Зміст
Добірка наукової літератури з теми "Vision stéréo"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Vision stéréo".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Vision stéréo"
"Microscope stéréo, vision en ligne et coordination main/œil." Revue Francophone des Laboratoires 2006, no. 387 (December 2006): 94. http://dx.doi.org/10.1016/s1773-035x(06)80507-1.
Повний текст джерелаДисертації з теми "Vision stéréo"
Zhao, Jian. "Extraction d'information tri-dimensionnelle par stéréo vision." Toulouse 3, 1989. http://www.theses.fr/1989TOU30207.
Повний текст джерелаGyory, Georges. "Détection d'obstacles pour conduite assistée par vision stéréo." Paris 11, 2003. http://www.theses.fr/2003PA112107.
Повний текст джерелаFor a multisensor car with data fusion the stereo vision must deliver independent data from the other sensors. We tested two groups of methods to do that, one predicting the dense disparity maps to save CPU time and the other eliminating road surface points and looking for obstacles in the contour points left. To predict the disparity maps we need the position of the expansion center and the expansion coefficient, the latter depending on speed. We tested uniform and depth-dependent expansion, depth being estimated from the disparity values. Parameter estimations were made comparing several estimated disparity maps' values. The prediction methods can extend the considered disparity values' range without loss of image size and can follow correct matches over time. On the other hand, they don't follow the objects' own movement and in lack of everywhere dense contrast points in road situations the estimations cannot be corrected. Road surface elimination needs matching several road surface points. Supposing some are on an arc of circle more or less tangent to the car, we apply a Hough transform to find them. On planar road the matching parameters vary dependently with the car's pitch movement and we exploit that to use just one road point matched. On the contour points left we look for quasi-vertical scending sequences with quasi-constant disparity values close to that of the road surface at the beginning of the sequence. This gives a very fast algorithm yielding positions and confidence values (length of the ascending sequence) of obstacle contours
Laïeb, Noureddine. "Contribution à la vision par ordinateur : une méthode de stéréo vision passive." Le Havre, 1987. http://www.theses.fr/1987LEHA0005.
Повний текст джерелаZhu, Ying. "Etude psychophysique de la vision en relief humaine en télévision stéréo." Lyon, INSA, 1992. http://www.theses.fr/1992ISAL0106.
Повний текст джерелаThis thesis is concerned with the stud of certain hurnan stereo vision cues. Particularly relevant ta depth perception in a dynamic 3d (three-dimensional) stereoscopic TV and with t he understanding of human stereoscopic visual processes using local spectral models. We have studied different types of stereo acuity all the retinal meridian in both central and eccentric eye positions, in physiological and pathological subjects. Accomdation and convergence, the two essentiel depth perception cues in 3D Tvs, have benn investigated in detail, allowing ta get insight into the way the human visual system behaves in arder to resolve the conflict between accommodation and convergence. The quality problem of depth perception in the presence of geometrical distortions was also addressed. Within this framework. Two types of geornetrical distortions have been distinguished, and their affect the visual comfort and binocular disparity sensitivity bas been detailed in various situations. Finally, in arder ta get an insight into the stereo informatian processing and coding processes, we have studied the influence of the monocular images' local spectral content on human stereo vision by employing a 2D (two-dimensional) space/spatial-frequency model based on using the 2D Wigner-Vill distribution, and the 2D discrets cosine transformation
Bak, Adrien. "Coopération stéréo mouvement pour la détection des objets dynamiques." Phd thesis, Université Paris Sud - Paris XI, 2011. http://tel.archives-ouvertes.fr/tel-00673364.
Повний текст джерелаSIMOND, Nicolas. "Localisation robuste d'un véhicule en environnement urbain à partir d'un système de stéréo-vision." Phd thesis, Université de Nice Sophia-Antipolis, 2005. http://tel.archives-ouvertes.fr/tel-00009694.
Повний текст джерелаUne modélisation polyhédrique des rues qui forment l'environnement urbain de cette étude permet de segmenter trois plans principaux : la route et les façades verticales des bâtiments qui délimitent l'espace de navigation. La segmentation du plan de la route est facilitée par la matérialisation des voies de navigation et autres trottoirs ou terre-pleins, parallèles entre eux au premier plan, qui sont à l'origine dans les images de contours qui convergent vers un point de fuite dominant.
Les conditions d'illumination et la présence d'obstacles dynamiques qui obstruent le champ de vision compliquent la tâche de suivi des plans segmentés. L'emploi d'une paire stéréo permet à chaque nouvelle pose de déterminer quelles sont les régions des images qui correspondent aux plans segmentés en calculant l'homographie induite par chaque plan entre les deux images de la paire. Le déplacement du véhicule étant supposé plan, ses mouvements d'inclinaison et de lacet influent peu sur chacune des homographies estimées entre les images de la paire stéréo. Nous possédons ainsi un outil fiable de segmentation des plans principaux qui forment l'environnement.
L'estimation du déplacement entre deux poses de chaque caméra consiste à estimer l'homographie induite par le mouvement relatif du plan considéré. Le calcul est entrepris grâce à la mise en correspondance des primitives (points, droites) détectées dans les régions planaires segmentées. La précision et la fiabilité des résultats dépendent essentiellement de la répartition spatiale des primitives mises en correspondance.
L'introduction de la notion de super-homographie permet de robustifier les estimations des homographies en calculant de manière simultanée toutes les homographies induites par un même plan, observé dans plusieurs images. La redondance des contraintes imposées par le mouvement relatif des primitives coplanaires mises en correspondance améliore l'estimation du mouvement de la projection du plan dans les différentes images. L'apport de la super-homographie est double : elle permet de détecter d'éventuelles erreurs de mise en correspondance et fournit une estimée des coordonnées des primitives coplanaires avec une précision sub-pixellique. Lorsque la calibration de la paire stéréo est connue, la trajectographie du véhicule peut être estimée en décomposant l'homographie relative au mouvement d'une des caméras, extraite de la super-homographie.
Simond, Nicolas. "Localisation robuste d'un véhicule en environnement urbain à l'aide d'un système de stéréo-vision." Nice, 2005. http://www.theses.fr/2005NICE4018.
Повний текст джерелаThe thesis deals with mobile robots in the specific context of urban environment. We want to extract the maximum of data on the motion of an uncalibrated stereo-rig embedded in a vehicle with in a structured environment. The aim of this study is to estimate the motion of a vehicle when the localization is impossible with a satellite position system due to the occlusion of the free space. A polyhedrical model of the streets, which is the considered environment in this study, allows the segmentation of three main plane : the road and the vertical facades which represent the frontier of the navigation area. We assume that the while lanes which split the different ways and the kerbs which delimit the road are all parallel in the scene, at least on the foreground. Therefore the detection of these induced edges in image is easy because they all converge in a dominant vanishing point. The lighting conditions and the dynamical obstacles which occlude the vision field make the tracking task of the segmented planes difficult. The use of a stereo-vision allows the segmentation in image of the coplanar area of the scene assuming that each plane induces a homography between both images of the stereo-rig. The vehicle motion is assumed to be plane, the pan and tilt rotation motions have low contributions on the computed homographies. We hence possess a reliable tool to segment the main planes which structure the environment. The motion of the cameras between two poses is obtained with the homography induced by the relative motion of one plane. The homography computation requires the matching of features (lines, points) detected in the coplanar regions of images. The precision and the reliability of the result highly depends on the spatial distribution of the matched features. The introduction of the motion of super-homography improves the robustness of the homography computation by computing in one shot all the homographies induced by the same plane in several images. The redundancy of the constraints imposed by the relative motion of the matched coplanar features increases the constraints of the plane projection in each image. The super-homography has two advantages : it allows the detection of mismatched features and supplies coordinates with a sub-pixellic precision. When the calibration of the stereo-rig is available, the extraction of the homography induced by the relative motion of a camera from the super-homography supplies the trajectography of the vehicle
Lefaudeux, Benjamin. "Détection, localisation et suivi des obstacles et objets mobiles à partir d'une plate forme de stéréo-vision." Thesis, Paris, ENMP, 2013. http://www.theses.fr/2013ENMP0091/document.
Повний текст джерелаThis PhD work is to be seen within the context of autonomous vehicle perception, in which the detection and localisation of elements of the surroundings in real time is an obvious requirement. Subsequent perception needs are manyfold, from localisation to obstacle detection, and are the subject of a continued research interest. The goal of this work is to build, in real time and from stereovision acquisition, a 3D map of the surroundings ; while detecting and tracking moving objects.Interest point selection and tracking on picture space are a first step, which we initiate by a thorough comparison of detectors from the literature. As regards tracking, we propose a massively parallel implementation of the standard KLT algorithm, using redundant tracking to provide reliable quality estimation. This allows us to track thousands of points in real-time, which compares favourably to the state of the art.Next step is the ego-motion estimation, along with the positioning of tracked points in 3D space. We first propose an iterative variant of the well known “SVD” process followed by UKF filtering, which allows for a very fast and reliable estimation. Then the position of every followed interest point is filtered on the fly over time, in contrast to most dense approaches from the literature.We finally propose a segmentation of moving objects in the augmented position-speed space, which is made possible by our continuous estimation of feature points position. Target tracking and filtering finally use a GM-PHD approach
Petitpas, Benoit. "Extraction de paramètres bio-geo-physiques de surfaces 3D reconstruites par multi-stéréo-restitution d'images prises sans contraintes." Phd thesis, Université Paris-Est, 2011. http://tel.archives-ouvertes.fr/tel-00693326.
Повний текст джерелаAmur, Khua Bux. "Contrôle adaptatif, techniques de régularisation et applications en analyse d'images." Thesis, Metz, 2011. http://www.theses.fr/2011METZ011S/document.
Повний текст джерелаAn adaptive control and regularization techniques are studied for some linear and nonlinear ill-posed problems in image processing and computer vision. These methods are based on variational approach which constitutes the minimization of a suitable energy functional made up of two parts data term obtained from constancy of grey value assumption and regularization term which cope with ill-posed problem by its filling in effect property. We have provided a novel adaptive approach for optic flow and stero vision problems. Which is based on adaptive finite element method using unstructutred grid as the domain of computation, which allow the automatic choice of local optimal regularization parameters. Various linear and nonlinear variational models have been considered in this thesis for scientific computations of optic flow and stereo vision problems and an efficient adaptive control is obtained. This novel regularization strategy is controlled by the regularization parameter [alpha] which depends on space and a posteriori error estimator called residual error indicator. This local adptive behavior has encouraged us to experiment with other problems in image analysis such as denoising, we add a preliminary chapter on hte model of Perona-Malik. This work falls in to the category novel and advanced numerical strategies for scientific computations specifically for image motion problems