Rozprawy doktorskie na temat „Suivi d'image”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych rozpraw doktorskich naukowych na temat „Suivi d'image”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj rozprawy doktorskie z różnych dziedzin i twórz odpowiednie bibliografie.
Ben, Himane Mohamed Selim. "Vers une approche unifiée pour le suivi temps réel et l'asservissement visuel". Paris, ENMP, 2006. http://www.theses.fr/2006ENMP1393.
Pełny tekst źródłaNowadays, in addition to the classical domain of the robotic manipulation, vision-based control offers a large spectrum of applications in various contexts using computer vision and control theory. One possibility to develop vision-based control algorithms is to integrate methods and approaches developed in a separately by the vision and the control communities. Instead of considering vision and control techniques separately, in this thesis, they are integrated in a unified framework. We developed a generic, flexible and robust system that can be used by a wide variety of robotic applications. We made different contributions towards the conception of such complete system. Two major contributions are presented:1- A template-based visual tracking of objects in the image using an Efficient Second-order Minimization technique called the ESM technique. Compared to the existing methods, the proposed algorithm gives better convergence properties (bigger radius and higher rate and frequency of convergence). This approach has been generalized to the direct estimation in the Cartesian space of the relative camera/object motion. 2- A new 2D visual servoing is also introduced. The control law is locally stable and unlike all the existing methods, it does not need any a priori measure of the model of object with respect to which the visual servoing is performed. Only information extracted from the reference and the current images are used to compute the control law
Ieng, Sio-Song. "Méthodes robustes pour la détection et le suivi des marquages". Paris 6, 2004. http://www.theses.fr/2004PA066547.
Pełny tekst źródłaPrimet, Maël. "Méthodes probabiliste pour le suivi de points et l'analyse d'images biologiques". Phd thesis, Université René Descartes - Paris V, 2011. http://tel.archives-ouvertes.fr/tel-00669220.
Pełny tekst źródłaHistace, Aymeric. "Détection et suivi robustes de structures sur des séquences d'images : application à l'IRM cardiaque marquée". Angers, 2004. http://www.theses.fr/2004ANGE0022.
Pełny tekst źródłaThis thesis is dealing with the detection and the follow-up of structures in image sequences. We show that the integration of original external energies in a simple active contours model can lead to precise and reliable data detections. This work is presented through a particular application : the study of tagged cardiac MRI sequences. The study of those sequences can be divided into two parts : a detection and a follow-up of the internal and external boundaries of the Left Ventricle and a detection and a follow-up of the grid of tags. For the achievement of the first step, we propose the integration of a particular external energy which generation is based on a texture analysis of the tagged MRI. For the second, we propose an anisotropic diffusion of the images, which leading equation is based on an informational formalism using the Extreme Physical Information process. All the obtained results has been validated by a medical expert
Ireta, Munoz Fernando Israel. "Estimation de pose globale et suivi pour la localisation RGB-D et cartographie 3D". Thesis, Université Côte d'Azur (ComUE), 2018. http://www.theses.fr/2018AZUR4054/document.
Pełny tekst źródłaThis thesis presents a detailed account of novel techniques for pose estimation by using both, color and depth information from RGB-D sensors. Since pose estimation simultaneously requires an environment map, 3D scene reconstruction will also be considered in this thesis. Localization and mapping has been extensively studied by the robotics and computer vision communities and it is widely employed in mobile robotics and autonomous systems for performing tasks such as tracking, dense 3D mapping and robust localization. The central challenge of pose estimation lies in how to relate sensor measurements to the state of position and orientation. When a variety of sensors, which provide different information about the same data points, are available, the challenge then becomes part of how to best fuse acquired information at different times. In order to develop an effective algorithm to deal with these problems, a novel registration method named Point-to-hyperplane Iterative Closest Point will be introduced, analysed, compared and applied to pose estimation and key-frame mapping. The proposed method allows to jointly minimize different metric errors as a single measurement vector with n-dimensions without requiring a scaling factor to tune their importance during the minimization process. Within the Point-to-hyperplane framework two main axes have been investigated. Firstly, the proposed method will be employed for performing visual odometry and 3D mapping. Based on actual experiments, it has been shown that the proposed method allows to accurately estimate the pose locally by increasing the domain of convergence and by speeding up the alignment. The invariance is mathematically proven and results in both, simulated and real environments, are provided. Secondly, a method is proposed for global localization for enabling place recognition and detection. This method involves using the point-to-hyperplane methods within a Branch-and-bound architecture to estimate the pose globally. Therefore, the proposed method has been combined with the Branch-and-bound algorithm to estimate the pose globally. Since Branch-and-bound strategies obtain rough alignments regardless of the initial position between frames, the Point-to-hyperplane can be used for refinement. It will be demonstrated that the bounds are better constrained when more dimensions are considered. This last approach is shown to be useful for solving mistracking problems and for obtaining globally consistent 3D maps. In a last part of the thesis and in order to demonstrate the proposed approaches and their performance, both visual SLAM and 3D mapping results are provided
Fontmarty, Mathias. "Vision et filtrage particulaire pour le suivi tridimensionnel de mouvements humains: applications à la robotique". Phd thesis, Université Paul Sabatier - Toulouse III, 2008. http://tel.archives-ouvertes.fr/tel-00400305.
Pełny tekst źródłaXu, Kele. "Visualisation tridimensionnelle de la langue basée sur des séquences d'image échographique en mode-B". Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066498/document.
Pełny tekst źródłaA silent speech interface (SSI) is a system to enable speech communication with non-audible signal, that employs sensors to capture non-acoustic features for speech recognition and synthesis. Extracting robust articulatory features from such signals, however, remains a challenge. As the tongue is a major component of the vocal tract, and the most important articulator during speech production, a realistic simulation of tongue motion in 3D can provide a direct, effective visual representation of speech production. This representation could in turn be used to improve the performance of speech recognition of an SSI, or serve as a tool for speech production research and the study of articulation disorders. In this thesis, we explore a novel 3D tongue visualization framework, which combines the 2D ultrasound imaging and 3D physics-based modeling technique. Firstly, different approaches are employed to follow the motion of the tongue in the ultrasound image sequences, which can be divided into two main types of methods: speckle tracking and contour tracking. The methods to track speckles include deformation registration, optical-flow, and local invariant features-based method. Moreover, an image-based tracking re-initialization method is proposed to improve the robustness of speckle tracking. Compared to speckle tracking, the extraction of the contour of the tongue surface from ultrasound images exhibits superior performance and robustness. In this thesis, a novel contour-tracking algorithm is presented for ultrasound tongue image sequences, which can follow the motion of tongue contours over long durations with good robustness. To cope with missing segments caused by noise, or by the tongue midsagittal surface being parallel to the direction of ultrasound wave propagation, active contours with a contour-similarity constraint are introduced, which can be used to provide “prior” shape information. Experiments on synthetic data and on real 60 frame per second data from different subjects demonstrate that the proposed method gives good contour tracking for ultrasound image sequences even over durations of minutes, which can be useful in applications such as speech recognition where very long sequences must be analyzed in their entirety…
Lelong, Thibault. "Reconnaissance des documents avec de l'apprentissage profond pour la réalité augmentée". Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAS017.
Pełny tekst źródłaThis doctoral project focuses on issues related to the identification of images and documents in augmented reality applications using markers, particularly when using cameras. The research is set in a technological context where interaction through augmented reality is essential in several domains, including industry, which require reliable identification methodologies.In an initial phase, the project assesses various identification and image processing methodologies using a database specially designed to reflect the challenges of the industrial context. This research allows an in-depth analysis of existing methodologies, thus revealing their potentials and limitations in various application scenarios.Subsequently, the project proposes a document detection system aimed at enhancing existing solutions, optimized for environments such as web browsers. Then, an innovative image research methodology is introduced, relying on an analysis of the image in sub-parts to increase the accuracy of identification and avoid image confusions. This approach allows for more precise and adaptive identification, particularly with respect to variations in the layout of the target image.Finally, in the context of collaborative work with ARGO company, a real-time image tracking engine was developed, optimized for low-power devices and web environments. This ensures the deployment of augmented reality web applications and their operation on a wide range of devices, including those with limited processing capabilities.It is noteworthy that the works resulting from this doctoral project have been concretely applied and valorized by the Argo company for commercial purposes, thereby confirming the relevance and viability of the developed methodologies and solutions, and attesting to their significant contribution to the technological and industrial field of augmented reality
Xu, Kele. "Visualisation tridimensionnelle de la langue basée sur des séquences d'image échographique en mode-B". Electronic Thesis or Diss., Paris 6, 2016. http://www.theses.fr/2016PA066498.
Pełny tekst źródłaA silent speech interface (SSI) is a system to enable speech communication with non-audible signal, that employs sensors to capture non-acoustic features for speech recognition and synthesis. Extracting robust articulatory features from such signals, however, remains a challenge. As the tongue is a major component of the vocal tract, and the most important articulator during speech production, a realistic simulation of tongue motion in 3D can provide a direct, effective visual representation of speech production. This representation could in turn be used to improve the performance of speech recognition of an SSI, or serve as a tool for speech production research and the study of articulation disorders. In this thesis, we explore a novel 3D tongue visualization framework, which combines the 2D ultrasound imaging and 3D physics-based modeling technique. Firstly, different approaches are employed to follow the motion of the tongue in the ultrasound image sequences, which can be divided into two main types of methods: speckle tracking and contour tracking. The methods to track speckles include deformation registration, optical-flow, and local invariant features-based method. Moreover, an image-based tracking re-initialization method is proposed to improve the robustness of speckle tracking. Compared to speckle tracking, the extraction of the contour of the tongue surface from ultrasound images exhibits superior performance and robustness. In this thesis, a novel contour-tracking algorithm is presented for ultrasound tongue image sequences, which can follow the motion of tongue contours over long durations with good robustness. To cope with missing segments caused by noise, or by the tongue midsagittal surface being parallel to the direction of ultrasound wave propagation, active contours with a contour-similarity constraint are introduced, which can be used to provide “prior” shape information. Experiments on synthetic data and on real 60 frame per second data from different subjects demonstrate that the proposed method gives good contour tracking for ultrasound image sequences even over durations of minutes, which can be useful in applications such as speech recognition where very long sequences must be analyzed in their entirety…
El-Chaar, Wafi. "Segmentation et suivi d'objets couleur dans une séquence vidéo à l'aide de réseaux de neurones auto-organisés". Littoral, 2007. http://www.theses.fr/2007DUNK0204.
Pełny tekst źródłaIn this research, we are interested in automatic segmentation of color objects using artificial neural networks. We apply this segmentation to track moving objects in a video sequence. Our ultimate goal is to build an “intelligent Visual Machine” that is able to “ see” and “understand” what it sees. A wide range of applications could be benefit from such a research : intelligent transportation systems, objects or persons tracking, objects or behavior recognition and many other engineering or biomedical applications. We developed an algorithm that starts with a pre-defined set of neurons uniformly representing the color space. The algorithm then reduces this set by eliminating the ones which had little or no contribution to the colors of the image. A Kohonen’s SOM neural network learns then the distribution of the remaining (useful) colors in the color space and represents them in an optimized way. Next, we use a histogram of market-shares to detect and keep only the most dominant useful colors found in the image. We use those colors to identify and separate color segments. We used the economical ABC-Analysis and Pareto’s 80/20 rule to filter the available segments and concentrate on the most important 95% of them. This represent a huge reduction in the number of objects treated and a much better quality of segmentation. We applied this segmentation algorithm to feed an object tracking algorithm that contained some new rules governing tracking algorithms and validating their results. The most important one was that tracking algorithms should perform the same way if applied in forward or backward playing mode (objects should match both ways). We developed a tracking algorithm based on visual features matching technique and calculated the relative difference of 5 basic visual features to do the match. Those features were color, centroid, area, boundingbox, and orientation and were compared between different objects from consecutive frames. We were able to detect all 3 states of an object : appearance, existence, and disappearance
Orczyk, Clément. "Modélisation du cancer de la prostate par l'imagerie : détection, stratification, planning thérapeutique et suivi en 3D d'une thérapie focale basés sur le recalage-fusion d'image en multi modalité". Thesis, Normandie, 2017. http://www.theses.fr/2017NORMC405/document.
Pełny tekst źródłaConventional prostate MRI, enhanced by diffusion and perfusion sequences, and then named multiparametric, showed high performances for detection of prostate cancer using visual scoring. Indications in stratification, prognosis, treatment planning and follow up are currently under investigations.First part of this work attached itself to describe, elaborate and use a non-rigid image fusion method in 3D between gold standard histology of radical prostatectomy and MRI. Investigations captured the significant differences in shape and volume of in vivo and ex vivo prostate using MRI. The developed multimodality fusion method was applied to a cohort of patients who underwent MRI prior surgery. Results showed a stratified underestimation of cancer volume by MRI. Clinical output resides in detection, stratification and surgical planning.The second part proposed some texture analysis of sequences and quantitative maps. As a multiparametric approach, the Entropy Score is applied in a pilot cohort at time of biopsy and showed some potential usefulness to select MRI targets without compromising detection of significant cancer. By positively correlating with the Gleason Score and the maximal core length of cancer, Entropy Score participates of stratification of cancer.The third part explored application of image registration in the longitudinal follow up of an emergent therapy, said focal (FT). As a conservative approach, FT induces very local deformation of the gland which appears to be appropriately modelled by non-rigid registration, then opening possibilities to guide further control biopsy and radiologic assessment
Dupont, Romain. "Suivi des parties cachées dans une séquence vidéo et autres problèmes soulevés par la reconstruction tridimensionelle d'un environnement urbain". Phd thesis, Ecole des Ponts ParisTech, 2006. http://pastel.archives-ouvertes.fr/pastel-00002357.
Pełny tekst źródłaPapadakis, Nicolas. "Assimilation de données images : application au suivi de courbes et de champs de vecteurs". Phd thesis, Université Rennes 1, 2007. http://tel.archives-ouvertes.fr/tel-00655898.
Pełny tekst źródłaBismuth, Vincent. "Image processing algorithms for the visualization of interventional devices in X-ray fluoroscopy". Thesis, Paris Est, 2012. http://www.theses.fr/2012PEST1062/document.
Pełny tekst źródłaStent implantation is the most common treatment of coronary heart disease, one of the major causes of death worldwide. During a stenting procedure, the clinician inserts interventional devices inside the patient's vasculature. The navigation of the devices inside the patient's anatomy is monitored in real-time, under X-ray fluoroscopy. Three specific interventional devices play a key role in this procedure: the guide-wire, the angioplasty balloon and the stent. The guide-wire appears in the images as a thin curvilinear structure. The angioplasty balloon, that has two characteristic markerballs at its extremities, is mounted on the guide-wire. The stent is a 3D metallic mesh, whose appearance is complex in the fluoroscopic images. Stents are barely visible, but the proper assessment of their deployment is key to the procedure. The objective of the work presented in this thesis is twofold. On the first hand, we aim at designing, studying and validating image processing techniques that improve the visualization of stents. On the second hand, we study the processing of curvilinear structures (like guide-wires) for which we propose a new image processing technique. We present algorithms dedicated to the 2D and 3D visualization of stents. Since the stent is hardly visible, we do not intend to directly locate it by image processing means in the images. The position and motion of the stent are inferred from the location of two landmarks: the angioplasty balloon and of the guide-wire, which have characteristic shapes. To this aim, we perform automated detection, tracking and registration of these landmarks. The cornerstone of our 2D stent visualization enhancement technique is the use of the landmarks to perform motion compensated noise reduction. We evaluated the performance of this technique for 2D stent visualization over a large database of clinical data (nearly 200 cases). The results demonstrate that our method outperforms previous state of the art techniques in terms of image quality. A comprehensive validation confirmed that we reached the level of performance required for the commercial introduction of our algorithm. It is currently deployed in a large number of clinical sites worldwide. The 3D stent visualization that we propose, uses the landmarks to achieve motion compensated tomographic reconstruction. We show preliminary results over 22 clinical cases. Our method seems to outperform previous state of the art techniques both in terms of automation and image quality. The previous stent visualization methods involve the segmentation of the part of the guide-wire extending through the stent. We propose a generic tool to process such curvilinear structures that we call the Polygonal Path Image (PPI). The PPI relies on the concept of locally optimal paths. One of its main advantages is that it unifies the concepts of several previous state of the art techniques in a single formalism. Moreover the PPI enables to control the smoothness and the length of the structures to segment. Its parametrization is simple and intuitive. In order to fully benefit from the PPI, we propose an efficient scheme to compute it. We demonstrate its applicability for the task of automated guide-wire segmentation, for which it outperforms previous state of the art techniques
Braisaz-Latille, Paul. "Suivi et prédiction de l'initiation de l'endommagement et de la durée de vie en fatigue dans un matériau composite tissé présentant un défaut artificiel de fabrication par le biais d'une approche hybride". Mémoire, Université de Sherbrooke, 2015. http://hdl.handle.net/11143/6612.
Pełny tekst źródłaMathon, Julien. "Développement de nouveaux outils algorithmiques et technologiques pour l'étude du mouvement des chromosomes dans la levure S. Cerevisiae". Phd thesis, Université Paul Sabatier - Toulouse III, 2013. http://tel.archives-ouvertes.fr/tel-00949331.
Pełny tekst źródłaKone, Tiémoman. "Recalage automatique d'images angiographiques rétiniennes par analyse numérique d'images : application au suivi de séquences d'images". Paris 12, 1993. http://www.theses.fr/1993PA120046.
Pełny tekst źródłaDahdouh, Sonia. "Filtrage, segmentation et suivi d'images échographiques : applications cliniques". Phd thesis, Université Paris Sud - Paris XI, 2011. http://tel.archives-ouvertes.fr/tel-00647326.
Pełny tekst źródłaMONTAGNE, ERIC. "Suivi d'amers visuels dans une sequence d'images routieres". Clermont-Ferrand 2, 1996. http://www.theses.fr/1996CLF21796.
Pełny tekst źródłaGanoun, Ali. "Suivi de structure déformable dans une séquence d'images". Orléans, 2007. http://www.theses.fr/2007ORLE2003.
Pełny tekst źródłaPINEAU, PATRICK. "Detection et suivi d'objets par analyse de sequences d'images". Rennes 1, 1991. http://www.theses.fr/1991REN10111.
Pełny tekst źródłaArnaud, Elise. "Methodes de filtrage pour du suivi dans des sequences d'images - Application au suivi de points caracteristiques". Phd thesis, Université Rennes 1, 2004. http://tel.archives-ouvertes.fr/tel-00307896.
Pełny tekst źródłaNous proposons d'abord une modelisation originale du probleme. Celle-ci rend les images explicites et permet de construire des algorithmes sans information a priori. Les filtres associes a cette nouvelle representation sont derives sur la base des filtres classiques, en considerant un conditionnement par rapport a la sequence. Il est egalement presente comment ce nouveau schema permet de considerer des modeles simples, pour lesquels la fonction d'importance optimale est disponible.
Ensuite, nous nous interessons a la validation pratique de la modelisation proposee sur une application de suivi de points caracteristiques. Les systemes mis en oeuvre sont entierement estimes sur la sequence. Ils associent des mesures de similarite a une dynamique definie a partir d'un mouvement instantane estime par une methode differentielle robuste. Afin de controler l'importance des differents elements du systeme, les matrices de covariance de bruit des modeles sont estimees. Trois algorithmes de suivi de points sont ainsi construits et valides sur de nombreuses sequences reelles. Enfin, cette approche est etendue au suivi de motifs plans textures. Le modele considere introduit une information geometrique par homographie et amene a un algorithme robuste aux occultations totales.
Arnaud, Elise. "Méthodes de filtrage pour du suivi dans des équences d'images. Application au suivi de points caractéristiques". Rennes 1, 2004. http://www.theses.fr/2004REN10101.
Pełny tekst źródłaMOULET, DOMINIQUE. "Extraction et suivi de contours dans les sequences d'images animees". Nantes, 1990. http://www.theses.fr/1990NANT2016.
Pełny tekst źródłaDelamarre, Quentin. "Suivi du mouvement d'objets articulés dans des séquences d'images vidéo". Nice, 2003. http://www.theses.fr/2003NICE4067.
Pełny tekst źródłaWe introduce you to a method designed to provide the computer, the ability to automatically understand the motions of a markerless filmed human in a multi-cameras environment. In a first step, we decide to estimate the time extended motions variations. Secondly, these variations are interpreted in order to give them significance. After being retrieved from the video pictures, information are compared to a tracked object geometric model. These information could be a segmentation of the object silhouette in case of far distant cameras from each other, or a three-dimensional reconstruction in case of near distant cameras from each other. We ll explain why this distinction is made. In each case, we assume that the object geometry is known thanks to the build of a 3D model made of simple articulated rigid parts. The position parameters error correction is done by creating forces and by resolving the equations of the 3D articulated model dynamic. Information found in the pictures allow us to create such forces. Different steps of the algorithm are introduced: how to calibrate the cameras, the 3D model structure, the information retrieve process, how to apply forces to the model, its dynamic, the estimation and anticipation of the motion in the scene thanks to a Kalman filter. Finally, we expose encouraging results and try to give ideas in order to generalize the algorithm
Inglebert, Claude. "Suivi et reconstruction de courbes a partir d'une séquence d'images : application au suivi de la signalisation routière". Vandoeuvre-les-Nancy, INPL, 1993. http://www.theses.fr/1993INPL016N.
Pełny tekst źródłaAllezard, Nicolas. "Reconnaissance,localisation et suivi d'objets texturés par vision monoculaire". Clermont Ferrand 2, 2001. http://www.theses.fr/2001CLF21314.
Pełny tekst źródłaThis thesis deals with textured objects recognition by monocular vision as well as their localization and tracking in the camera coordinates system. We have developed a mixed approach, based on the matching of visual primitives between the image to analyse and the images of a training base, but which uses the knowledge of the 3D object model to validate the result of the recognition process and to locate the object. In a context of textured objects the most relevant features seems to be keypoints. These points are located in image zones having a high information content. We propose a local description of such features directly based on the luminance signal. It is insensitive to image rotations ans translations and we also present a multi-scale implementation of these description in order to recognize objects in spite of important scale changes. Before the recognition, a training stage is carried out. It consists in the genration of synthetic images of the object then in the creation of a data base gathering the extracted primitives and their characterization vector. After that the data are organize in order to scan the base as fast as possible. The use of synthetics images allows them to compute the 3D coordinates of the keypoints extracted at the training stage. So, after the matching done, we obtain a set of 2D/3D pairs between the image and the object model. Thus, we compute the object position with a robust method which introduce a strong geometrical constraint on the 2D/3D pairs. In the case of a images sequence, once the object position known in the first image, the process can be considerably accelerated : the features extraction is limited to a part of the image and the data base scanning is initialized by the preceding 3D position of the object
Duculty, Florent. "Suivi automatique d'objets 3D basé sur l'apparence dans des séquences d'images". Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2003. http://tel.archives-ouvertes.fr/tel-00610720.
Pełny tekst źródłaBechar, Hassane. "Comparaison d'images : Application à la surveillance et au suivi de trajectoire". Nancy 1, 1987. http://www.theses.fr/1987NAN10062.
Pełny tekst źródłaMeyer, François. "Suivi de regions et analyse des trajectoires dans une sequence d'images". Rennes 1, 1993. http://www.theses.fr/1993REN10070.
Pełny tekst źródłaPrimet, Maël. "Méthodes probabilistes pour le suivi de points et l'analyse d'images biologiques". Paris 5, 2011. http://www.theses.fr/2011PA05S009.
Pełny tekst źródłaThe subject of this thesis is the problem of object tracking, that we approached using statistical methods. The first contribution of this work is the conception of a tracking algorithm of bacterial cells in a sequence of image, to recover their lineage; this work has led to the implementation of a software suite that is currently in use in a research laboratory. The second contribution is a theoretical study of the detection of trajectories in a cloud of points. We define a trajectory detector using the a-contrario statistical framework, which requires essentially no parameter to run. This detector yields remarkable results, and is in particular able to detect trajectories in sequences containing a large number of noise points, while keeping a very low number of false detections. We then study more specifically the correspondence problem between two point clouds, a problem often encountered for the detection of trajectories or the matching of stereographic images. We first introduce a theoretically optimal model for the point correspondence problem that makes it possible to study the performances of several classical algorithms in a variety of conditions. We then formulate a parameterless point correspondence algorithm using the a-contrario framework, that enables us to define a new trajectory tracking algorithm
Llucia, Ludovic. "Suivi d'objets à partir d'images issues de caméras mobiles non calibrées". Thesis, Aix-Marseille 2, 2011. http://www.theses.fr/2011AIX22009/document.
Pełny tekst źródłaThis work refers to a 3D simulator that has for purpose to help football trainers interpreting tactical sequences based on real situations. This simulator has to be able to interpret video movies, to reconstruct a situation. The camera’s calibration state has to be as simple as possible. The first part of this document refers to the solution elaborated to implement this constraint whereas the second one is more oriented on the industrialisation process. These processes imply to focus on vision computing and ergonomics problems and to answer questions such as : how to characterize a homographic transformation matching the image and the model ? How to retrieve the position of the camera? Which area is part of the image? In an ergonomically point of view, the simulator has to reproduce the game play reality and to improve the abstraction and the communication of the coaches
Bechar, Hassane. "Comparaison d'images application à la surveillance et au suivi de trajectoire /". Grenoble 2 : ANRT, 1987. http://catalogue.bnf.fr/ark:/12148/cb37602702g.
Pełny tekst źródłaLefèvre, Sébastien. "Détection d'événements dans une séquence vidéo". Phd thesis, Université François Rabelais - Tours, 2002. http://tel.archives-ouvertes.fr/tel-00278073.
Pełny tekst źródłaMikram, Mounia. "Suivi d'objets dans une séquence d'images par modèle d'apparence : conception et évaluation". Thesis, Bordeaux 1, 2008. http://www.theses.fr/2008BOR13736/document.
Pełny tekst źródłaAbstract
Grégoire, Vincent. "Suivi des piétons par fusion d'images infrarouges et visibles en scènes intérieures". Thesis, Université Laval, 2006. http://www.theses.ulaval.ca/2006/23765/23765.pdf.
Pełny tekst źródłaMostafaoui, Ghilès. "Détection de mouvements et suivi de personnes dans les séquences d'images couleurs". Paris 6, 2005. http://www.theses.fr/2005PA066446.
Pełny tekst źródłaTacchella, Jean-Marc. "Méthodes d'analyse de volumes d'images multimodales pour le suivi longitudinal en oncologie". Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066049/document.
Pełny tekst źródłaLongitudinal follow-up in oncology consists in assessing tumor progression in order to define a treatment strategy for each patient. It is thus necessary to identify relevant biomarkers that allow an early evaluation of the tumor’s response to the treatment. Biomedical imaging exams help to ensure a non-invasive monitoring of patients and to propose complementary biomarkers to existing ones. This search for new biomarkers requires relying on clinical studies to compare globally and locally exams acquired at different times and in different modalities.In this PhD dissertation, we focused on developing an integrated image processing framework to analyze the relevance of indices for evaluating the tumor evolution. The strategy includes three steps: registration data acquired at different times and in different modalities, the segmentation of tumor lesions on exams in each modality, and the computation of global and local indices reflecting the spatiotemporal evolution of the tumor.The most innovative aspect lies in the registration step: due to the difficulties faced with conventional methods, we proposed a new approach consisting in using several registration methods and selecting the best one for each dataset, thanks to a quantitative criterion based on the specific features of the application. The contribution of this approach was proven in two clinical studies: 1) monitoring of patients with high-grade gliomas treated with an antiangiogenic drug, where Single Photon Emission Tomography data (SPECT) obtained after injection of Technetium-99m Sestamibi have to be matched with T1-weighted Magnetic Resonance Images (MRI) acquired after the injection of a contrast agent; 2) monitoring of patients with liver damage treated with various anticancer drugs, requiring the alignment of Computed Tomography (CT) data.The complete image processing framework was applied to the first study. Tumor areas were segmented on MR images using a conventional 2D Level Set method, as well as on the TEMP data using five thresholding methods that differ in the choice of the threshold options. Despite a strong correlation in terms of overall volumes, local indices have shown that some of the detected tumor volumes on early SPECT exams (performed 15 minutes after injection) and late SPECT exams (performed 3 hours after injection) could be located out of the tumor volumes detected on MRI. The high correlation found between the intensity variations in tumor volume during treatment on late SPECT exams and the index of Overall Survival (OS) suggests that this relative change of intensity could be predictive of the patient overall survival, which is not the case with the indices derived from the MRI data on our limited series of patients. Thus, these results show that SPECT imaging, with an exam performed 3 hours after injection of Technetium-99m Sestamibi, can be complementary to MRI in the assessment of tumor progression in glioblastomas.The main perspective for this PhD work would consist in applying the analysis strategy to other clinical studies. However, each step must be adapted to suit the specific nature of the targeted application, including the imaging modalities involved and the considered anatomical area. The expected sticking points are the automation and the robustness of the different steps of the processing chain
Tacchella, Jean-Marc. "Méthodes d'analyse de volumes d'images multimodales pour le suivi longitudinal en oncologie". Electronic Thesis or Diss., Paris 6, 2015. http://www.theses.fr/2015PA066049.
Pełny tekst źródłaLongitudinal follow-up in oncology consists in assessing tumor progression in order to define a treatment strategy for each patient. It is thus necessary to identify relevant biomarkers that allow an early evaluation of the tumor’s response to the treatment. Biomedical imaging exams help to ensure a non-invasive monitoring of patients and to propose complementary biomarkers to existing ones. This search for new biomarkers requires relying on clinical studies to compare globally and locally exams acquired at different times and in different modalities.In this PhD dissertation, we focused on developing an integrated image processing framework to analyze the relevance of indices for evaluating the tumor evolution. The strategy includes three steps: registration data acquired at different times and in different modalities, the segmentation of tumor lesions on exams in each modality, and the computation of global and local indices reflecting the spatiotemporal evolution of the tumor.The most innovative aspect lies in the registration step: due to the difficulties faced with conventional methods, we proposed a new approach consisting in using several registration methods and selecting the best one for each dataset, thanks to a quantitative criterion based on the specific features of the application. The contribution of this approach was proven in two clinical studies: 1) monitoring of patients with high-grade gliomas treated with an antiangiogenic drug, where Single Photon Emission Tomography data (SPECT) obtained after injection of Technetium-99m Sestamibi have to be matched with T1-weighted Magnetic Resonance Images (MRI) acquired after the injection of a contrast agent; 2) monitoring of patients with liver damage treated with various anticancer drugs, requiring the alignment of Computed Tomography (CT) data.The complete image processing framework was applied to the first study. Tumor areas were segmented on MR images using a conventional 2D Level Set method, as well as on the TEMP data using five thresholding methods that differ in the choice of the threshold options. Despite a strong correlation in terms of overall volumes, local indices have shown that some of the detected tumor volumes on early SPECT exams (performed 15 minutes after injection) and late SPECT exams (performed 3 hours after injection) could be located out of the tumor volumes detected on MRI. The high correlation found between the intensity variations in tumor volume during treatment on late SPECT exams and the index of Overall Survival (OS) suggests that this relative change of intensity could be predictive of the patient overall survival, which is not the case with the indices derived from the MRI data on our limited series of patients. Thus, these results show that SPECT imaging, with an exam performed 3 hours after injection of Technetium-99m Sestamibi, can be complementary to MRI in the assessment of tumor progression in glioblastomas.The main perspective for this PhD work would consist in applying the analysis strategy to other clinical studies. However, each step must be adapted to suit the specific nature of the targeted application, including the imaging modalities involved and the considered anatomical area. The expected sticking points are the automation and the robustness of the different steps of the processing chain
Dehais, Christophe. "Contributions pour les applications de réalité augmentée : suivi visuel et recalage 2D. Suivi d'objets 3D représentés par des modèles par points". Phd thesis, Toulouse, INPT, 2008. http://oatao.univ-toulouse.fr/7244/1/dehais.pdf.
Pełny tekst źródłaRicquebourg, Yann. "Analyse de mouvements articules : mesure et suivi 2d ; application a la telesurveillance". Rennes 1, 1997. http://www.theses.fr/1997REN10221.
Pełny tekst źródłaGarcia, Vincent. "Suivi d'objets d'intérêt dans une séquence d'images : des points saillants aux mesures statistiques". Nice, 2008. http://www.theses.fr/2008NICE4059.
Pełny tekst źródłaThe problem of object tracking is a problem arising in domains such as computer vision (video surveillance for instance) and cinematographic post-production (special effects). There are two major classes of solution to this problem : region of interest tracking, which indicates a coarse tracking, and space-time segmentation, which corresponds to a precise tracking of the region of interest’s contour. In both cases, the region of interest must be selected beforehand on the first, and possibly on the last image of the video sequence. In this thesis, we propose two tracking methods (one of each type). We propose also a fast implementation of an existing tracking method using the programmation on Graphics Processing Unit (GPU). The first method is based on the analysis of temporal trajectories of salient points and provides a region of interest tracking. Salient points (typically of point of strong curvature of the isointensity lines) are detected in all the images of the sequence. The trajectories are built by matching salient points of consecutive images whose neighbourhoods are coherent. Our first contribution consists in the analysis of the trajectories on a group of pictures, which improves the motion estimation quality. Moreover, we use a space-time weighting for each trajectory which makes it possible to add a temporal constraint on the movement while taking into account the local geometrical deformations of the object ignored by a global motion model. The second method performs a space-time segmentation. The object contour motion is estimated using the information contained in an outer-layer centered on the object contour. Our first contribution is the use of this outer-layer which contains information about both the background and the object in a local context. The matching using a statistical similarity measure (residual entropy) allows to improve the tracking while facilitating the choice of the optimal size of the crown. Finally, we propose a fast implementation of an existing tracking method of region of interest. This method relies on the use of a statistical similarity measure : the Kullback-Leibler divergence. This divergence can be estimated in a high dimension space using k-th nearest neighbors distance. These calculations being computationally very expensive, we propose a parallel implementation of the exhaustive search of the k-th nearest neighbors using GPU programming (via the programming interface NVIDIA CUDA). We show that this implementation speeds-up the tracking process up to a factor 15 compared to a classical implementation of this search using data structuring methods
Vincent, Garcia. "Suivi d'objets d'intérêt dans une séquence d'images : des points saillants aux mesures statistiques". Phd thesis, Université de Nice Sophia-Antipolis, 2008. http://tel.archives-ouvertes.fr/tel-00374657.
Pełny tekst źródłaLa première méthode repose sur l'analyse de trajectoires temporelles de points saillants et réalise un suivi de régions d'intérêt. Des points saillants (typiquement des lieux de forte courbure des lignes isointensité) sont détectés dans toutes les images de la séquence. Les trajectoires sont construites en liant les points des images successives dont les voisinages sont cohérents. Notre contribution réside premièrement dans l'analyse des trajectoires sur un groupe d'images, ce qui améliore la qualité d'estimation du mouvement. De plus, nous utilisons une pondération spatio-temporelle pour chaque trajectoire qui permet d'ajouter une contrainte temporelle sur le mouvement tout en prenant en compte les déformations géométriques locales de l'objet ignorées par un modèle de mouvement global.
La seconde méthode réalise une segmentation spatio-temporelle. Elle repose sur l'estimation du mouvement du contour de l'objet en s'appuyant sur l'information contenue dans une couronne qui s'étend de part et d'autre de ce contour. Cette couronne nous renseigne sur le contraste entre le fond et l'objet dans un contexte local. C'est là notre première contribution. De plus, la mise en correspondance par une mesure de similarité statistique, à savoir l'entropie du résiduel, d'une portion de la couronne et d'une zone de l'image suivante dans la séquence permet d'améliorer le suivi tout en facilitant le choix de la taille optimale de la couronne.
Enfin, nous proposons une implémentation rapide d'une méthode de suivi de régions d'intérêt existante. Cette méthode repose sur l'utilisation d'une mesure de similarité statistique : la divergence de Kullback-Leibler. Cette divergence peut être estimée dans un espace de haute dimension à l'aide de multiples calculs de distances au k-ème plus proche voisin dans cet espace. Ces calculs étant très coûteux, nous proposons une implémentation parallèle sur GPU (grâce à l'interface logiciel CUDA de NVIDIA) de la recherche exhaustive des k plus proches voisins. Nous montrons que cette implémentation permet d'accélérer le suivi des objets, jusqu'à un facteur 15 par rapport à une implémentation de cette recherche nécessitant au préalable une structuration des données.
Djemal, Khalifa. "Segmentation par contour actif et suivi automatique d'un objet dans une séquence d'images". Toulon, 2002. http://www.theses.fr/2002TOUL0017.
Pełny tekst źródłaAvenel, Christophe. "Suivi de courbes libres fermées déformables par processus stochastiques". Rennes 1, 2011. http://www.theses.fr/2011REN1S116.
Pełny tekst źródłaThe joint analysis of movement and deformation is crucial in many computer vision applications. This thesis proposes a stochastic non-linear filter to track a free curve in time. The proposed approach is implemented through a particle filter including colorimetric measurements characterizing respectively the target and the background. The involved dynamics is formulated as a stochastic differential equation. This allows a continuous representation of the curve trajectory, and thus the possibility to deduce the deformation between images. The curve is defined by an implicit level set, on which the stochastic dynamics is expressed. This takes the form of a stochastic differential equation with a Brownian motion of small dimension. We combined in these evolution models a local motion information extracted from the images and a model of the uncertainty of the dynamics. The associated filter proposed for curve tracking thus belongs to the family of conditional particle filters. Its capabilities are tested on different sequences containing highly deformable objects
Dietrich, Gabriel de. "Segmentation d'organes tubulaires par suivi de squelette". Bordeaux 1, 2003. http://www.theses.fr/2003BOR12670.
Pełny tekst źródłaNguyen, Quoc Dinh. "Détection et suivi automatique du mouvement des lèvres". Paris 6, 2010. http://www.theses.fr/2010PA066650.
Pełny tekst źródłaSekkal, Rafiq. "Techniques visuelles pour la détection et le suivi d’objets 2D". Thesis, Rennes, INSA, 2014. http://www.theses.fr/2014ISAR0032/document.
Pełny tekst źródłaNowadays, image processing remains a very important step in different fields of applications. In an indoor environment, for a navigation system related to a mobile robot (electrical wheelchair), visual information detection and tracking is crucial to perform robotic tasks (localization, planning…). In particular, when considering passing door task, it is essential to be able to detect and track automatically all the doors that belong to the environment. Door detection is not an obvious task: the variations related to the door status (open or closed), their appearance (e.g. same color as the walls) and their relative position to the camera have influence on the results. On the other hand, tasks such as the detection of navigable areas or obstacle avoidance may involve a dedicated semantic representation to interpret the content of the scene. Segmentation techniques are then used to extract pseudosemantic regions based on several criteria (color, gradient, texture...). When adding the temporal dimension, the regions are tracked then using spatiotemporal segmentation algorithms. In this thesis, we first present joint door detection and tracking technique in a corridor environment: based on dedicated geometrical features, the proposed solution offers interesting results. Then, we present an original joint hierarchical and multiresolution segmentation framework able to extract a pseudo-semantic region representation. Finally, this technique is extended to video sequences to allow the tracking of regions along image sequences. Based on contour motion extraction, this solution has shown relevant results that can be successfully applied to corridor videos
Bonnaud, Laurent. "Schémas de suivi d'objets vidéo dans une séquence animée : application à l'interpolation d'images intermédiaires". Phd thesis, Université Rennes 1, 1998. http://tel.archives-ouvertes.fr/tel-00070533.
Pełny tekst źródłaaux séquences d'images, pour des applications multimédia. Ce travail est
divisé en deux contributions principales~: un algorithme de segmentation
d'images en objets vidéo en mouvement, et une méthode d'interpolation
temporelle opérant sur ces objets.
La segmentation de la séquence est effectuée par un algorithme de suivi
temporel. Un algorithme de segmentation spatio-temporelle est utilisé
initialement pour obtenir des régions dans la première image de la séquence.
Cette partition est ensuite suivie par une technique de contours actifs, qui
opère sur une nouvelle représentation de la segmentation, composée des
frontières ouvertes séparant les régions. L'algorithme estime à la fois le
mouvement des frontières et celui des régions. Il est capable de suivre
plusieurs objets simultanément et de traiter les occultations entre eux. Des
résultats, obtenus sur des séquences d'images réelles, montrent que cet
algorithme permet une bonne stabilité temporelle de la segmentation et une
bonne précision des frontières.
Le but de l'algorithme d'interpolation est de reconstruire des images
intermédiaires entre deux images de la séquence. Il s'agit d'un algorithme de
faible complexité qui peut être utilisé à la fin d'une chaîne codeur/décodeur.
L'interpolation est compensée en mouvement et utilise le mouvement des régions,
estimé pendant la phase de suivi. Il est aussi basé objets, dans le sens où il
utilise la segmentation pour prédire correctement les zones d'occultation. Cet
algorithme peut être utilisé pour trois applications différentes~: le codage
interpolatif (où des images de la séquence sont prédites par interpolation),
l'adaptation de la fréquence de la séquence à la fréquence d'affichage du
terminal de visualisation dans une transmission multipoints et la
reconstruction d'images manquantes (où l'on calcule des images non observées).
Des résultats expérimentaux pour la première application montrent que pour une
qualité de reconstruction donnée, la taux de compression moyen sur un groupe
d'images est plus élevé en utilisant l'interpolation qu'avec une prédiction
causale.
Irace, Zacharie. "Modélisation statistique et segmentation d'images TEP : application à l'hétérogénéité et au suivi de tumeurs". Phd thesis, Toulouse, INPT, 2014. http://oatao.univ-toulouse.fr/12201/1/irace.pdf.
Pełny tekst źródła