Дисертації з теми "Suivi du mouvement en échocardiographie"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Suivi du mouvement en échocardiographie".
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.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Ansari, Chekeib. "Traitement des images échocardiographiques : suivi automatique des contours et analyse du mouvement des parois ventriculaires par flux optique." Paris 12, 1990. http://www.theses.fr/1990PA120026.
Yang, Yingyu. "Analyse automatique de la fonction cardiaque par intelligence artificielle : approche multimodale pour un dispositif d'échocardiographie portable." Electronic Thesis or Diss., Université Côte d'Azur, 2023. http://www.theses.fr/2023COAZ4107.
According to the 2023 annual report of the World Heart Federation, cardiovascular diseases (CVD) accounted for nearly one third of all global deaths in 2021. Compared to high-income countries, more than 80% of CVD deaths occurred in low and middle-income countries. The inequitable distribution of CVD diagnosis and treatment resources still remains unresolved. In the face of this challenge, affordable point-of-care ultrasound (POCUS) devices demonstrate significant potential to improve the diagnosis of CVDs. Furthermore, by taking advantage of artificial intelligence (AI)-based tools, POCUS enables non-experts to help, thus largely improving the access to care, especially in less-served regions.The objective of this thesis is to develop robust and automatic algorithms to analyse cardiac function for POCUS devices, with a focus on echocardiography (ECHO) and electrocardiogram (ECG). Our first goal is to obtain explainable cardiac features from each single modality respectively. Our second goal is to explore a multi-modal approach by combining ECHO and ECG data.We start by presenting two novel deep learning (DL) frameworks for echocardiography segmentation and motion estimation tasks, respectively. By incorporating shape prior and motion prior into DL models, we demonstrate through extensive experiments that such prior can help improve the accuracy and generalises well on different unseen datasets. Furthermore, we are able to extract left ventricle ejection fraction (LVEF), global longitudinal strain (GLS) and other useful indices for myocardial infarction (MI) detection.Next, we propose an explainable DL model for unsupervised electrocardiogram decomposition. This model can extract interpretable information related to different ECG subwaves without manual annotation. We further apply those parameters to a linear classifier for myocardial infarction detection, which showed good generalisation across different datasets.Finally, we combine data from both modalities together for trustworthy multi-modal classification. Our approach employs decision-level fusion with uncertainty, allowing training with unpaired multi-modal data. We further evaluate the trained model using paired multi-modal data, showcasing the potential of multi-modal MI detection to surpass that from a single modality.Overall, our proposed robust and generalisable algorithms for ECHO and ECG analysis demonstrate significant potential for portable cardiac function analysis. We anticipate that our novel framework could be further validated using real-world portable devices. We envision that such advanced integrative tools may significantly contribute towards better identification of CVD patients
Rezaei, Zahra, and Zahra Rezaei. "Système de suivi de mouvement." Master's thesis, Université Laval, 2019. http://hdl.handle.net/20.500.11794/37222.
Le comportement des petits animaux est important pour les chercheurs scientifiques et précliniques; ils veulent connaître les effets des interventions sur leur vie naturelle. Pour les maladies humaines, les rongeurs sont utilisés comme modèles. L’étude du comportement des rongeurs permet d’identifier et de développer de nouveaux médicaments pour les troubles psychiatriques et neurologiques. La surveillance des animaux peut être traitée et un grand nombre de données traitées peuvent conduire à de meilleurs résultats de recherche dans un temps plus court. Ce mémoire présente le système de suivi du comportement des rongeurs basé sur des techniques de vision numérique. En vision numérique, la détection d’un sujet consiste à balayer et à rechercher un objet dans une image ou une vidéo (qui n’est qu’une séquence d’images), mais la localisation d’un objet dans des images successives d’une vidéo est appelée suivi. Pour trouver la position d’un sujet dans une image, nous avons utilisé la détection du sujet et le suivi, car le suivi peut aider lorsque la détection échoue et vice et versa. Avec cette approche, nous pouvons suivre et détecter tout type du sujet (souris, headstage, ou par exemple un ballon). Il n’y a pas de dépendance au type de caméra. Pour trouver un sujet dans une image, nous utilisons l’algorithme AdaBoost en ligne qui est un algorithme de suivi du sujet et l’algorithme de Canny qui est un algorithme de détection du sujet, puis nous vérifions les résultats. Si l’algorithme Adaboost en ligne n’a pas pu trouver le sujet, nous utilisons l’algorithme Canny pour le trouver. En comparant les résultats de notre approche avec les résultats des algorithmes AdaBoost en ligne et Canny séparément, nous avons constaté que notre approche permet de mieux trouver le sujet dans l’image que lorsque nous utilisons ces deux algorithmes séparément. Dans ce mémoire, nous décrirons les algorithmes de détection et de suivi du sujet.
Small animal behavior is important for science and preclinical researchers; they want to know the effects of interventions in their natural life. For human diseases, rodents are used as models; studying rodent behavior is good for identifying and developing new drugs for psychiatric and neurological disorders. Animal monitoring can be processed and a large number of data can lead to better research result in a shorter time. This thesis introduces the rodents’ behavior tracking system based on computer vision techniques. In computer vision, object detection is scanning and searching for an object in an image or a video (which is just a sequence of images) but locating an object in successive frames of a video is called tracking. To find the position of an object in an image, we use object detection and object tracking together because tracking can help when detection fails and inversely. With this approach, we can track and detect any objects (mouse, headstage, or a ball). There is no dependency to the camera type. To find an object in an image we use the online AdaBoost algorithm, which is an object tracking algorithm and the Canny algorithm, which is an object detection algorithm together, then we check the results. If the online Adaboost algorithm could not find the object, we use the Canny algorithm to find the object. By comparing the results of our approach with the results of the online AdaBoost and Canny algorithms separately, we found that our approach can find the object in the image better than when we use these two algorithms separately. In this thesis, we will describe implemented object detection and tracking algorithms.
Small animal behavior is important for science and preclinical researchers; they want to know the effects of interventions in their natural life. For human diseases, rodents are used as models; studying rodent behavior is good for identifying and developing new drugs for psychiatric and neurological disorders. Animal monitoring can be processed and a large number of data can lead to better research result in a shorter time. This thesis introduces the rodents’ behavior tracking system based on computer vision techniques. In computer vision, object detection is scanning and searching for an object in an image or a video (which is just a sequence of images) but locating an object in successive frames of a video is called tracking. To find the position of an object in an image, we use object detection and object tracking together because tracking can help when detection fails and inversely. With this approach, we can track and detect any objects (mouse, headstage, or a ball). There is no dependency to the camera type. To find an object in an image we use the online AdaBoost algorithm, which is an object tracking algorithm and the Canny algorithm, which is an object detection algorithm together, then we check the results. If the online Adaboost algorithm could not find the object, we use the Canny algorithm to find the object. By comparing the results of our approach with the results of the online AdaBoost and Canny algorithms separately, we found that our approach can find the object in the image better than when we use these two algorithms separately. In this thesis, we will describe implemented object detection and tracking algorithms.
Léger, Christophe. "Contribution au suivi volumique en temps réel du ventricule gauche par échocardiographie." Phd thesis, Université d'Orléans, 1993. http://tel.archives-ouvertes.fr/tel-00607860.
Nguyen, Quoc Dinh. "Détection et suivi automatique du mouvement des lèvres." Paris 6, 2010. http://www.theses.fr/2010PA066650.
WANG, JUHUI. "Analyse et suivi du mouvement 3d articule : application a l'etude du mouvement humain." Rennes 1, 1992. http://www.theses.fr/1992REN10131.
LACASSAGNE, LIONEL. "Detection de mouvement et suivi d'objets en temps reel." Paris 6, 2000. http://www.theses.fr/2000PA066252.
Delamarre, Quentin. "Suivi du mouvement d'objets articulés dans des séquences d'images vidéo." Nice, 2003. http://www.theses.fr/2003NICE4067.
We 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
Chezalviel, Frédérique. "Mise au point d'un modèle d'étude de la fonction ventriculaire gauche par échocardiographie temps mouvement chez le chien éveillé." Paris 5, 1988. http://www.theses.fr/1988PA05P012.
Mostafaoui, Ghilès. "Détection de mouvements et suivi de personnes dans les séquences d'images couleurs." Paris 6, 2005. http://www.theses.fr/2005PA066446.
Aurat, David. "Immersion visuelle tridimensionnelle haute performance par suivi du mouvement des yeux." Thesis, Paris Sciences et Lettres (ComUE), 2016. http://www.theses.fr/2016PSLEM014/document.
Simulators are more and more used in industry because they help for making and testing objects. Like in other domains, simulators use stereoscopic screen to get closer natural vision and artificial vision. However, stereoscopy create some physiological problems like vergence-accommodation conflict. This conflict is one of the main cause of visual strain while viewing stereoscopic contents. In a first part, we will see some methods to reduce visual fatigue due to vergence-accommodation conflict. Then, we will propose, test and validate a new method: a blur in peripheral vision. This treatment reduce eye strain. In addition, we found out that the smaller the sharp area is, the more effective the treatment is. In the second part, we will focus on the shape perception in stereoscopic vision and how to improve it. The main contribution will be to take into account the user’s gaze point in the rendering process to reproduce the effect of the gaze direction in natural vision and improve the perception of the virtual environment. This camera convergence create deformations – called vertical parallaxes – on the screen in peripheral vision. This new method improve shape perception if objects are located close to the user
Marzani, Franck. "Contribution à l'analyse et au suivi du mouvement humain sans marqueur." Dijon, 1998. http://www.theses.fr/1998DIJOS008.
Touil, Basma. "Segmentation du myocarde en échocardiographie ultrasonore par ensembles de niveaux sous contrainte de forme et de mouvement." Lyon, INSA, 2010. http://theses.insa-lyon.fr/publication/2010ISAL0127/these.pdf.
Segmentation of cardiac structures in ultrasound imaging is still an open and difficult problem. Indeed, the physical process of ultrasound image formation (ultrasonic wave interaction with the explored biological tissues) leads to noisy images ("speckle" phenomenon) and low contrast. Because of these difficulties, most of the research has been devoted to the segmentation of the endocardium (internal interface between blood and heart muscle) and few studies address the segmentation of the epicardium (external interface). To achieve a complete segmentation of the myocardium, we proposed in this thesis a method integrating motion information in the segmentation process. The first part of this work is therefore devoted to motion estimation in echocardiographic images sequences. Most of motion estimation techniques are limited due to the complexity of ultrasound image formation. These limitations have been assessed for block matching methods, from realistic simulations and in vivo cardiac data. From these results a reliable motion estimation technique has been selected and used on real data. The developed segmentation belongs to active contours methods. Our approach is based on the variational level set formalism. The evolution of the associated interface based on local statistics and incorporates an elliptical shape prior. The novelty of the approach is linked to the fact that this shape prior is propagated through the cardiac sequence using a Kalman tiller. Our method was tested on real in vivo data, corresponding to 120 cardiac images. The evaluation was done by comparing the obtained contours with the contours traced by an expert cardiologist. The results showed that the method performs very well for the segmentation of the epicardium, independently of image sequence quality. The segmentation of the endocardium still need to be improved and we draw methodological perspectives that may lead to such improvement
Béréziat, Dominique. "Détection et suivi de structures déformables en mouvement : application à la météorologie." Paris 11, 1999. http://www.theses.fr/1999PA112214.
Verpillat, Frédéric. "Suivi 3D de nanoparticules d'or par holographie digitale." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2012. http://tel.archives-ouvertes.fr/tel-00836925.
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.
HAMDAN, RAOUF. "Detection, suivi et reconnaissance des formes et du mouvement par modeles probabilistes d'apparence." Université Louis Pasteur (Strasbourg) (1971-2008), 2001. http://www.theses.fr/2001STR13002.
Saboune, Jamal. "Développement d'un système passif de suivi 3D du mouvement humain par filtrage particulaire." Phd thesis, Université de Technologie de Troyes, 2008. http://tel.archives-ouvertes.fr/tel-00598867.
Saboune, Jamal. "Développement d'un système passif de suivi 3D du mouvement humain par filtrage particulaire." Phd thesis, Troyes, 2008. http://www.theses.fr/2008TROY0002.
The main idea behind the PARAChute project is to reduce the number of falls in the elderly by preventing them. This thesis work which is a part of this project aims to develop a new non intrusive human gait analysis system which would be a component of a fall risk evaluation system. Many methods have been used to evaluate dynamic equilibrium of a person while walking. By studying these methods, we were able to identify some gait parameters which are pertinent for fall risk detection. All these methods previously used, are based on clinical tests, or on using wearable sensors. Thus, we opted to develop a new approach based on a completer marker less 3D human motion capture system. The new system we created uses video feeds, a virtual 3d body model and a novel particle filtering algorithm we developed. This algorithm reorganizes the model’s configurations search space in a efficient, optimal and deterministic way. In order to reduce the complexity of this algorithm, we also developed a factorized version of it, using a dynamic Bayesian network. In terms of quality of 3D reconstruction, the results of our method are satisfactory
Halit, Mehdi. "Détection et suivi de contours sur des séquences échocardiographiques apicales par coopération de modèles déformables et de réseaux de neurones." Lille 1, 1999. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/1999/50376-1999-147.pdf.
Devevey, Christophe. "Etude du mouvement sur des séquences d'images échographiques : : poursuite de cibles rigides et segmentation, par une approche connexionniste du champ, des vitesses d'objets déformables." Lyon, INSA, 1993. http://www.theses.fr/1993ISAL0006.
The purpose of this study is the exploitation of the motion information generated in ultrasonic image sequence. In the first section, the performances of four tracking techniques is first compared in terms of accuracy and processing time. The best algorithm. Based on correlation is then used to track gallstones or urinary stones in order to enhance the efficiency of extracorporeal lithotripsy. In the second part of this work. The optical flow is estimated and parametrized using two neural networks. The classification of the vector field parameters by clustering is then used for motion segmentation. The computer analysis of heart motion from two-dimensional echocardiograms using this technique can facilitate the diagnosis of cardiac pathology
Dornier, Aurélie. "Etude du mouvement de kinésine par suivi de particule unique par onde évanescente progressive." Paris 6, 2005. http://www.theses.fr/2005PA066085.
Mansencal, Nicolas. "Tumeurs endocrines digestives et cardiopathie carcinoïde : valeur diagnostique de l'échocardiographie, suivi prospectif et prise en charge thérapeutique." Versailles-St Quentin en Yvelines, 2010. http://www.theses.fr/2010VERS0054.
Carcinoid heart disease is a rare disease, which is mainly defined as a right-sided retracted valvular disease These valvular injuries occur only in case of digestive endocrine tumor (less than 2 per 100,000 persons per year) and carcinoid syndrome (less than 10% of carcinoid tumors). Serotonin plays a major role in the pathogenis of carcinoid heart disease. In this thesis, we performed a review of the literature of carcinoid heart disease in 2010, then we present the results of different prospective studies that we performed: echocardiographic follow-up of carcinoid heart disease, assessment of patent foramen ovale, validation of a new echocardiographic tool for the prognostic assessment of carcinoid heart disease and a new therapeutic approach in patients with carcinoid heart disease and patent foramen ovale
Perret, Yannick. "Suivi de paramètres de modèle géométriques à partir de séquences vidéo multi-vues." Lyon 1, 2001. http://www.theses.fr/2001LYO10276.
Thery, Alice. "Étude de la détection du ventricule gauche, à partir de vues échocardiographiques sous incidence apicale, par application de la logique floue : contribution à la restitution 3D du mouvement du ventricule." Lille 1, 1995. http://www.theses.fr/1995LIL10123.
Wei, Yan. "Planification et Suivi de Mouvement d’un Système de Manipulateur Mobile non-holonome à deux bras." Thesis, Ecole centrale de Lille, 2018. http://www.theses.fr/2018ECLI0004/document.
This thesis focuses on the motion planning and tracking of a dual-arm mobile humanoid. First, MDH is used for kinematic modeling. The co-simulation via Simulink-Adams on prototype is realized to validate the effectiveness of RBFNN controller. In order to overcome the shortcomings of Euler-Lagrange’s formulations that require calculating energy and energy derivatives, Kane’s method is used. In addition, physical stability is analyzed based on Kane’s method and a controller is designed using back-stepping technique. Secondly, an improved MaxiMin NSGA-II is proposed to design the mobile base’s (MB) optimal position-orientation and the upper manipulator’s (UM) optimal configuration given only the initial pose and end-effectors’ (EEs) desired positions-orientations. A direct connect algorithm combining BiRRT and gradient-descent is designed to plan the transition from initial pose to optimal pose, and a geometric optimization method is designed to optimize and cohere the path. In addition, forward motions are obtained by assigning orientations for MB thus indicating robot’s intention. In order to solve the failure problem of offline algorithm, an online algorithm is proposed while estimating dynamic obstacles’ motions. In addition, in order to optimize via-poses, an algorithm based on EEs’ via-points and MOGA is proposed by optimizing four via-pose-based objective functions. Finally, the motion tracking problem is studied given EEs’ motions in the task space. Instead of controlling the absolute motion, two relative motions are introduced to realize the coordination and cooperation between MB and UM. In addition, an modulated WLN technique is proposed to avoid joints’ limits
Fontmarty, Mathias. "Vision et filtrage particulaire pour le suivi tridimensionnel de mouvement humain : applications à la robotique." Toulouse 3, 2008. http://www.theses.fr/2008TOU30162.
A great robotic challenge today is the one of the personal robot. While moving in real environments, the robot must take into account the human presence in its neighborhood in order to avoid them or to facilitate their moves. However, for an active interaction, the robot must also be able to perceive their pose or their moves. To this end, we are willing to set up a human motion tracking system from embedded cameras on the robot. A rough 3D representation of the human body is proposed taking into account biomecanics and anthropomorphic constraints. The model projection is then fitted to the images by exploiting various 2D visual cues (edges, colors, motion) and 3D sparse reconstruction of the scene. In order to estimate the 3D configuration parameters, we use the well-known particle flters. Evolutions are considered in order to efficiently tackle the problem by satisfying strong temporal constraints due to the final application. To address issues step by step, two different contexts are proposed. The first one (ubiquist robotics) operate with fixed ambiance cameras proposing various and complementary view points. The second one (mobile robotics) exploits a stereo camera embedded on the robot
Fitton, Isabelle. "Analyse d'images d'échocardiographie et Doppler tissulaire myocardique : Applicationsà l'étude du mouvement myocardique dans le plan petit axe cardiaque." Bordeaux 2, 2001. http://www.theses.fr/2001BOR28832.
Two-dimensional echocardiography is a highly effective tool for the assessment and the prognosis of a cardiac pathology. Nowadays, ultrasound imagers reduce the wall motion analysis to a qualitative study. In this report, we propose to derive quantitative information about left ventricular motion by the processing of echographic images in short-axis view. An essential first step is to determine the location of the cardiac boundaries within each image of the cardiac sequence. So, we developed a user-friendly computer software of segmentation. The method we applied is based on the characteristics of ultrasound images acquisition. Secondly, from the boundaries obtained by the procedure of segmentation, the software automatically provides physicians with the left ventricle wall regional thickening, during a cardiac cycle. Thirdly, by use of the combination of informations extracted from two-dimensional echocardiocardiography and Doppler tissue imaging, we propose an original method to identify the complex wall motion into three components : contraction, rotation and translation throughout a cardiac cycle, and apply it to the reconstruction of myocardial regional contraction velocity images
Bugeau, Aurélie. "Détection et suivi d'objets en mouvement dans des scenes complexes, application a la surveillance des conducteurs." Phd thesis, Université Rennes 1, 2007. http://tel.archives-ouvertes.fr/tel-00551601.
Selsis, Muriel. "Application des modèles de contours actifs au suivi et à la localisation 3D d'objets en mouvement." Lille 1, 1996. http://www.theses.fr/1996LIL10021.
Bugeau, Aurélie Pérez Patrick. "Détection et suivi d'objets en mouvement dans des scènes complexes application à la surveillance des conducteurs /." [S.l.] : [s.n.], 2007. ftp://ftp.irisa.fr/techreports/theses/2007/bugeau.pdf.
Bugeau, Aurélie. "Détection et suivi d'objets en mouvement dans des scènes complexes : application à la surveillance des conducteurs." Rennes 1, 2007. ftp://ftp.irisa.fr/techreports/theses/2007/bugeau.pdf.
Detecting and tracking moving objects in dynamic scenes is a hard but essential task in a large number of computer vision applications such as surveillance. This thesis aims at detecting, segmenting and tracking foreground moving objects in sequences (such as driver sequences) having highly dynamic backgrounds, illumination changes and low contrasts, and possibly shot by a moving camera. Two main steps compose the thesis. First, moving points, described by their motion and color, are selected within a sub-grid of image pixels. Clusters of points are then formed using a variable bandwidth mean shift with automatic bandwidth selection. In a second part, a tracking method is proposed. It combines color and motion distributions, the prediction of the tracked object and some external observations (which can be the clusters from the detector) into an energy function minimized with Graph Cuts
MAURIZOT, MARIETTE. "Analyse du mouvement fluide 2d dans des sequences d'images numeriques : localisation, caracterisation et suivi des points singuliers." Rennes 1, 1997. http://www.theses.fr/1997REN10153.
Arnaud, 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.
Nous 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.
Allouche, Cyril. "Reconstruction, recalage et modélisation 4D du mouvement du ventricule gauche du cœur humain pour le traitement d'images médicales." Paris 11, 2002. http://www.theses.fr/2002PA112048.
The present PhD thesis is devoted novel 3D and 4D reconstruction and registration techniques for cardiac imaging. It was made within the "Philips Research France" laboratories, Medical Imaging Systems group, from October 1999 to November 2001, with academic collaboration with INRIA's EPIDAURE project. Part I describes my work on MRI tagging images, including a very fast and accurate tag detection algorithm, a new interpolation technique for wall motion computation from the grid points and applications to the acquisation of quantitative and clinical motion parameters. Part II introduces novel methods for the building of a 3D compact deformation model of the human left ventricle, then for a statistical 4D (3D+t) model. Part III is devoted to the application of Part II models to surface-based registration. Relevant applications are shown on the wall motion computation in 3D echocardiography. .
Asselin, Pierre-Luc. "Le dôme (nouvelles) suivi de L'espace narratif et l'évolution identitaire des personnages dans Cet imperceptible mouvement de Aude." Mémoire, Université de Sherbrooke, 2010. http://savoirs.usherbrooke.ca/handle/11143/2656.
Vincent, Fabrice. "Gabarits déformables élastiques pour la segmentation et le suivi de mouvement du coeur en Imagerie par Résonance Magnétique." Lyon, INSA, 2001. http://www.theses.fr/2001ISAL0079.
We propose in this report an original deformable template whose regularisation energy comes from the theory of elasticity. We apply this template to the 2D/3D segmentation and the motion tracking of the heart in Magnetic Resonance (MR) Imaging, with and without tagging. The medical purpose of such image processing techniques is to quantify the contractile function of the heart and detect abnormalities related to cardiovascular diseases such as ischaemia. We first show that a template whose energy is composed of a data term and the elastic energy, gives good segmentation results on 2D/3D MR standard images. We the propose an improvement of this template by adding an energy component that regularizes the interfaces and a pixel based matching criterion. We illustrate the good behaviour of the proposed template by tracking the heart motion in tagged MRI
Leduc, Billie-Anne. "Marées d'Iris, roman par tableaux, suivi de La dérobade comme mouvement d'écriture chez Marina Tsvetaeva et Sylvia Plath." Mémoire, Université de Sherbrooke, 2017. http://hdl.handle.net/11143/10535.
Vincent, Fabrice Magnin Isabelle. "Gabarits déformables élastiques pour la segmentation et le suivi de mouvement du coeur en Imagerie par Résonance Magnétique." Villeurbanne : Doc'INSA, 2005. http://docinsa.insa-lyon.fr/these/pont.php?id=vincent.
Cuzol, Anne Memin Étienne. "Analyse d'écoulements fluides à partir de séquences d'images estimation de champs de vitesses et suivi temporel par filtrage stochastique non linéaire /." [S.l.] : [s.n.], 2006. ftp://ftp.irisa.fr/techreports/theses/2006/cuzol.pdf.
Blanco, César. "Suivi de la cinétique de croissance du biofilm généré dans un réacteur à biofilm à lit en mouvement (RBLM)." Mémoire, École de technologie supérieure, 2010. http://espace.etsmtl.ca/629/1/BLANCO_C%C3%A9sar.pdf.
Delhay, Bertrand. "Estimation spatio-temporelle de mouvement et suivi de structures déformables : application à l'imagerie dynamique du coeur et du thorax." Lyon, INSA, 2006. http://theses.insa-lyon.fr/publication/2006ISAL0119/these.pdf.
The motivation of this study is the extraction of quantitative parameters characterizing the dynamics of moving organs from three-dimensional cardiac and thoracic image sequences. Our approach is based on non-linear parametric registration technique. The deformation model, known as free form deformation transformation, is based on a hierachical multi-scale parametric representation using B-Spline basis functions. We quickly noticed the limits of this 3D approach for motion estimation and tracking in sequences and the need for introducing temporal constraints. First of all, we contributed to the construction of a probabilistic dynamic model of the 4 cardiac chambers. The geometrical model of the structures consists of a set of pseudo-markers which describe the evolution of cardiac surfaces. A sampling of the trajectories of these pseudo-markers is adapted to the image sequence of images. This results in a statistical model made up of an average shape and variations estimated by Parzen windowing at each time points. A parametric and continuous state model of the spatio-temporal transformations is introduced. An algorithm based on the Kalman filter estimates the parameters of this model under the constraint of motion periodicity. The principal advantage of this method is to take into account all the images in the sequence. This proposed framework allows the contextual adaptation of the complexity of the motion model. In order to decrease computing times, a parallel version and various strategies were implemented, in particular on a multiprocessors architecture. Lastly, an evaluation of the parameters influence is proposed on synthetic and real cases
GARCIA-GARDUNO, VICTOR. "Une approche de compression orientee-objets par suivi de segmentation basee mouvement pour le codage de sequences d'images numeriques." Rennes 1, 1995. http://www.theses.fr/1995REN10045.
Delhay, Bertrand Clarysse Patrick Magnin Isabelle. "Estimation spatio-temporelle de mouvement et suivi de structures déformables application à l'imagerie dynamique du coeur et du thorax /." Villeurbanne : Doc'INSA, 2007. http://docinsa.insa-lyon.fr/these/pont.php?id=delhay.
Hamlaoui, Soumya. "Suivi 2D de visages et de mouvements faciaux." Compiègne, 2006. http://www.theses.fr/2006COMP1531.
Tracking a face and its facial features in a video sequence is a challenging problem in computer vision. This thesis addresses the problem of tracking the 2D global motion of a face as well as the local motion of its inner features. Ln this thesis, we propose a stochastic approach based on a particle filtering scheme. The observation distribution is derived from an active appearance model, or from an on-Iine estimated appearance model. The dynamics describing the state system evolution are guided by a deterministic research. The particle number is adjusted to the effective needs of the tracking at each time step. This adjustment allows an optimization of the computing time. We also use a robust distance measure which increases the tracking robustness when the face is partially occulted. Experiments on real video show encouraging results
Dupont, Romain. "Suivi des parties cachées et autres problèmes urbains soulevés par la reconstruction tridimensionnel de l'environnement urbain." Marne-la-vallée, ENPC, 2006. http://www.theses.fr/2006ENPC0619.
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.
BELLON, ALEX. "Detection et suivi de vehicules en mouvement dans une sequence d'images. Implantation parallele sur un systeme experimental a memoire distribuee." Clermont-Ferrand 2, 1996. http://www.theses.fr/1996CLF21843.
Treuillet, Sylvie. "Analyse de trajectoires 2d en vue de l'estimation du mouvement d'un objet par vision monoculaire : application au suivi d'obstacles routiers." Clermont-Ferrand 2, 1993. http://www.theses.fr/1993CLF21563.
Lanvin, Patrick. "Fusion multicapteurs pour la détection et le suivi de formes par filtrage particulaire : une approche dense." Littoral, 2004. http://www.theses.fr/2004DUNK0115.
The aim of this work is the tracking, the estimation of the position and the motion, and the detection of 3D objects, in a multisensor environment. The originality of this work relies on a dense modelling of the object which avoids any preprocessing of the images. The problem relies on a non-linear state modelling whose solution is based on a sequential Monte-Carlo method. This one is particularly suitable to process the non-linearities of the models. The use of a centralized fusion architectureallows to preserve the optimality of the processing. The works can be essentially split into two main parts : the first part concerns the detection and the tracking of 2D objects where more than one hypothesis are possible. The method is applied on synthetic and real monocular image sequences with low signal/noise ratios. The second part proposes a global modelling in the case of 3D objects and more particularly in a multisensor environment, by fusing the measurements from reflectance and range images. By way of perspective, a last part describes any possible strategies to decrease the computing load of this method