AI) to further boost the performance of the proposed algorithm
43
Yang, Huai-Sin, and 楊懷新. "Real-Time Visual Localization and Mapping." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/4sxz22.
Full textAbstract:
碩士國立臺北科技大學
電機工程系所
97
The thesis proposes a method for a robot which uses map of the environment to localize itself accurately. A vision-based mobile robot localization and mapping algorithm which use SIFT (scale invariant of feature transform) to select suitable visual landmarks proposed in the thesis for mobile robot localization and database building, and RANSAC (Random Sample Consensus) is used to find affine transformation matrix and robot localization in image sequences and visual database. The control method of speed and direction of robot is developed to affine transformation matrix, and do designated tasks at specified destination. A robot can successful navigates and localizes in outdoor or indoor by using this method. It enter VSLAM (Visual Simultaneous Localization and Mapping) which will begin to find effective obstacle features when detect obstacles in navigation. The thesis proposes an improved method of VSLAM feature match in short distance which can be accelerated and accurate to find actual feature position in the image. Predicted feature''s position and actual feature''s position can updata EKF(Extended Kalman Filter) model to calculate accurate feature position in next time. VSLAM effectively build feature map and mobile robot localization at a period of time, and avoid the obstacle after entering the target distance.
44
Yeh, Chung-Ju, and 葉宗儒. "FPGA-Based Real Time License Plate Localization System." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/rry64e.
Full textAbstract:
碩士國立臺灣師範大學
資訊工程研究所
97
The study of license plate recognition (LPR) has been developed for over the decade of years. There were also plenty of contributions by this area of research. However, LPR is not the universal system in human daily life. The reason is that image processing costs large amount of computation by personal computer so that license plate does not preciously and slowly locate. If license plate location can be implemented by hardware, it will enhance the performance, speed, preciseness and reliability for the use of the system of intelligence transportation. The thesis proposed an approach of license plate location implemented by hardware in order to improve the speed of operation. In section of license plate location, using the color attribute of license plate is to be the feature for detecting four kinds of license plate in Taiwan, that is to eliminate the edge which is not belong to the color of license plate by color edge detection. Because the remained license- plate edges are almost closed to each other, the approach of morphology using closing, opening and dilation respectively can connect those edges to be a bigger region and remove the noise out simultaneously. After binarization, applying connect component labeling is to assign the unique number to each region. The size filter and aspect ratio can seize the location of license plate. In experimental results, the execution time of one color image is about 6.543ms by FPGA architecture, Color edge detection
45
Chien, Kuang-Hung, and 簡光宏. "Real-time Localization from LiDAR and RGB Cues." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/zd946p.
Full textAbstract:
碩士國立清華大學
資訊系統與應用研究所
107
This thesis describes a real-time vehicle localization system. This system uses LiDAR and RGB Cues to achieve simultaneous localization and mapping (SLAM). Existing localization methods that rely on merely the GPS information are more suitable for navigation systems with static maps. Such navigation systems cannot either adapt to dynamic scenarios or benefit from the abundant visual cues in the surroundings. In our system, we use simultaneous localization and mapping (SLAM) to construct the point cloud from the visual cues acquired by a monocular RGB camera and the corresponding LiDAR information. Our system compares the current reconstructed point cloud with the pre-acquired, GPS-aware point cloud in the database, and finally infers the accurate position and odometry of the vehicle via continuous adjustment as the vehicle moves forward.
46
Wang, Wei-Chi, and 王偉齊. "Real time facial feature localization using active shape model." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/05025993295701710590.
Full textAbstract:
碩士國立屏東教育大學
資訊科學系碩士班
102
In this thesis, we improve the approach published by Stephen Milborrow in 2007 to detect facial features quickly. The traditional ASM search needs to obtain the average face from training database, and the average face is used to calculate the facial features. In this thesis, we propose a way to use the facial features position of previous frame to being the initial position in current frame and ignore the detection of face position. Thereby, we remove the masses of computation to enhance the speed of the program. To improve the correctness of detecting the facial, we also redesign training database and the experiments show that results can be improved.
47
Lin, Guang-Cheng, and 林廣誠. "Study on Monte Carlo Localization and Real-time Map Building." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/81669617880998413874.
Full textAbstract:
碩士國立高雄第一科技大學
電機工程研究所碩士班
103
If wanting to work in an unknown environment, then people need to explore and record the environment information. If wanting to work in a known environment, then they need to localize the position of the this environment to execute assigned missions, similar to humanoid robots. In this experiment, Similar to real human, humanoid robot sensor only uses a computer vision system with webcam is designed for localization and map building, rather than using ultrasound, infrared and laser sensors for distance measurement. To finish the localization and map building depends on single camera is quite challenging for humanoid robot system. In this thesis, Monte Carlo localization method for localization in the known map, and update the map information immediately with unknown obstacles. In addition, for reducing convergence time of Monte Carlo localization, combined with trilateration method to the initial position is also included.
48
Islam, Mohd Noor. "Real time endoscope capsule localization using the electromagnetic field method." Thesis, 2018. http://hdl.handle.net/1959.13/1355544.
Full textAbstract:
Research Doctorate - Doctor of Philosophy (PhD)Capsule endoscope systems require localization within the gastrointestinal tract in order to efficiently identify lesions. Commercialized capsule systems presently use the radio signal strength indicator to track the capsule, which has limited accuracy. Methods based on X-Rays, Gamma-Rays, MRI, ultrasound, and visible wave methods are expensive and may pose a health risk with long-term exposure. The permanent magnet method provides satisfactory accuracy but is limited in range and is susceptible to interference. In this thesis, an electromagnetic tracking system is proposed to overcome the limitations of permanent magnet methods. The six-degree-of-freedom localization system consists of three concentric orthogonal transmitting and sensing coils. The measurement range of this arrangement is only dependent on the transmitter and sensing coil geometries. An algorithm is described for optimizing the transmitter parameters such the geometry, applied power, frequency, and the available volume. A triaxial arrangement of sensor coils is then described which provides 59% more measurement range than traditional cylindrical coils. Resonance-coupling is also investigated to passively increase the induced voltage and enhance the measurement range. A consequence of resonance enhancement is an increased settling time which reduces the measurement rate. A resistive tuning method is proposed to control the trade-off between gain and settling time. Experimental results are presented throughout to clarify and validate the concepts presented.
49
Lin, Shih-Chin, and 林仕晉. "People Help People : A Community-based Fingerprinting Real-time Localization System." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/32012815522823302375.
Full textAbstract:
碩士國立交通大學
網路工程研究所
96
Location-based services (LBSs) have emerged as one of the killer applications for mobile computing and wireless data services. Among all localization systems, the RF-based pattern matching schemes are the most cost effective and useful. However, these schemes may incur high calibration efforts and the high comparison cost in the large-scale environment. We adopt a novel community-based system design to solve the calibration problem and develop the confidence filter and feedback tuning mechanisms to guarantee the data reliability. For computation speed and finer location estimation,We apply two critical large-scale algorithms to this system. We also design a location-based service architecture for this community based fingerprinting real time localization system.
50
Xuan-FanYang and 楊軒釩. "Autonomous Omni-Directional Mobile Robot - The Application of Real-Time Localization." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/39164061333001969861.
Full textAbstract:
碩士國立成功大學
工程科學系碩博士班
98
The goal of this thesis is to design an omni-directional vehicle with the ability to recognize the objects in order to localize and exchange these objects in near distance. In light of the ability to recognize and localize the objects, the Autonomous Mobile Vehicle (AMV) together with the real-time image process techniques and mobile platform was designed to adapt to environment of insufficient information. The AMV with a group of CCD Webcam which captures the image was controlled by the mobile platform of omni-directional wheels. The AMV transmits image through the Netbook (ASUS EEEPC 901) to implement the real-time digital image processing techniques which is made use of PIC16F877 as its control chip. We use Borland C++ Builder 6.0 to accomplish the Human-Machine interface system. Through the Human-Machine interface system we are able to send signals to command the AMV which is driven by of direct current motors and communicates with the Netbook Computer through RS232. In terms of experiments and results, the AMV coordinated with visual localization provides the efficient function to exchange objects automatically. The research in the real environment shows that the research offers a better method to deal with the problems about the robot failed to exchange objects precisely in the past.