1,721,072 research outputs found
Cross-modality guided Image Enhancement
Full text linkThe quality of medical images is a crucial factor that affects the performance of several image analysis tasks. Low contrast and noise are among the widely investigated distortions in medical image enhancement problems. In this thesis, the approaches to improve the contrast of medical images and reduce the noise have been proposed by particularly investigating how the cross-modal guidance from another medical image impacts the enhancement. We are particularly interested in enhancing Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) which are widely used in both diagnosis and therapy planning. The first section of the thesis focuses on contrast enhancement and the second section focuses ondenoising. This dissertation presents our research work supported by six original publications (including five published papers and one accepted for publication).
First, in the context of cross-modality guided contrast enhancement, two traditional global enhancement approaches are proposed to improve the contrast of CT images of the human liver using corresponding MR images. The first approach uses context-aware two-dimensional histogram specification (HS) and morphological operations. The objective of this scheme is to improve the visibility of the organ’s anatomy to facilitate the tasks of surgeons and radiologists. The second uses 2D-HS followed by an optimization scheme to minimize the artifacts associated with histogram-based methods and simultaneously preserves the structure of the image during enhancement. In this approach, the enhanced images are analyzed from two perspectives (contrast enhancement and improvement in tumor segmentation). Both techniques have been validated on multi-modal data acquired from a hospital in Norway. Furthermore, an acceleration scheme was proposed by parallelizing the steps involved in the proposed CE approach which drastically reduced the execution time of the algorithm. The third method uses deep learning to improve the contrast of medical images using guidance from multi-modal MR images. Cycle-GAN (Generative Adversarial Network) was applied for this purpose where the corresponding high-contrast image from another modality was used as ground truth as opposed to using manually enhanced ground truth/ referenceimage.
Secondly, noise is another artifact that affects the visual quality of medical images. It not only hampers the visibility of structures for clinicians who inspect these images to thoroughly understand the organ’s morphology; but it also affects the subsequent image analysis tasks. It is therefore imperative to remove noise and improve the perceptual quality of medical images. Different kinds of noise contaminate medical images. In this thesis, we proposed a method to denoise T1- weighted (T1-w) MR images contaminated with Rician noise. We exploited the complementarity-aware information in better perceptual quality multi-modal medical images for denoising purpose. In particular, the role of deep learning approach was investigated in this regard. The features from dual images were combined in a hierarchical manner to extract rich features, which are later combined in a systematic way as opposed to simple feature concatenation. The performance was validated on two public datasets both from a qualitative and quantitative perspective. Moreover, the comparison was done with single image denoising schemes on varying levels of noise
A fast incremental approach for accurate measurement of the displacement field
No full textA fast method for accurate measurement of displacement field that combines template matching and differential techniques is proposed. This method, which is able to deal with the problems of non-rigid object movement as well as large inter frame displacements, operates in three steps. First, a sparse displacement field is obtained by a classic template matching technique. Then, this information is propagated through the overall image to obtain a dense displacement field. Finally, this field is considered as approximate solution before the use of classical differential technique for optical flow estimation. To illustrate the efficiency of the proposed procedure, a number of experimental results using both synthetic and real images are presented and discussed. The results show significant improvement over those obtained using standard multigrid approaches, especially in the cases of textured, very structured images or large inter frame displacements
Boosting UAVs live uplink streaming by video stabilization
Full text linkThe high-impact scenario of UAV live uplink streaming is gaining significant interest in diverse applications, such as ambient monitoring, disaster rescue, and smart surveillance. This paper addresses the problem of uplink streaming by a fleet of camera-equipped UAVs, with one UAV acting as the sink, collecting and transmitting videos from the others. We demonstrate that performing video stabilization at the source UAVs or the sink enhances video quality and reduces required communication throughput, leading to bandwidth savings. We analyze the UAV live uplink streaming architecture to identify the most effective stabilization point within the network in a distributed manner. Using a reinforcement learning framework, we develop a method to dynamically optimize the stabilization gain-cost trade-off, pinpointing the optimal node for stabilization tasks. Through targeted numerical simulations under different system conditions we identify when and where stabilization should be applied to maximize efficiency. Our results show that video stabilization improves system performance in terms of media quality, battery life, and bandwidth usage
Visual Mall
No full textThis CD Contains the work done during the Erasmus Stage at the Institule Galilee of the Université Paris 13 Nord, In this project I do a study and development in a 3D Web, 3D visualization and Streaming of HD Videos. 3D Web refers to the process and techniques used to display 3D content in a browser, the first part will describe the general concepts, after that a brief description of the actual technologies and options to development and creation of 3D contents, the end of the first part will be a more complete description of the option chosen and the reasons and criteria to choose.
The second part will explore the techniques and theory of the 3D visualization, beginning with the physical and biological concept of the 3D perception, after that will be the explication of the theory necessary to implement the 3D visualization and the last part will describe the implementation. The third and last part will describe the concepts of Streaming and HD in video, give a overview of resolution, quality and definition in videos and at last, will describe the implementation of the Streaming of HD Videos. This article will end with a overview to all the system, describe the different parts and give some examples.Álvarez Morales, VM. (2011). Visual Mall. https://riunet.upv.es/handle/10251/12650.Archivo delegad
Résolution du problème de transfert de chaleur par une approche TAC application au traitement et à l'analyse des images
No full textThis thesis proposes an alternative to partial differential equations (PDEs) for the solution of some problems in computer vision based on the heat transfer equation. Traditionally, the method for solving such physics-based problems is to discretize and solve a PDE by a purely mathematical process. Instead of using the PDE, we propose to use the global heat equation and to decompose it into basic laws. We show that some of these laws admit an exact global version since they arise from balance principles. We also show that the assumptions made on the other basic laws can be made wisely, taking into account knowledge about the problem and the domain. We use a computational algebraic topology-based image model which allows us to encode a physical conservative law by linking a global value on a domain with values on its boundary. The numerical scheme is derived in a straightforward way from the problem modeled. It thus provides a physical explanation of each solving step in the solution. We apply the scheme to various applications: image reconstruction from the Laplacian, optical flow computation, denoising by graylevel and multispectral diffusion and inpainting which are all modeled with the heat transfer equation
Résolution du problème de transfert de chaleur par une approche TAC : application au traitement et à l'analyse des images
No full textThis thesis proposes an alternative to partial differential equations (PDEs) for the solution of some problems in computer vision based on the heat transfer equation. Traditionally, the method for solving such physics-based problems is to discretize and solve a PDE by a purely mathematical process. Instead of using the PDE, we propose to use the global heat equation and to decompose it into basic laws. We show that some of these laws admit an exact global version since they arise from balance principles. We also show that the assumptions made on the other basic laws can be made wisely, taking into account knowledge about the problem and the domain. We use a computational algebraic topology-based image model which allows us to encode a physical conservative law by linking a global value on a domain with values on its boundary. The numerical scheme is derived in a straightforward way from the problem modeled. It thus provides a physical explanation of each solving step in the solution. We apply the scheme to various applications: image reconstruction from the Laplacian, optical flow computation, denoising by graylevel and multispectral diffusion and inpainting which are all modeled with the heat transfer equation.Nous proposons une alternative aux équations aux dérivées partielles (EDP) en vue de solutionner certains problèmes en traitement d'images qui sont basés sur un modèle de transfert de chaleur. Traditionnellement , la démarche pour solutionner de tels problèmes basés sur un modèle de champs physiques est de discrétiser et de solutionner une EDP par un procédé purement mathématique. Au lieu de l'EDP, nous proposons d'utiliser une approche qui consiste à décomposer en lois de base, le principe global de conservation de chaleur. Nous montrons que certaines de ces lois admettent une version globale et exacte puisqu'elles proviennent de principes conservateurs. Nous montrons également que les hypothèses sur les autres lois de base peuvent être faites de façon avisée, en tenant compte de certaines connaissances sur le problème et le domaine. Nous utilisons un modèle d'images basé sur la topologie algébrique calculatoire qui nous permet d'encoder simplement les lois de conservation en liant une valeur globale sur un domaine avec des valeurs sur les frontières de ce domaine. Le schéma numérique est dérivé directement du problème modélisé. Ce procédé fournit une explication physique de chaque étape de la résolution. Nous appliquons ce schéma à plusieurs problèmes de traitement d'images qui sont tous régis par le transfert de chaleur : la reconstruction d'images à partir du Laplacien, le calcul du flot optique, le débruitage par diffusion des niveaux de gris et des couleurs ainsi que la retouche d'images ( «inpainting» )
Multichannel processing and analysis for QoS and quality driven video surveillance over wireless sensors
No full textLes systèmes de vidéosurveillance intelligente sont de plus en plus exigeants en termes de qualité, de fiabilité et de flexibilité, notamment ceux basés sur les réseaux de capteurs multimédia sans fil. Bien que les nouveaux systèmes accordent beaucoup d’attention à des fonctionnalités de haut niveau telles que la détection d’événements anormaux, la qualité de la vidéo ainsi que la qualité du réseau ont été plus ou moins longtemps négligées. Ces distorsions sont d’origines diverses, dépendant ainsi des conditions d’acquisition, du codage vidéo et/ou la mauvaise qualité du réseau. La qualité de la vidéo est donc fortement conditionnée par ces trois éléments essentiels de la chaine de vidéo surveillance. En effet, cela se répercute inévitablement sur les performances du système de détection et d’identification d’objets, d’événements anormaux et de façon générale l’interprétation de la scène filmée. L’un des principaux défis de la vidéosurveillance intelligente est donc d’améliorer la qualité d’expérience du système. En effet, il est primordial d’évaluer la qualité perceptuelle vidéo afin de de décider d’éventuels pré-traitements ou post-traitements de rehaussement de qualité. D’autre part, l’architecture du réseau doit répondre aux exigences de la vidéo-surveillance et respecter ses spécificités afin de garantir une bonne qualité de service. Dans cette thèse, nous nous intéressons à la qualité des systèmes de vidéo surveillance. Notre objectif est d’étudier l’aspect qualité des nouveaux systèmes émergents de vidéosurveillance intelligente. Les principales contributions de cette thèse se situent à trois niveaux. Premièrement, une nouvelle technique de codage d’images stéréoscopiques basée sur l’optimisation des filtres d’un schéma de lifting non séparables est proposée. En fait, cette technique de codage stéréoscopique peut être étendue au contexte du codage multi-vues et peut offrir de meilleures performances de codage pour les systèmes de vidéosurveillance multi-vue. La deuxième contribution porte sur une nouvelle architecture de vidéo surveillance intelligente basée sur l’évaluation de la qualité vidéo. Une base de données de qualité vidéo orientée vers la vidéosurveillance a été ainsi développée pour la première fois, à notre connaissance, pour ce besoin spécifique. Enfin, un modèle de planification basé sur la priorité des trafics pour les capteurs multimédias est proposé. Les résultats de cette thèse soulignent l’importance de nos contributions dans le domaine de la vidéosurveillance intelligente. Ce travail n’a pas la prétention d’avoir résolu complètement les problèmes soulevés dans cette thèse. Il constituent une première contribution modeste en ayant exploré et analysé les problèmes les plus cruciaux. Il a néanmoins le mérite d’avoir analysé à fond les problèmes que soulèvent la VS et d’avoir proposé quelques solutions qui restent à parfaire dans le cadre de travaux futures. Soulignons enfin, la mise à disposition de la communauté scientifique d’une base de vidéos haute résolution, unique à notre connaissance, présentant différents scénarios constitue un apport considérable.Intelligent Video surveillance systems are more and more demanding in terms ofquality, reliability and flexibility especially those based on Multimedia wirelesssensors networks. As much as new systems pay a lot of attention to high-levelfeatures such as abnormal event detection, the quality of the video as well asthe quality of the network were for a long time neglected. However, due tosome natural distortions, inappropriate coding techniques and/or bad networkquality, the video quality may be deteriorated making object/event detection verydifficult. A main challenging issue of intelligent video surveillance is to improveQuality-of-Experience of the system. In fact, three major factors are involved inthe global quality of a video surveillance system which are: the captured videoquality, the video coding and the quality-of-service of the network. To this end,it is primordial to assess the video quality in order to decide whether or notan enhancement is needed. On the other hand, the network architecture mustfulfil the video surveillance requirements and respects its specificities in order toguarantee a good quality of service.In this thesis, we focus our interest on video surveillance system’s quality.Our objective is to study the quality aspect in new emergent intelligent videosurveillance systems. The principal contributions of this thesis are threefold.First, we propose a new stereoscopic image coding techniques based on sparseoptimization of non separable vector lifting scheme. In fact, this stereoscopiccoding technique can be extended to the context of multiview coding and may offerbest coding performance for 3D video surveillance systems. Then, we introduce anew quality-based intelligent video surveillance architecture based on video qualityassessment. A video surveillance oriented video quality database is proposed within this architecture. Finally, a scheduling model based on priority of trafficsfor multimedia sensors is proposed. The results of this thesis underline theimportance of our contributions in the field of intelligent video surveillance. Thiswork does not claim to have completely resolved the problems raised in thisthesis. It constitutes a modest first contribution by having explored and analysedthe most crucial problems. Nevertheless, it has the merit of having thoroughlyanalyzed the problems raised by the SV and of having proposed some solutionsthat remain to be improved in the context of future work. Finally, the provisionto the scientific community of a high-resolution video database, unique to ourknowledge, presenting different scenarios, is a considerable contribution
Towards efficient methods for stereo image processing, coding and quality assessment
No full textLes récents développements des technologies de l’imagerie 3D et en particulier la stéréoscopie ont ouvert de nouveaux horizons dans de nombreux domaines d’application tels que la TV 3D, le cinéma 3D, les jeux vidéo et la vidéoconférence. Ces avancées technologiques ont soulevé plusieurs défis aussi bien sur le plan théorique que pratique et en particulier dans le domaine du codage des données 3D. En effet, l’énorme quantité d’information issue des systèmes d’acquisition requiert des solutions efficaces pour la coder et la transmettre. L’objectif de cette thèse est le développement de méthodes pour optimiser les principales étapes de la chaine de traitement et transmission d’images stéréoscopiques. Nous nous limitons dans ce travail au rehaussement de contraste, le codage et l’évaluation de la qualité d’images stéréoscopiques. La première partie de ce travail traite les problèmes d’évaluation et d’amélioration de la qualité d’images stéréoscopiques. Nous nous intéressons d’abord au rehaussement de contraste en s’inspirant des méthodes 2D et en intégrant quelques éléments liés à la perception visuelle. Nous proposons ainsi une première méthode de rehaussement de contraste local basée sur la carte de saillance visuelle. L’aspect qualité est aussi traité selon une approche basée sur les protocoles et méthodes conues pour le cas des images 2D et 3D. Cette méthode exploite les caractéristiques et propriétés connues du système visuel humain (SVH) telles que la non-linéarité, la sensibilité au contraste, la sélectivité directionnelle et fréquentielle ainsi que le seuil de discrimination binoculaire. Nous avons aussi d´eveloppé une méthode de prédiction de la qualité d’images stéréoscopiques sans référence. Cette dernière est basée sur des descripteurs 3D statistiques issus de la scène naturelle afin identifier les distorsions. Ces descripteurs 3D statistiques correspondent aux attributs extraits à partir de la paire stéréo naturelle et de la carte de disparité. L’extraction de ces descripteurs se fait au moyen de l’analyse en ondelettes des images stéréoscopiques. La deuxième partie de cette thèse traite les problèmes de compression d’images stéréoscopiques. Nous avons commencé par l’exploitation de la transformée en cosinus discret unidirectionnel et unidimensionnel pour encoder l’image résiduelle issue de la compensation de disparité. Ensuite, en se basant sur la transformée en ondelettes, nous avons étudié deux techniques pour optimiser le calcul de l’image résiduelle. Enfin, nous avons proposé des méthodes d’allocation de débit pour la compression des images stéréoscopiques. En général, le problème d’allocation de bits est résolu d’une manière empirique en cherchant le débit optimale qui minimise une certaine distorsion. Cependant cette stratégie est complexe. Pour cela, nous avons proposé des méthodes d’allocation de débits, rapides et efficaces appropriées pour le codage en boucle ouverte et en boucle fermée. Cette thèse ouvre des perspectives dans les trois thématiques abordées, à savoir le rehaussement de contraste, le codage et l’évaluation de la qualité d’images stéréoscopiques.Recent developments in 3D stereoscopic technology have opened new horizons in many application fields such as 3DTV, 3D cinema, video games and videoconferencing and at the same time raised a number of challenges related to the processing and coding of 3D data. Today, stereoscopic imaging technology is becoming widely used in many fields. There are still some problems related to the physical limitations of image acquisition systems, e.g. transmission and storage requirements. The objective of this thesis is the development of methods for improving the main steps of stereoscopic imaging pipeline such as enhancement, coding and quality assessment. The first part of this work addresses quality issues including contrast enhancement and quality assessment of stereoscopic images. Three algorithms have been proposed. The first algorithm deals with the contrast enhancement aiming at promoting the local contrast guided by calculated/estimated object importance map in the visual scene. The second and the third algorithms aim at predicting the distortion severity of stereo images. In the second one, we have proposed a fullreference metric that requires the reference image and is based on some 2D and 3D findings such as amplitude non-linearity, contrast sensitivity, frequency and directional selectivity, and binocular just noticeable difference model. While in the third algorithm, we have proposed a no-reference metric which needs only the stereo pair to predict its quality. The latter is based on Natural Scene statistics to identify the distortion affecting the stereo image. The statistic 3D features consist in combining features extracted from the natural stereo pair and those from the estimate disparity map. To this end, a joint wavelet transform, inspired from the vector lifting concept is first employed. Then, the features are extracted from the obtained subbands. The second part of this dissertation addresses stereoscopic image compression issues. We started by investigating a one-dimensional directional discrete cosine transform to encode the disparity compensated residual image. Afterwards, and based on the wavelet transform, we investigated two techniques for optimizing the computation of the residual image. Finally, we present efficient bit allocation methods for stereo image coding purpose. Generally, the bit allocation problem is solved in an empirical manner by looking for the optimal rates leading to the minimum distortion value. Thanks to recently published work on approximations of the entropy and distortion functions, we proposed accurate and fast bit allocation schemes appropriate for the open-loop and closed-loop based stereo coding structures
- …
