No description available.

L’objectif de cette thèse est de trouver de nouvelles méthodes de compression sémantique compatible avec un encodeur classique tel que H.264/AVC. . L’objectif principal est de maintenir la sémantique et non pas la qualité globale. Un débit cible de 300 kb/s a été fixé pour des applications de sécurité et de défense Pour cela une chaine complète de compression a dû être réalisée. Une étude et des contributions sur les modèles de saillance spatio-temporel ont été réalisées avec pour objectif d’extraire l’information pertinente. Pour réduire le débit, une méthode de redimensionnement dénommée «seam carving » a été combinée à un encodeur H.264/AVC. En outre, une métrique combinant les points SIFT et le SSIM a été réalisée afin de mesurer la qualité des objets sans être perturbée par les zones de moindre contenant la majorité des artefacts. Une base de données pouvant être utilisée pour des modèles de saillance mais aussi pour de la compression est proposée avec des masques binaires. Les différentes approches ont été validées par divers tests. Une extension de ces travaux pour des applications de résumé vidéo est proposée. / The objective of this thesis is to find new methods for semantic video compatible with a traditional encoder like H.264/AVC. The main objective is to maintain the semantic and not the global quality. A target bitrate of 300 Kb/s has been fixed for defense and security applications. To do that, a complete chain of compression has been proposed. A study and new contributions on a spatio-temporal saliency model have been done to extract the important information in the scene. To reduce the bitrate, a resizing method named seam carving has been combined with the H.264/AVC encoder. Also, a metric combining SIFT points and SSIM has been created to measure the quality of objects without being disturbed by less important areas containing mostly artifacts. A database that can be used for testing the saliency model but also for video compression has been proposed, containing sequences with their manually extracted binary masks. All the different approaches have been thoroughly validated by different tests. An extension of this work on video summary application has also been proposed.

We propose a method of adaptive image denoising using a support vector machine (SVM) classifier to select between multiple well-performing contemporary denoising algorithms for each pixel of a noisy image. We begin by proposing a simple method for realistically generating noisy images, and also describe a number of novel and pre-existing features based on seam energy, local colour, and saliency which are used as classifier inputs. Our SVM strategic image denoising (SVMSID) results demonstrate better image quality than either candidate denoising algorithm for images of moderate noise level, as measured using the perceptually-based quaternion structural similarity image metric (QSSIM). We also demonstrate a modified training point selection method to improve robustness across many noise levels, and propose various extensions to SVMSID for further exploration. / Thesis / Master of Applied Science (MASc)

As the fidelity of computer generated imagery has increased, the need to digitally create convincing natural phenomena like fluids has become fundamental to the entertainment production industry. Because fluids are complex, the underlying physics must be computationally simulated. However, because a strictly physics-based approach is both computationally expensive and difficult to control, it does not lend itself well to the way artists and directors like to work. Directors require control to achieve their specific artistic vision. Furthermore, artistic workflows rely on quick iteration and the ability to apply changes late in the production process. In this dissertation we present novel techniques in adaptive simulation and fluid post-processing to improve artistic workflows for fluid simulation. Our methods reduce fluid simulation iteration time and provide a new way for artists to intelligently resize a wide range of volumetric data including fluid simulations. To reduce iteration time, we present a more cache-friendly linear octree structure for adaptive fluid simulation that reduces the overhead of previous octree-based methods. To increase the viability of reusable effects libraries, and to give artists intuitive control over simulations late in the production process we present a ``fluid carving" technique. Fluid carving uses seam carving methods to allow intelligent resizing on a variety of fluid phenomena without the need for costly re-simulation. We present methods that improve upon traditional seam carving approaches to address issues with scalability, non-rectangular boundaries, and that generalize to a variety of different visual effects data like particles, polygonal meshes, liquids, smoke, and fire. We achieve these improvements by guiding seams along user-defined lattices that can enclose regions of interest defined as OpenVDB grids with a wide range of shapes. These techniques significantly improve artist workflows for fluid simulation and allow visual entertainment to be produced in a more intuitive, cost-effective manner.

<p>The purpose of this master thesis was to study different content-aware video retargeting techniques, concentrating on a generalization of seam carving for video. Focus have also been put on the possibility to combine different techniques to achieve better retargeting of both multi-shot video and single-shot video. This also involved significant studies of automatic cut detection and different measures of video content. The work resulted in a prototype application for semi-automatic video retargeting, developed in Matlab. Three different retargeting techniques, seam carving, automated pan & scan and subsampling using bi-cubic interpolation, have been implemented in the prototype. The techniques have been evaluated and compared to each other from a content preservation perspective and a perceived quality perspective.</p> / <p>Syftet med examensarbetet har varit att studera tekniker för ändring av bredd/höjd-förhållandet i videosekvenser, där hänsyn tas till innehållet i bilderna. Fokus har lagts på en generalisering av "seam carving" för video och möjligheterna att kombinera olika tekniker för att nå bättre kvalitet både för videosekvenser som består av endast ett, eller flera, klipp. Detta innefattade således också omfattande studier av automatisk klippdetektering och olika mått av videoinnehåll. Arbetet har resulterat i en prototypapplikation utvecklad i Matlab för halvautomatisk förändring av bildförhållande där hänsyn tas till innehållet i sekvenserna. I prototypen finns tre metoder implementerade, "seam carving", automatiserad "pan & scan" och nedsampling med bi-kubisk interpolering. Dessa metoder har utvärderats och jämförts med varandra från ett innehållsbevarande perspektiv och ett kvalitetsperspektiv.</p>

The purpose of this master thesis was to study different content-aware video retargeting techniques, concentrating on a generalization of seam carving for video. Focus have also been put on the possibility to combine different techniques to achieve better retargeting of both multi-shot video and single-shot video. This also involved significant studies of automatic cut detection and different measures of video content. The work resulted in a prototype application for semi-automatic video retargeting, developed in Matlab. Three different retargeting techniques, seam carving, automated pan &amp; scan and subsampling using bi-cubic interpolation, have been implemented in the prototype. The techniques have been evaluated and compared to each other from a content preservation perspective and a perceived quality perspective. / Syftet med examensarbetet har varit att studera tekniker för ändring av bredd/höjd-förhållandet i videosekvenser, där hänsyn tas till innehållet i bilderna. Fokus har lagts på en generalisering av "seam carving" för video och möjligheterna att kombinera olika tekniker för att nå bättre kvalitet både för videosekvenser som består av endast ett, eller flera, klipp. Detta innefattade således också omfattande studier av automatisk klippdetektering och olika mått av videoinnehåll. Arbetet har resulterat i en prototypapplikation utvecklad i Matlab för halvautomatisk förändring av bildförhållande där hänsyn tas till innehållet i sekvenserna. I prototypen finns tre metoder implementerade, "seam carving", automatiserad "pan &amp; scan" och nedsampling med bi-kubisk interpolering. Dessa metoder har utvärderats och jämförts med varandra från ett innehållsbevarande perspektiv och ett kvalitetsperspektiv.