Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Stereo.
Thèses sur le sujet « Stereo »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleures thèses pour votre recherche sur le sujet « Stereo ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
1
Greenfeld, Joshua S. « A stereo vision approach to automatic stereo matching in photogrammetry / ». The Ohio State University, 1987. http://rave.ohiolink.edu/etdc/view?acc_num=osu1487331541710317.
Texte intégral
2
Aydinoğlu, Behçet Halûk. « Stereo image compression ». Diss., Georgia Institute of Technology, 1997. http://hdl.handle.net/1853/15447.
Texte intégral
3
O'Kennedy, Brian James. « Stereo camera calibration ». Thesis, Stellenbosch : Stellenbosch University, 2002. http://hdl.handle.net/10019.1/53063.
Texte intégralRésumé :
Thesis (MScEng)--Stellenbosch University, 2002.ENGLISH ABSTRACT: We present all the components needed for a fully-fledged stereo vision system, ranging from object detection through camera calibration to depth perception. We propose an efficient, automatic and practical method to calibrate cameras for use in 3D machine vision metrology. We develop an automated stereo calibration system that only requires a series of views of a manufactured calibration object in unknown positions. The system is tested against real and synthetic data, and we investigate the robustness of the proposed method compared to standard calibration practice. All the aspects of 3D stereo reconstruction is dealt with and we present the necessary algorithms to perform epipolar rectification on images as well as solving the correspondence and triangulation problems. It was found that the system performs well even in the presence of noise, and calibration is easy and requires no specialist knowledge.
AFRIKAANSE OPSOMMING: Ons beskryf al die komponente van 'n omvattende stereo visie sisteem. Die kern van die sisteem is 'n effektiewe, ge-outomatiseerde en praktiese metode om kameras te kalibreer vir gebruik in 3D rekenaarvisie. Ons ontwikkel 'n outomatiese, stereo kamerakalibrasie sisteem wat slegs 'n reeks beelde van 'n kalibrasie voorwerp in onbekende posisies vereis. Die sisteem word getoets met reële en sintetiese data, en ons vergelyk die robuustheid van die metode met die standaard algoritmes. Al die aspekte van die 3D stereo rekonstruksie word behandel en ons beskryf die nodige algoritmes om epipolêre rektifikasie op beelde te doen sowel as metodes om die korrespondensie- en diepte probleme op te los. Ons wys dat die sisteem goeie resultate lewer in die aanwesigheid van ruis en dat kamerakalibrasie outomaties kan geskied sonder dat enige spesialis kennis benodig word.
4
Sac, Hakan. « Opti-acoustic Stereo Imaging ». Master's thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12614782/index.pdf.
Texte intégralRésumé :
In this thesis, opti-acoustic stereo imaging, which is the deployment of two-dimensional (2D) high frequency imaging sonar with the electro-optical camera in calibrated stereo configuration, is studied.
Optical cameras give detailed images in clear waters. However, in dark or turbid waters, information coming from electro-optical sensor is insufficient for accurate scene perception. Imaging sonars, also known as acoustic cameras, can provide enhanced target details under these scenarios. To illustrate these visibility conditions, a 2D high frequency imaging sonar simulator as well as an underwater optical image simulator is developed. A computationally efficient algorithm is also proposed for the post-processing of the returned sonar signals.
Where optical visibility allows, integration of the sonar and optical images effectively provides binocular stereo vision capability and enables the recovery of three-dimensional (3D) structural information. This requires solving the feature correspondence problem for these completely different sensing modalities. Geometrical interpretation of this problem is examined on the simulated optical and sonar images. Matching the features manually, 3D reconstruction performance of opti-acoustic system is also investigated. In addition, motion estimation from opti-acoustic image sequences is studied.
Finally, a method is proposed to improve the degraded optical images with the help of sonar images. First, a nonlinear mapping is found to match local the features in opti-acoustical images. Next, features in the sonar image is mapped to the optical image using the transformation. Performance of the mapping is evaluated for different scene geometries.
5
Jiang, Qin. « Stereo image sequence compression ». Diss., Georgia Institute of Technology, 2000. http://hdl.handle.net/1853/15634.
Texte intégral
6
Powell, Christopher. « Mutual illumination photometric stereo ». Thesis, University of East Anglia, 2018. https://ueaeprints.uea.ac.uk/67065/.
Texte intégralRésumé :
Many techniques have been developed in computer vision to recover three-dimensional shape from two-dimensional images. These techniques impose various combinations of assumptions/restrictions of conditions to produce a representation of shape (e.g. surface normals or a height map). Although great progress has been made it is a problem which remains far from solved. In this thesis we propose a new approach to shape recovery - namely `mutual illumination photometric stereo'. We exploit the presence of colourful mutual illumination in an environment to recover the shape of objects from a single image.
7
Aumond, Bernardo Dantas 1972. « High precision stereo profilometry ». Thesis, Massachusetts Institute of Technology, 2001. http://hdl.handle.net/1721.1/88892.
Texte intégralRésumé :
Thesis (Ph.D.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering, 2001.Includes bibliographical references (leaves 186-190).
Metrological data from sample surfaces can be obtained by using a variety of profilome try methods. Atomic Force Microscopy (AFM), which relies on contact inter-atomic forces to extract topographical images of a sample, is one such method that can be used on a wide range of surface types, with possible nanometer resolution (both vertical andlateral). However, AFM images are commonly distorted by convolution, which reduces metrological accuracy. This type of distortion is more significant when the sample surface containshigh aspect ratio features such as lines, steps or sharp edges or when probe and sample share similar characteristic dimensions. Therefore, as the size of engineered features arepushed into the micrometer and sub-micrometer range by the development of new high precision fabrication techniques, convolution distortions embedded in the images becomeincreasingly more significant. Aiming at mitigating these distortions and recovering metrology sound ness, we introduce a novel image deconvolution scheme based on the principle of stereo imaging. Multiple images of a sample, taken at different angles, allow for separation ofcon volution artifacts from true topographic data. As a result, accurate samplereconstruction and probe shape estimation can be achieved simultaneously. Additionally, shadow zones, which are areas of the sample that cannot be reached by the AFM probe, are greatly re duced. Most importantly, this technique does not require a priori probe characterizationor any sort of shape assumption. It also reduces the need for slender or sharper probes,which, on one hand, induce less convolution distortion but, on the other hand, are more prone to wear and damage, thus decreasing the overall inspection system reliability.
(cont.) This research project includes a survey of current high precision metrology tools and an in-depthanalysis of the state of the art deconvolution techniques for probe based metrology instruments. Next, the stereo imaging algorithm is introduced, simulation results presented and anerror analysis is conducted. Finally, experimental validations of the technique are carried outfor an industrial inspection application where the characteristic dimensions of the samplesare in the nanometer range. The technique was found to be robust and insensitive to probe or shape geometries. Furthermore, the same framework was deemed to be applicable to other probe based imaging techniques such as mechanical stylus profilometers and scanning tunneling microscopy.
by Bernardo Dantas Aumond.
Ph.D.
8
Wildes, Richard Patrick. « On interpreting stereo disparity ». Thesis, Massachusetts Institute of Technology, 1989. http://hdl.handle.net/1721.1/17262.
Texte intégral
9
Capps, Michael Vincent 1972. « Shared-Frustum stereo rendering ». Thesis, Massachusetts Institute of Technology, 2000. http://hdl.handle.net/1721.1/81521.
Texte intégralRésumé :
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2000.Includes bibliographical references (p. 52-54).
by Michael Vincent Capps.
S.M.
10
Bolelli, Maria Virginia. « Neurogeometry of stereo vision ». Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS107.
Texte intégralRésumé :
Ce travail vise à développer un modèle neurogéométrique de la vision stéréo, basé sur les architectures corticales impliquées dans le problème de la perception 3D et les mécanismes neuronaux générés par les disparités rétiniennes. Nous l'appliquons pour reproduire des expériences phénoménologiques ainsi que pour traiter des images 3D, en identifiant des percepts visuels tridimensionnels dans l'espace, en résolvant le problème de correspondance. Tout d'abord, nous proposons une géométrie sub-riemannienne pour la vision stéréo. Cette proposition s'inspire du travail sur le problème de la stéréo effectué par Li et Zucker, et elle utilise les outils sub-riemanniens introduits par Citti et Sarti pour la vision monoculaire. En particulier, nous présentons une interprétation mathématique des mécanismes neuronaux qui sous-tendent le comportement des cellules binoculaires, qui intègrent les entrées monoculaires, en introduisant un espace fibré corticales approprié. La compatibilité naturelle entre la triangulation stéréo et les modèles neurophysiologiques (modèle d'énergie binoculaire) montre que ces cellules binoculaires sont sensibles soit à la position et soit à l'orientation. Nous modélisons donc leur action dans l'espace R^3xS^2 équipé d'une métrique sub-riemannienne. Les courbes intégrales de la structure sub-riemannienne éclairent les calculs qui sous-tendent le problème de correspondance. Elles codent non seulement les variables de l'espace, mais aussi la courbure et la torsion, qui sont nécessaires pour résoudre la correspondance 3D. De plus, un éventail de ces courbes peut modéliser l'analogue 3D des champs d'association psychophysiques de Field, Heyes et Hess. Ceci illustre comment une bonne continuation dans le monde généralise une bonne continuation en 2D. Ensuite, nous étudions la constitution d'unités perceptuelles 3D dans la scène tridimensionnelle générée à partir de la géométrie sub-riemannienne. Ces unités perceptuelles émergent comme une conséquence de la connexion cortico-corticale aléatoire des cellules binoculaires. Nous présentons le processus stochastique à la base de ce phénomène, en considérant une version stochastique opportune des courbes intégrales. Nous générons une famille de solutions fondamentales pour l'opérateur de Kolmogorov associé au processus stochastique généré. Cette famille représente la probabilité d'interaction entre les cellules binoculaires et est mise en oeuvre comme un modèle de facilitation pour définir l'évolution de l'activité de la population neuronale. Cette activité est généralement modélisée par une équation de champ moyen. L'existence et l'unicité d'une solution découlent classiquement du problème de Cauchy dans les espaces de Banach. En revanche, l'analyse de stabilité est effectuée à l'aide de la méthode de Lyapunov, ce qui conduit à la prise en compte du problème des valeurs propres associé. Nous démontrons que les unités perceptuelles tridimensionnelles apparaissent de façon naturelle, à partir de la version discrète du problème des valeurs propres. Enfin, nous mettons en évidence la relation entre les solutions fondamentales des opérateurs géométriques apparaissant dans les espaces impliqués dans notre modèle: l'espace des positions et des orientations R^3xS^2 et le groupe de Lie SE(3). Nous étudions d’abord l'existence d'une isométrie (locale) entre ces deux espaces, avec la métrique induite par la structure corticale et sa contrepartie dans SE(3). Enfin, nous relions le comportement des solutions fondamentales dans les deux espaces en utilisant la notion de soulèvement d'opérateurThis work aims to develop a neurogeometric model of stereo vision, based on cortical architectures involved in the problem of 3D perception and neural mechanisms generated by retinal disparities. We apply it to reproduce phenomenological experiments as well as to process 3D images, identifying three-dimensional visual percepts in space, solving the correspondence problem. First, we provide a sub-Riemannian geometry for stereo vision. This proposal is inspired by the work on the stereo problem by Li and Zucker, and it uses sub-Riemannian tools introduced by Citti and Sarti for monocular vision. In particular, we present a mathematical interpretation of the neural mechanisms underlying the behavior of binocular cells, that integrate monocular inputs, by introducing a suitable cortical fiber bundle. The natural compatibility between stereo geometry (stereo triangulation) and neurophysiological models (binocular energy model) shows that these binocular cells are sensitive to position and orientation. Therefore, we model their action in the space R^3xS^2 equipped with a sub-Riemannian metric. Integral curves of the sub-Riemannian structure shed light on the computations underlying the correspondence problem. They encode not only the variables of the space, but also curvature and torsion, which are necessary for the 3D matching. Moreover, a fan of these curves can model the 3D analog of the psychophysical association fields of Field, Heyes and Hess, for the 3D process of regular contour formation, studied by psychophysical experiments. This illustrates how good continuation in the world generalizes good continuation in the plane, as conjectured by Li and Zucker. As a second step, we study the constitution of 3D perceptual units in the three-dimensional scene generated from the sub-Riemannian geometry. These perceptual units emerge as a consequence of the random cortico-cortical connection of binocular cells. We present the stochastic process at the basis of this phenomenon, by considering an opportune stochastic version of the integral curves. We generate a family of kernels through the forward Kolmogorov operator associated to the generated stochastic process, and approximate them using a Monte Carlo simulation-based method. These kernels represent the probability of interaction between binocular cells and are implemented as facilitation patterns to define the evolution in time of neural population activity at a point. This activity is usually modeled through a mean field equation. The existence and uniqueness of a solution classically follow from the Cauchy problem in Banach spaces, while the stability analysis is performed using the Lyapunov method, leading to the consideration of the associated eigenvalue problem. We show that three-dimensional perceptual units arise naturally from the discrete version of the eigenvalue problem associated to the integro-differential equation of the population activity. Finally, we highlight the relation between the fundamental solutions of the geometric operators arising in the spaces involved in our model, namely the space of positions and orientations R^3xS^2 and the Lie group of three-dimensional rigid body motions SE(3). We first provide the existence of a (local) isometry between these two spaces, with the metric induced by the cortical structure and its SE(3) counterpart. Finally, we relate the behavior of fundamental solutions in both spaces using the notion of lifting of operator
11
Zhang, Li. « Spacetime stereo and its applications / ». Thesis, Connect to this title online ; UW restricted, 2005. http://hdl.handle.net/1773/6865.
Texte intégral
12
Liu, Qin. « Resolving ambiguity in computational stereo ». Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape10/PQDD_0028/MQ40746.pdf.
Texte intégral
13
Li, Fuxing. « Active stereo for AGV navigation ». Thesis, University of Oxford, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.338984.
Texte intégral
14
Ross, Alistair. « Stereo reconstruction of prehistoric footprints ». Thesis, University of Nottingham, 2013. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.597104.
Texte intégralRésumé :
The preservation and understanding of our past is fundamental to our development as a society and without the dedicated work of scientists, archaeologists and historians, the clues as to how we have evolved over the millennia would be lost. The work underlying this thesis provides a permanent 3-dimensional record of the hominid trackway discovered at Laetoli, Tanzania in 1978 from the stereo photographs taken during the expedition. Despite great care and attention from the archaeologists, many of the footprints have, since initial excavation, been irreparably damaged and as a result, the photographs and 3-dimensional models produced are all that remain of a vitally important discovery. In order to overcome issues presented by the original stereo photographs, robust reconstruction techniques have been implemented in conjunction with a novel segmentation approach for the extraction of the footprint from the background surface. The accuracy of the resulting models is then assessed by way of photogrammetric plots of the footprints, drawn soon after their discovery. This is achieved via a novel contour matching and evaluation technique. Finally, the results of the application of these algorithms to the entire laetoli footprint dataset are provided for the benefit of future researchers in related fields.
15
Moravec, Kimberly Lynn Cooper. « Scale trees for stereo vision ». Thesis, University of East Anglia, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.365022.
Texte intégral
16
Crossley, Simon. « Robust temporal stereo computer vision ». Thesis, University of Sheffield, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.327614.
Texte intégral
17
Pollard, Stephen. « Identifying correspondences in binocular stereo ». Thesis, University of Sheffield, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283563.
Texte intégral
18
Kordelas, Georgios. « Accurate and fast stereo vision ». Thesis, Queen Mary, University of London, 2015. http://qmro.qmul.ac.uk/xmlui/handle/123456789/9546.
Texte intégralRésumé :
Stereo vision from short-baseline image pairs is one of the most active research fields in computer vision. The estimation of dense disparity maps from stereo image pairs is still a challenging task and there is further space for improving accuracy, minimizing the computational cost and handling more efficiently outliers, low-textured areas, repeated textures, disparity discontinuities and light variations. This PhD thesis presents two novel methodologies relating to stereo vision from short-baseline image pairs: I. The first methodology combines three different cost metrics, defined using colour, the CENSUS transform and SIFT (Scale Invariant Feature Transform) coefficients. The selected cost metrics are aggregated based on an adaptive weights approach, in order to calculate their corresponding cost volumes. The resulting cost volumes are merged into a combined one, following a novel two-phase strategy, which is further refined by exploiting semi-global optimization. A mean-shift segmentation-driven approach is exploited to deal with outliers in the disparity maps. Additionally, low-textured areas are handled using disparity histogram analysis, which allows for reliable disparity plane fitting on these areas. II. The second methodology relies on content-based guided image filtering and weighted semi-global optimization. Initially, the approach uses a pixel-based cost term that combines gradient, Gabor-Feature and colour information. The pixel-based matching costs are filtered by applying guided image filtering, which relies on support windows of two different sizes. In this way, two filtered costs are estimated for each pixel. Among the two filtered costs, the one that will be finally assigned to each pixel, depends on the local image content around this pixel. The filtered cost volume is further refined by exploiting weighted semi-global optimization, which improves the disparity accuracy. The handling of the occluded areas is enhanced by incorporating a straightforward and time efficient scheme. The evaluation results show that both methodologies are very accurate, since they handle efficiently low-textured/occluded areas and disparity discontinuities. Additionally, the second approach has very low computational complexity. Except for the aforementioned two methodologies that use as input short-baseline image pairs, this PhD thesis presents a novel methodology for generating 3D point clouds of good accuracy from wide-baseline stereo pairs.
19
Gillett, Walter Eisner. « Issues in parallel stereo matching ». Thesis, Massachusetts Institute of Technology, 1988. http://hdl.handle.net/1721.1/14600.
Texte intégral
20
Shi, Fangmin. « Wavelet transforms for stereo imaging ». Thesis, University of South Wales, 2002. https://pure.southwales.ac.uk/en/studentthesis/wavelet-transforms-for-stereo-imaging(65abb68f-e30b-4367-a3a8-b7b3df85f566).html.
Texte intégralRésumé :
Stereo vision is a means of obtaining three-dimensional information by considering the same scene from two different positions. Stereo correspondence has long been and will continue to be the active research topic in computer vision. The requirement of dense disparity map output is great demand motivated by modern applications of stereo such as three-dimensional high-resolution object reconstruction and view synthesis, which require disparity estimates in all image regions. Stereo correspondence algorithms usually require significant computation. The challenges are computational economy, accuracy and robustness. While a large number of algorithms for stereo matching have been developed, there still leaves the space for improvement especially when a new mathematical tool such as wavelet analysis becomes mature. The aim of the thesis is to investigate the stereo matching approach using wavelet transform with a view to producing efficient and dense disparity map outputs. After the shift invariance property of various wavelet transforms is identified, the main contributions of the thesis are made in developing and evaluating two wavelet approaches (the dyadic wavelet transform and complex wavelet transform) for solving the standard correspondence problem. This comprises an analysis of the applicability of dyadic wavelet transform to disparity map computation, the definition of a waveletbased similarity measure for matching, the combination of matching results from different scales based on the detectable minimum disparity at each scale and the application of complex wavelet transform to stereo matching. The matching method using the dyadic wavelet transform is through SSD correlation comparison and is in particular detailed. A new measure using wavelet coefficients is defined for similarity comparison. The approach applying a dual tree of complex wavelet transform to stereo matching is formulated through phase information. A multiscale matching scheme is applied for both the matching methods. Imaging testing has been made with various synthesised and real image pairs. Experimental results with a variety of stereo image pairs exhibit a good agreement with ground truth data, where available, and are qualitatively similar to published results for other stereo matching approaches. Comparative results show that the dyadic wavelet transform-based matching method is superior in most cases to the other approaches considered.
21
Dovesi, Pier Luigi. « Real-Time Semantic Stereo Matching ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-280835.
Texte intégralRésumé :
Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields. To fully accomplish this task, an autonomous agent has to infer the 3D structure of the sensed scene (to know where it looks at) and its content (to know what it sees). To tackle the two tasks, deep neural networks trained to infer semantic segmentation and depth from stereo images are often the preferred choices. Specifically, Semantic Stereo Matching can be tackled by either standalone models trained for the two tasks independently or joint end-to-end architectures. Nonetheless, as proposed so far, both solutions are inefficient because requiring two forward passes in the former case or due to the complexity of a single network in the latter, although jointly tackling both tasks is usually beneficial in terms of accuracy. In this paper, we propose a single compact and lightweight architecture for real-time semantic stereo matching. Our framework relies on coarse-to-fine estimations in a multi-stage fashion, allowing: i) very fast inference even on embedded devices, with marginal drops in accuracy, compared to state-of-the-art networks, ii) trade accuracy for speed, according to the specific application requirements. Experimental results on high-end GPUs as well as on an embedded Jetson TX2 confirm the superiority of semantic stereo matching compared to standalone tasks and highlight the versatility of our framework on any hardware and for any application. The work described in this thesis is also available in [1], ICRA 2020.Scenförståelse spelar en viktig roll inom robotik, självnavigering, augmented reality och många andra områden. För att fullständigt kunna utföra denna uppgift måste en autonom agent kunna förstå 3D-strukturen i sin omgivning (för att veta var det den tittar på är) och omgivningens innehåll (för att veta vad det är den ser). För att lösa dessa uppgifter är ofta det föredragna valet att träna djupa neurala nätverk till att beräkna semantisk segmentering och pixeldjup från stereobilder. Specifikt kan semantisk stereomatchning hanteras antingen genom fristående modeller tränade att utföra de två uppgifterna oberoende av varandra eller genom en gemensam end-to-end arkitektur. Såsom föreslagits hittills är båda lösningarna däremot ineffektiva eftersom det krävs två framåtpasseringar i det tidigare fallet och på grund av komplexiteten hos det sammanslagna nätverket i det senare, även om gemensam träning av båda uppgifterna vanligtvis är fördelaktigt när det gäller noggrannhet. I den här artikeln föreslår vi en kompakt och beräkningslätt arkitektur för gemensam semantisk stereomatchning i realtid. Vårt ramverk bygger på att uppskatta scenmodellen i flera steg från grovt till noggrant, vilket tillåter: i) mycket snabb inferens även på inbyggda enheter, med minimal minskning i noggrannhet jämfört med moderna nätverk, ii) övervägning mellan hastighet och noggrannhet enligt de specifika tillämpningskraven. Experimentella resultat på högpresterande grafikkort samt på en inbyggd Jetson TX2 bekräftar överlägsenheten med semantisk stereomatchning jämfört med fristående nätverk och belyser mångsidigheten i vårt ramverk för all hårdvara och för alla tillämpningsområden. Innehållet i denna uppsats finns även beskrivet i [1], ICRA 2020.
22
Wen, Bo. « Color Constancy for Stereo Imaging ». University of Dayton / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1343743270.
Texte intégral
23
Barthel, Roland. « Flußvermessung mit einem Stereo-Kamerasystem ». [S.l.] : Universität Stuttgart , Fakultät Informatik, 1998. http://www.bsz-bw.de/cgi-bin/xvms.cgi?SWB6783608.
Texte intégral
24
Dehlin, Carl. « Visual Tracking Using Stereo Images ». Thesis, Linköpings universitet, Datorseende, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-153776.
Texte intégralRésumé :
Visual tracking concerns the problem of following an arbitrary object in a video sequence. In this thesis, we examine how to use stereo images to extend existing visual tracking algorithms, which methods exists to obtain information from stereo images, and how the results change as the parameters to each tracker vary. For this purpose, four abstract approaches are identified, with five distinct implementations. Each tracker implementation is an extension of a baseline algorithm, MOSSE. The free parameters of each model are optimized with respect to two different evaluation strategies called nor- and wir-tests, and four different objective functions, which are then fixed when comparing the models against each other. The results are created on single target tracks extracted from the KITTI tracking dataset, and the optimization results show that none of the objective functions are sensitive to the exposed parameters under the joint selection of model and dataset. The evaluation results also shows that none of the extensions improve the results of the baseline tracker.
25
De, Franchis Carlo. « Earth Observation and Stereo Vision ». Thesis, Université Paris-Saclay (ComUE), 2015. http://www.theses.fr/2015SACLN002/document.
Texte intégralRésumé :
Cette thèse étudie les problèmes posés par l’estimation automatique de modèles numériques d’élévation de la surface terrestre à partir de photographies prises par des satellites. Ce travail a bénéficié d’une collaboration avec le CNES (Centre National d’Etudes Spatiales) sur le développement d’outils de vision stéréoscopique pour Pléiades, le premier satellite d’observation de la Terre capable de produire des paires ou triplets d’images quasi-simultanées. Le premier chapitre de la thèse décrit un modèle simplifié de caméra pushbroom destiné aux satellites d’observation de la Terre, et aborde le problème de la correction des données de calibration en faisant intervenir des mesures externes. Ce chapitre propose un nouvel algorithme pour affiner les paramètres d’orientation du satellite à partir d’un jeu de points de contrôle. Il est utilisable pour tous les satellites munis de caméras pushbroom. Dans le but d’appliquer aux images satellitaires les nombreux algorithmes de mise en correspondance stéréoscopique développés en traitement d’images et en vision par ordinateur, le deuxième chapitre explore l’adaptation de la théorie de la rectification épipolaire aux images prises par des caméras pushbroom. La rectification épipolaire est utilisée habituellement pour réduire la complexité du problème de mise en correspondance stéréoscopique, et permet d’appliquer les algorithmes les plus récents à des images satellitaires. Le chapitre suivant étudie les effets des erreurs de calibration géométrique sur la rectification et propose une méthode pour éliminer leur impact sur la mise en correspondance. Le quatrième chapitre décrit et analyse en détails une implémentation de l’algorithme Semi-Global Matching (SGM), classé actuellement parmi les meilleurs algorithmes de mise en correspondance stéréoscopique. En se fondant sur une réinterprétation récente de SGM, ce chapitre en propose une variante qui permet de réduire d’un facteur cinq son écart en énergie par rapport aux algorithmes de référence pour la minimisation de champs aléatoires de Markov. En assemblant les blocs algorithmiques décrits dans les chapitres précédents, le cinquième chapitre décrit S2P, une chaîne stéréoscopique complète qui produit des modèles numériques d’élévation à partir d’images satellitaires. Un modèle d’évolution de paysage est présenté dans le sixième chapitre comme exemple d’application. Le modèle est utilisé pour simuler numériquement la structure fine du réseau hydrographique sur des modèles numériques d’élévation obtenus à partir d’images prises par Pléiades. Le code source de la chaîne S2P2 est distribué en tant que logiciel open source. Afin d’assurer la reproductibilité des résultats obtenus, les algorithmes implémentés dans S2P sont en cours de publication dans le journal IPOL, accompagnés de descriptions et d’analyses détaillées, de codes sources documentés et de démonstrateurs en ligneThis thesis deals with the problem of computing accurate digital elevationmodels of the Earth's surface from optical images taken by pushbroomobservation satellites. It takes advantage of the collaboration of thedefendant with CNES (the French Space Agency) on the development ofstereo vision tools for Pléiades, the first Earth observation satelliteproducing quasi simultaneous stereo pairs or triplets with small baseline.The first chapter describes a simple pushbroom camera model for observationsatellites orbiting around the Earth and addresses the correction of theacquisition geometry by involving extrinsic information. This chapter proposesa new algorithm to refine the orientation parameters from a set of groundcontrol points, applicable to all pushbroom satellites.With the goal of testing for satellite imaging the thriving exploration ofstereo matching by the computer vision community, the second chapter exploresthe adaptation of the theory of epipolar resampling to pushbroom images.Epipolar resampling is traditionally used in stereo to reduce the matchingcomputational cost, and permits to test for satellite imaging the mostcompetitive computer vision algorithms. The third chapter discusses the effectsof geometric calibration inaccuracies and proposes a method to cancel itsimpact on stereo matching.The fourth chapter analyzes and describes a detailed implementation of theSemi-Global Matching (SGM) algorithm, which is currently among the top-rankedstereo vision algorithms. Based on a recently proposed interpretation of SGM asa min-sum Belief Propagation algorithm, a variant is proposed that allows toreduce by a factor five the energy gap of SGM with respect to referencealgorithms for Markov Random Fields with truncated smoothness terms.By wrapping together the algorithmic blocks described in the previous chapters,the fifth chapter describes S2P, a complete stereo pipeline for producingdigital elevation models from satellite images. As an application, a landscapeevolution model is presented in the sixth chapter. The model is used tosimulate numerically the fine structure of the river networks on digitalelevation models obtained from Pléiades Earth observation images.The source code of the S2P stereo pipeline is distributed as open source. Toensure reproducibility, the algorithms implemented in each step of the S2Ppipeline are submitted to the IPOL journal, with detailed descriptions of thealgorithms, documented source codes and online demonstrations for each block ofthe pipeline
26
Karásek, Miroslav. « Zpracování a vizualizace stereo snímků ». Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2012. http://www.nusl.cz/ntk/nusl-219673.
Texte intégralRésumé :
This thesis deals with the processing of stereo images. It described the principles of calibration and rectification of stereo images. The thesis described several methods for finding important points. SURF method is then implemented for practical solution. Finding correspondences is realized using the methods of image processing library OpenCV. Reconstructed spatial coordinates of points and write by the format specified VRML97. Finally, there is introduced evaluated accuracy of spatial data acquisition and comparison of computational cost generated programs.
27
Campisi, Andrea. « Development of a photometric stereo system ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018.
Trouver le texte intégralRésumé :
Photometric stereo is a method of estimating surface geometry by using a fixed-position camera and multiple light sources. The idea of photometric stereo is to vary the direction of incident illumination between successive images, while the viewing direction is constant; in this way, the correspondence of image points is known beforehand, as the position of the object is not changed, and surface orientation is determined by using the radiance values recorded with the different images. Photometric stereo has several applications: it is used to detect small surface defects, imperceptible to the human eye; it has also medical applications, i.e. to detect skin lesions and help in the diagnosis of melanoma. More recently, it has been used also to perform a non-invasive 3D scan of surfaces, and as a cheap method to get a real-time facial motion capture, widely used in computer graphics applications.
The goals of this thesis are to describe the main algorithms used to achieve a photometric stereo analysis of surfaces, and the realization of a hardware device capable of acquire the images.
28
Dikmen, Mehmet. « 3d Face Reconstruction Using Stereo Vision ». Master's thesis, METU, 2006. http://etd.lib.metu.edu.tr/upload/12607543/index.pdf.
Texte intégralRésumé :
3D face modeling is currently a popular area in Computer Graphics and Computer Vision. Many techniques have been introduced for this purpose, such as using one or more cameras, 3D scanners, and many other systems of sophisticated hardware with related software. But the main goal is to find a good balance between visual reality and the cost of the system. In this thesis, reconstruction of a 3D human face from a pair of stereo cameras is studied. Unlike many other systems, facial feature points are obtained automatically from two photographs with the help of a dot pattern projected on the object’
s face. It is seen that using projection pattern also provided enough feature points to derive 3D face roughly. These points are then used to fit a generic face mesh for a more realistic model. To cover this 3D model, a single texture image is generated from the initial stereo photographs.
29
Buyukatalay, Soner. « Photometric Stereo Considering Highlights And Shadows ». Phd thesis, METU, 2011. http://etd.lib.metu.edu.tr/upload/12613749/index.pdf.
Texte intégralRésumé :
Three dimensional (3D) shape reconstruction that aims to reconstruct 3D surface of objects
using acquired images, is one of the main problems in computer vision. There are many
applications of 3D shape reconstruction, from satellite imaging to material sciences, considering
a continent on earth or microscopic surface properties of a material. One of these
applications is the automated firearm identification that is an old, yet an unsolved problem in
forensic science. Firearm evidence matching algorithms rely on the fact that a firearm creates
characteristic marks on surfaces of the bullets and the cartridge cases. These marks should
be digitized unaffected from different surface material properties of evidences. Accuracy of
3D shape is one of the most important parameters affecting the overall identification performance.
A very high resolution, accurate 3D data have to be reconstructed in the order of
minutes. Photometric stereo (PS) method is capable of reconstructing high resolution surfaces
in a fast manner. But, the metallic material and the surface topology of the firearm evidences
generate highlights and shadows on their images that does not comply with the assumptions
of conventional PS. In the scope of this work, it is intended to design an accurate, fast and
robust 3D shape reconstruction scheme using PS considering highlights and shadows. These
new PS procedures to be developed here should not be limited only to the ballistic evidences
but they also could be used for a wider range of objects reflection properties and texture. For
this purpose, masked PS methods which are quite fast when compared to other approaches,
were classified and implemented. Simple additional masking methods are also proposed. A
novel weighted PS method, using weighted least square estimation, is presented to eliminate
false edges created by the masks. Concurrently, the calibration processes and the illumination
configuration were improved. The disturbances due to close light sources were removed
by image calibrations. From experimental tests to simulate the light positioning problem, it
is concluded that the double zenith illumination configuration have better performance than
the optimal single zenith illumination configuration, when the highlights and the shadows are
considered. Double zenith illumination configuration results were further improved by the
weighted normal PS with a small additional computation cost. All the implemented methods
were tested firstly on the controlled environment using synthetic images. Later the same tests
were conducted on real objects with varying characteristics as well as the firearm evidences.
30
Bugdayci, Done. « Stereo Video Broadcasting Over Dvb-h ». Master's thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12614024/index.pdf.
Texte intégralRésumé :
This thesis proposes a complete framework of an end-to-end transmission of stereo video
to mobile devices using DVB-H. Block diagram of the system is presented and operations
conducted on the video at each layer are explained. Parameters and methodologies that may
make a robust transmission possible are discussed. The transmission performance is analyzed
in terms of error robustness under various coding methods, prediction structures, layering
and protection strategies for different contents and channel conditions. It also investigates
the effect of rate allocation between video quality and protection over robust transmission
in erroneous environment. This works provides directive conclusions on the selection of the
mentioned parameters and methods.
31
Manuylova, Ekaterina. « Investigations of stereo setup for Kinect ». Thesis, Linköpings universitet, Institutionen för teknik och naturvetenskap, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-75855.
Texte intégralRésumé :
The main purpose of this work is to investigate the behavior of the recently released by Microsoft company the Kinect sensor, which contains the properties that go beyond ordinary cameras. Normally, in order to create a 3D reconstruction of the scene two cameras are required. Whereas, the Kinect device, due to the properties of the Infrared projector and sensor allows to create the same type of the reconstruction using only one device. However, the depth images, which are generated by the Infrared laser projector and monochrome sensor in Kinect can contain undefined values. Therefore, in addition to other investigations this project contains an idea how to improve the quality of the depth images. However, the base aim of this work is to perform a reconstruction of the scene based on the color images using pair of Kinects which will be compared with the results generated by using depth information from one Kinect. In addition, the report contains the information how to check that all the performed calculations were done correctly. All the algorithms which were used in the project as well as the achieved results will be described and discussed in the separate chapters in the current report.
32
Lorentzon, Mattis, et Tobias Andersson. « Road Surface Modeling using Stereo Vision ». Thesis, Linköpings universitet, Reglerteknik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-78455.
Texte intégralRésumé :
Modern day cars are often equipped with a variety of sensors that collect information about the car and its surroundings. The stereo camera is an example of a sensor that in addition to regular images also provides distances to points in its environment. This information can, for example, be used for detecting approaching obstacles and warn the driver if a collision is imminent or even automatically brake the vehicle. Objects that constitute a potential danger are usually located on the road in front of the vehicle which makes the road surface a suitable reference level from which to measure the object's heights. This Master's thesis describes how an estimate of the road surface can be found to in order to make these height measurements. The thesis describes how the large amount of data generated by the stereo camera can be scaled down to a more effective representation in the form of an elevation map. The report discusses a method for relating data from different instances in time using information from the vehicle's motion sensors and shows how this method can be used for temporal filtering of the elevation map. For estimating the road surface two different methods are compared, one that uses a RANSAC-approach to iterate for a good surface model fit and one that uses conditional random fields for modeling the probability of different parts of the elevation map to be part of the road. A way to detect curb lines and how to use them to improve the road surface estimate is shown. Both methods for road classification show good results with a few differences that are discussed towards the end of the report. An example of how the road surface estimate can be used to detect obstacles is also included.
33
Johansson, Fredrik. « Visual Stereo Odometry for Indoor Positioning ». Thesis, Linköpings universitet, Datorseende, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-81215.
Texte intégralRésumé :
In this master thesis a visual odometry system is implemented and explained. Visual odometry is a technique, which could be used on autonomous vehicles to determine its current position and is preferably used indoors when GPS is notworking. The only input to the system are the images from a stereo camera and the output is the current location given in relative position. In the C++ implementation, image features are found and matched between the stereo images and the previous stereo pair, which gives a range of 150-250 verified feature matchings. The image coordinates are triangulated into a 3D-point cloud. The distance between two subsequent point clouds is minimized with respect to rigid transformations, which gives the motion described with six parameters, three for the translation and three for the rotation. Noise in the image coordinates gives reconstruction errors which makes the motion estimation very sensitive. The results from six experiments show that the weakness of the system is the ability to distinguish rotations from translations. However, if the system has additional knowledge of how it is moving, the minimization can be done with only three parameters and the system can estimate its position with less than 5 % error.
34
Chan, Kap Luk. « Optimization of multiple view stereo vision ». Thesis, Imperial College London, 1991. http://hdl.handle.net/10044/1/46705.
Texte intégral
35
Katz, Itzhak. « Coaxial stereo and scale-based matching ». Thesis, University of British Columbia, 1985. http://hdl.handle.net/2429/24693.
Texte intégralRésumé :
The past decade has seen a growing interest in computer stereo vision: the recovery of the depth map of a scene from two-dimensional images. The main problem of computer stereo is in establishing correspondence between features or regions in two or more images. This is referred to as the correspondence problem. One way to reduce the difficulty of the above problem is to constrain the camera modeling. Conventional stereo systems use two or more cameras, which are positioned in space at a uniform distance from the scene. These systems use epipolar geometry for their camera modeling, in order to curb the search space to be one-dimensional - along epipolar lines. Following Jain's approach, this thesis exploits a non-conventional camera modeling: the cameras are positioned in space one behind the other, such that their optical axes are collinear (hence the name coaxial stereo), and their distance apart is known. This approach complies with a simple case of epipolar geometry which further reduces the magnitude of the correspondence problem. The displacement of the projection of a stationary point occurs along a radial line, and depends only on its spatial depth and the distance between the cameras. Thus, to simplify (significantly) the recovery of depth from disparity, complex logarithmic mapping is applied to the original images. The logarithmic part of the transformation introduces great distortion to the image's resolution. Therefore, to minimize this distortion, it is applied to the features used in the matching process. The search for matching features is conducted along radial lines. Following Mokhtarian and Mackworth's approach, a scale-space image is constructed for each radial line by smoothing its intensity profile with a Gaussian filter, and finding zero-crossings in the second derivative at varying scale levels. Scale-space images of corresponding radial lines are then matched, based on a modified uniform cost algorithm. The matching algorithm is written with generality in mind. As a consequence, it can be easily adopted to other stereoscopic systems. Some new results on the structure of scale-space images of one dimensional functions are presented.Science, Faculty of
Computer Science, Department of
Graduate
36
Chu, Mengdie. « Chroma Keying Based on Stereo Images ». Thesis, Université d'Ottawa / University of Ottawa, 2017. http://hdl.handle.net/10393/35859.
Texte intégralRésumé :
This thesis proposes a novel chroma keying method based on stereo images, which can be applied to post-process the alpha matte generated by any existing matting approach. Given a pair of stereo images, a new matting Laplacian matrix is constructed based on the affinities between matching pixels and their neighbors from two frames. Based on the new matting Laplacian matrix, a new cost function is also formulated to estimate alpha values of the reference image through the propagation between stereo images.
37
Persson, Thom. « Building of a Stereo Camera System ». Thesis, Blekinge Tekniska Högskola, Avdelningen för signalbehandling, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-3579.
Texte intégralRésumé :
This project consists of a prototype of a stereo camera rig where you can mount two DSLR cameras, and a multithreaded software application, written in C++, that can move the cameras, change camera settings and take pictures. The resulting 3D-images can be viewed with a 2-view autostereoscopic display. Camera position is controlled by a step engine which is controlled by a PIC microcontroller. All communication with the PIC and the computer is made over USB. The camera shutters are synchronized so it is possible to take pictures of moving objects at a distance of 2.5 m or more. The results shows that there are several things to do before the prototype can be considered a product ready for the market, most of all the camera callback functionality.Detta projekt består av en stereokamerarigg som kan bestyckas med två DSLR-kameror, samt en applikation indelad i flera trådar (multithreaded) , skriven i C++, som kan förflytta kamerorna på riggen, ändra fotoinställningar och ra bilder. Resultatet blir 3D-bilder som kan ses på en autostereoskopisk skärm. Kamerornas position kontrolleras med en stegmotor, som i sin tur styrs av en PIC-mikrokontroller. Kommunikationen mellan PIC-enheten och datorn sker via USB. Slutarna på kamerorna är synkroniserade så det är möjligt att ta bilder på objekt i rörelse på ett avstånd av 2,5 m eller mer. Resultaten visar att det är flera punkter som måste åtgärdas på prototypen innan den kan anses vara redo för marknaden. Den viktigaste punkten är att kunna få fungerande respons (callback) från kamerorna.
38
Berntsson, Robin. « Photometric stereo for eye tracking imagery ». Thesis, Linköpings universitet, Medie- och Informationsteknik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-139019.
Texte intégralRésumé :
The goal of this work is to examine the possibility of surface reconstruction from the images produced by the Tobii H5 eye tracker. It starts of by examining classic photometric stereo and its limitations under the illuminator configuration of the eye tracker. It then proceeds to investigate two alternative solutions: photometric stereo under the assumption that the albedo is known and a method that uses the images from the eye tracker as a guide to mold a reference model into the users face. In the second method the pose of the reference model is estimated by minimizing a photometric error under the assumption that the face is Lambertian, using particle swarm optimization. The position of the generic 3D model is then used in an attempt to mold its shape into the face of the user using shape-from-shading.
39
Tan, Feng. « Stereo image matching and auto-DEM ». Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape17/PQDD_0014/MQ35024.pdf.
Texte intégral
40
Sahabi, Hossein. « Depth estimation error in stereo imaging ». Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape4/PQDD_0010/NQ59665.pdf.
Texte intégral
41
Ezzati, Majid. « Fast image segmentation using stereo vision ». Thesis, McGill University, 1995. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=23258.
Texte intégralRésumé :
Binocular stereopsis is a biologically motivated approach that uses two slightly different views of a scene to extract information about its three-dimensional properties. The two underlying principles of our approach to stereo vision are local computation of binocular disparities and the use of the resulting disparity map for image segmentation.The cepstrum is used to provide an estimation of binocular disparity between corresponding regions of the stereo image pair. We study the cepstrum and its properties, and suggest improvements to the initial disparity estimation stage. Next a modified median filtering scheme is employed for the refinement of the initial disparities using neighbourhood information. The overall disparity map is used for image segmentation based on distance.
Local estimation of initial disparities provides two fundamental advantages for real-time systems: the possibility of increased computational efficiency through parallel implementation and a fixed running time that is independent of image properties. Furthermore, using stereopsis for figure-ground segmentation rather than surface reconstruction eliminates the need for camera calibration which is essential for methods based on exact depth calculation. Therefore, the approach is well-suited to active vision systems in which the cameras are in constant motion.
We provide evidence for the plausibility of the disparity estimation algorithm and the properties of the overall disparity map in the context of biological stereopsis. The algorithm is implemented on a network of TMS320C40 processors to obtain a processing time of one second for a 128-pixel $ times$ 128-pixel image frame.
42
Uribe, Maria Patricia Trujillo. « A computational framework for stereo imaging ». Thesis, Queen Mary, University of London, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.534222.
Texte intégral
43
Yang, Qingxiong. « 3D RECONSTRUCTION FROM STEREO/RANGE IMAGES ». UKnowledge, 2007. http://uknowledge.uky.edu/gradschool_theses/437.
Texte intégralRésumé :
3D reconstruction from stereo/range image is one of the most fundamental and extensively researched topics in computer vision. Stereo research has recently experienced somewhat of a new era, as a result of publically available performance testing such as the Middlebury data set, which has allowed researchers to compare their algorithms against all the state-of-the-art algorithms. This thesis investigates into the general stereo problems in both the two-view stereo and multi-view stereo scopes. In the two-view stereo scope, we formulate an algorithm for the stereo matching problem with careful handling of disparity, discontinuity and occlusion. The algorithm works with a global matching stereo model based on an energy minimization framework. The experimental results are evaluated on the Middlebury data set, showing that our algorithm is the top performer. A GPU approach of the Hierarchical BP algorithm is then proposed, which provides similar stereo quality to CPU Hierarchical BP while running at real-time speed. A fast-converging BP is also proposed to solve the slow convergence problem of general BP algorithms. Besides two-view stereo, ecient multi-view stereo for large scale urban reconstruction is carefully studied in this thesis. A novel approach for computing depth maps given urban imagery where often large parts of surfaces are weakly textured is presented. Finally, a new post-processing step to enhance the range images in both the both the spatial resolution and depth precision is proposed.
44
Alkhalil, Fadi. « Stereo visual servoing from straight lines ». Phd thesis, Université de Strasbourg, 2012. http://tel.archives-ouvertes.fr/tel-00750946.
Texte intégralRésumé :
Closing the control loop of a manipulator robot with vision feedback is widelyknown. It concerns nowadays all areas of robotics. Such a return can make a comparison between a desired state and current state, using visual measurements. The main objective of this doctoral thesis is to design several types of kinematic control laws for stereo visual servoing. It strongly involves the formalism of the task function which is a well-known and useful mathematical tool to express the visual error as a function of state vectors.We have investigated the decoupling between the rotational and translational velocities control laws together with the epipolar constraint with a stereo visual feedback.That is why, the visual measurements and features used in this thesis are the 3Dstraight lines.The interests of this type of visual features rely on the robustness against the noise, and the possibility to represent straight lines or other features like points or planes pairs by the Plücker coordinates, as a 3D straight line can be represented as well by two points or the intersection of two planes. This makes all the control laws designed in this thesis valid for another visual features like points
45
Samani, Anjali Bharatkumar. « Automatic face recognition using stereo images ». Thesis, University of Sheffield, 2006. http://etheses.whiterose.ac.uk/3592/.
Texte intégralRésumé :
Face recognition is an important pattern recognition problem, in the study of both natural and artificial learning problems. Compaxed to other biometrics, it is non-intrusive, non- invasive and requires no paxticipation from the subjects. As a result, it has many applications varying from human-computer-interaction to access control and law-enforcement to crowd surveillance. In typical optical image based face recognition systems, the systematic vaxiability arising from representing the three-dimensional (3D) shape of a face by a two-dimensional (21)) illumination intensity matrix is treated as random vaxiability. Multiple examples of the face displaying vaxying pose and expressions axe captured in different imaging conditions. The imaging environment, pose and expressions are strictly controlled and the images undergo rigorous normalisation and pre-processing. This may be implemented in a paxtially or a fully automated system. Although these systems report high classification accuracies (>90%), they lack versatility and tend to fail when deployed outside laboratory conditions. Recently, more sophisticated 3D face recognition systems haxnessing the depth information have emerged. These systems usually employ specialist equipment such as laser scanners and structured light projectors. Although more accurate than 2D optical image based recognition, these systems are equally difficult to implement in a non-co-operative environment. Existing face recognition systems, both 2D and 3D, detract from the main advantages of face recognition and fail to fully exploit its non-intrusive capacity. This is either because they rely too much on subject co-operation, which is not always available, or because they cannot cope with noisy data. The main objective of this work was to investigate the role of depth information in face recognition in a noisy environment. A stereo-based system, inspired by the human binocular vision, was devised using a pair of manually calibrated digital off-the-shelf cameras in a stereo setup to compute depth information. Depth values extracted from 2D intensity images using stereoscopy are extremely noisy, and as a result this approach for face recognition is rare. This was cofirmed by the results of our experimental work. Noise in the set of correspondences, camera calibration and triangulation led to inaccurate depth reconstruction, which in turn led to poor classifier accuracy for both 3D surface matching and 211) 2 depth maps. Recognition experiments axe performed on the Sheffield Dataset, consisting 692 images of 22 individuals with varying pose, illumination and expressions.
46
MacVicar, Donald William. « Real-time stereo vision using FPGAs ». Thesis, University of Glasgow, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.402760.
Texte intégral
47
Meira, Guilherme Tebaldi. « Stereo Vision-based Autonomous Vehicle Navigation ». Digital WPI, 2016. https://digitalcommons.wpi.edu/etd-theses/344.
Texte intégralRésumé :
Research efforts on the development of autonomous vehicles date back to the 1920s and recent announcements indicate that those cars are close to becoming commercially available. However, the most successful prototypes that are currently being demonstrated rely on an expensive set of sensors. This study investigates the use of an affordable vision system as a planner for the Robocart, an autonomous golf cart prototype developed by the Wireless Innovation Laboratory at WPI. The proposed approach relies on a stereo vision system composed of a pair of Raspberry Pi computers, each one equipped with a Camera Module. They are connected to a server and their clocks are synchronized using the Precision Time Protocol (PTP). The server uses timestamps to obtain a pair of simultaneously captured images. Images are processed to generate a disparity map using stereo matching and points in this map are reprojected to the 3D world as a point cloud. Then, an occupancy grid is built and used as input for an A* graph search that finds a collision-free path for the robot. Due to the non-holonomic constraints of a car-like robot, a Pure Pursuit algorithm is used as the control method to guide the robot along the computed path. The cameras are also used by a Visual Odometry algorithm that tracks points on a sequence of images to estimate the position and orientation of the vehicle. The algorithms were implemented using the C++ language and the open source library OpenCV. Tests in a controlled environment show promising results and the interfaces between the server and the Robocart have been defined, so that the proposed method can be used on the golf cart as soon as the mechanical systems are fully functional.
48
Hollinghurst, Nicholas John. « Uncalibrated stereo and hand-eye coordination ». Thesis, University of Cambridge, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.627151.
Texte intégral
49
Haeling, Jonas [Verfasser]. « Immersive Automotive Stereo Vision / Jonas Haeling ». Tübingen : Universitätsbibliothek Tübingen, 2021. http://d-nb.info/1229916261/34.
Texte intégral
50
Hansen, Mark F. « 3D face recognition using photometric stereo ». Thesis, University of the West of England, Bristol, 2012. http://eprints.uwe.ac.uk/16754/.
Texte intégralRésumé :
Automatic face recognition has been an active research area for the last four decades. This thesis explores innovative bio-inspired concepts aimed at improved face recognition using surface normals. New directions in salient data representation are explored using data captured via a photometric stereo method from the University of the West of England’s “Photoface” device. Accuracy assessments demonstrate the advantage of the capture format and the synergy offered by near infrared light sources in achieving more accurate results than under conventional visible light. Two 3D face databases have been created as part of the thesis – the publicly available Photoface database which contains 3187 images of 453 subjects and the 3DE-VISIR dataset which contains 363 images of 115 people with different expressions captured simultaneously under near infrared and visible light. The Photoface database is believed to be the ?rst to capture naturalistic 3D face models. Subsets of these databases are then used to show the results of experiments inspired by the human visual system. Experimental results show that optimal recognition rates are achieved using surprisingly low resolution of only 10x10 pixels on surface normal data, which corresponds to the spatial frequency range of optimal human performance. Motivated by the observed increase in recognition speed and accuracy that occurs in humans when faces are caricatured, novel interpretations of caricaturing using outlying data and pixel locations with high variance show that performance remains disproportionately high when up to 90% of the data has been discarded. These direct methods of dimensionality reduction have useful implications for the storage and processing requirements for commercial face recognition systems. The novel variance approach is extended to recognise positive expressions with 90% accuracy which has useful implications for human-computer interaction as well as ensuring that a subject has the correct expression prior to recognition. Furthermore, the subject recognition rate is improved by removing those pixels which encode expression. Finally, preliminary work into feature detection on surface normals by extending Haar-like features is presented which is also shown to be useful for correcting the pose of the head as part of a fully operational device. The system operates with an accuracy of 98.65% at a false acceptance rate of only 0.01 on front facing heads with neutral expressions. The work has shown how new avenues of enquiry inspired by our observation of the human visual system can offer useful advantages towards achieving more robust autonomous computer-based facial recognition.