Le cadre général de cette étude est le traitement numérique du signal, appliqué<br />aux séquences d'images, pour des applications multimédia. Ce travail est<br />divisé en deux contributions principales~: un algorithme de segmentation<br />d'images en objets vidéo en mouvement, et une méthode d'interpolation<br />temporelle opérant sur ces objets.<br /><br />La segmentation de la séquence est effectuée par un algorithme de suivi<br />temporel. Un algorithme de segmentation spatio-temporelle est utilisé<br />initialement pour obtenir des régions dans la première image de la séquence.<br />Cette partition est ensuite suivie par une technique de contours actifs, qui<br />opère sur une nouvelle représentation de la segmentation, composée des<br />frontières ouvertes séparant les régions. L'algorithme estime à la fois le<br />mouvement des frontières et celui des régions. Il est capable de suivre<br />plusieurs objets simultanément et de traiter les occultations entre eux. Des<br />résultats, obtenus sur des séquences d'images réelles, montrent que cet<br />algorithme permet une bonne stabilité temporelle de la segmentation et une<br />bonne précision des frontières.<br /><br />Le but de l'algorithme d'interpolation est de reconstruire des images<br />intermédiaires entre deux images de la séquence. Il s'agit d'un algorithme de<br />faible complexité qui peut être utilisé à la fin d'une chaîne codeur/décodeur.<br />L'interpolation est compensée en mouvement et utilise le mouvement des régions,<br />estimé pendant la phase de suivi. Il est aussi basé objets, dans le sens où il<br />utilise la segmentation pour prédire correctement les zones d'occultation. Cet<br />algorithme peut être utilisé pour trois applications différentes~: le codage<br />interpolatif (où des images de la séquence sont prédites par interpolation),<br />l'adaptation de la fréquence de la séquence à la fréquence d'affichage du<br />terminal de visualisation dans une transmission multipoints et la<br />reconstruction d'images manquantes (où l'on calcule des images non observées).<br />Des résultats expérimentaux pour la première application montrent que pour une<br />qualité de reconstruction donnée, la taux de compression moyen sur un groupe<br />d'images est plus élevé en utilisant l'interpolation qu'avec une prédiction<br />causale.

<p>With the advance in computer and network technologies, multimedia systems and Internet applications are becoming more popular. As broadband network is prevailing, more clients are able to watch streaming videos or to play multimedia data over the Internet in real-time. Consequently, there is an increasing demand in the Internet for streaming video systems. As the run-time environment of such applications tends to be dynamic, it is imperative to handle transient overloads effectively. The goal of this work is to develop an algorithm that would provide a robust and controlled behavior of the video system so that important data is delivered on time to the video clients. In order to address this problem, we propose a QoS-sensitive approach that is using the technique of imprecise computation and is based on the principle of tuning. Our algorithm is aimed to provide the best possible QoS to the clients in the current available network capacity. As an environment to work with we have used a video system called QMPEGv2. A set of experiments were carried out to evaluate the performance of the algorithm. Through experiments, we show that the system can adapt to dynamic changes in network conditions and provide almost always the best possible QoS to its clients. Guaranteeing a certain minimal QoS level to all clients is only possible when, in run time, an admission controller adjusts the number of clients admitted tothe system according to the capacity of the network and video servers.</p>

<p>H.264, also known as MPEG-4 Part 10: Advanced Video Coding, is the latest MPEG standard for video coding. It provides approximately 50% bit rate savings for equivalent perceptual quality compared to any previous standard. In the same fashion as previous MPEG standards, only the bitstream syntax and the decoder are specified. Hence, coding performance is not only determined by the standard itself but also by the implementation of the encoder. In this report we propose two methods for improving the coding performance while remaining fully compliant to the standard. </p><p>After transformation and quantization, the transform coefficients are usually entropy coded and embedded in the bitstream. However, some of them might be beneficial to discard if the number of saved bits are sufficiently large. This is usually referred to as coefficient thresholding and is investigated in the scope of H.264 in this report. </p><p>Lagrangian optimization for video compression has proven to yield substantial improvements in perceived quality and the H.264 Reference Software has been designed around this concept. When performing Lagrangian optimization, lambda is a crucial parameter that determines the tradeoff between rate and distortion. We propose a new method to select lambda and the quantization parameter for non-reference frames in H.264. </p><p>The two methods are shown to achieve significant improvements. When combined, they reduce the bitrate around 12%, while preserving the video quality in terms of average PSNR. </p><p>To aid development of H.264, a software tool has been created to visualize the coding process and present statistics. This tool is capable of displaying information such as bit distribution, motion vectors, predicted pictures and motion compensated block sizes.</p>

<p>ITU - T and the Moving Picture Expert Group (MPEG) have jointly, under the name of Joint Video Team (JVT), developed a new video coding standard. The standard is called H.264 and is also known as Advanced Video Coding (AVC) or MPEG-4 part 10. Comparisons shows that H.264 greatly outperforms MPEG-2, currently used in DVD and digital TV. H.264 halves the bit rate with equal image quality. The great rate - distortion performance means nevertheless a high computational complexity. Especially on the encoder side.</p><p>Handling of audio and video, e.g. compressing and filtering, is quite complex and requires high performance hardware and software. A video encoder consists of a number of modules that find the best coding parameters. For each macroblock several $modes$ are evaluated in order to achieve optimal coding. The reference implementation of H.264 uses a brute force search for this mode selection which is extremely computational constraining. In order to perform video encoding with satisfactory speed there is an obvious need for reducing the amount of modes that are evaluated.</p><p>This thesis proposes an algorithm which reduces the number of modes and reference frames that are evaluated. The algorithm can be regulated in order to fulfill the demand on quality versus speed. Six times faster encoding can be obtained without loosing perceptual image quality. By allowing some quality degradation the encoding becomes up to 20 times faster.</p>

<p>In this thesis we present a system to extract the eye motion from a video stream containing a human face and applying this eye motion into a virtual character. By the notation eye motion estimation, we mean the information which describes the location of the eyes in each frame of the video stream. Applying this eye motion estimation into a virtual character, we achieve that the virtual face moves the eyes in the same way than the human face, synthesizing eye motion into a virtual character. In this study, a system capable of face tracking, eye detection and extraction, and finally iris position extraction using video stream containing a human face has been developed. Once an image containing a human face is extracted from the current frame of the video stream, the detection and extraction of the eyes is applied. The detection and extraction of the eyes is based on edge detection. Then the iris center is determined applying different image preprocessing and region segmentation using edge features on the eye picture extracted.</p><p>Once, we have extracted the eye motion, using MPEG-4 Facial Animation, this motion is translated into the Facial Animation arameters (FAPs). Thus we can improve the quality and quantity of Facial Animation expressions that we can synthesize into a virtual character.</p>

No description available.

The use of computer animated interactive faces in film, TV, games is ever growing, with new application areas emerging also on the Internet and mobile environments. Morph targets are one of the most popular methods to animate the face. Up until now 3D artists had to design each morph target defined by the MPEG-4 standard by hand. This is a very monotonous and tedious task. With the newly developed method of Facial Motion Cloning [11]the heavy work is relieved from the artists. From an already animated face model the morph targets can now be copied onto a new static face model. For the Facial Motion Cloning process there must be a subset of the feature points specified by the MPEG-4 standard defined. The purpose of this is to correlate the facial features of the two faces. The goal of this project is to develop a graphical editor in which the artists can define the feature points for a face model. The feature points will be saved in a file format that can be used in a Facial Motion Cloning software.

H.264, also known as MPEG-4 Part 10: Advanced Video Coding, is the latest MPEG standard for video coding. It provides approximately 50% bit rate savings for equivalent perceptual quality compared to any previous standard. In the same fashion as previous MPEG standards, only the bitstream syntax and the decoder are specified. Hence, coding performance is not only determined by the standard itself but also by the implementation of the encoder. In this report we propose two methods for improving the coding performance while remaining fully compliant to the standard. After transformation and quantization, the transform coefficients are usually entropy coded and embedded in the bitstream. However, some of them might be beneficial to discard if the number of saved bits are sufficiently large. This is usually referred to as coefficient thresholding and is investigated in the scope of H.264 in this report. Lagrangian optimization for video compression has proven to yield substantial improvements in perceived quality and the H.264 Reference Software has been designed around this concept. When performing Lagrangian optimization, lambda is a crucial parameter that determines the tradeoff between rate and distortion. We propose a new method to select lambda and the quantization parameter for non-reference frames in H.264. The two methods are shown to achieve significant improvements. When combined, they reduce the bitrate around 12%, while preserving the video quality in terms of average PSNR. To aid development of H.264, a software tool has been created to visualize the coding process and present statistics. This tool is capable of displaying information such as bit distribution, motion vectors, predicted pictures and motion compensated block sizes.

ITU - T and the Moving Picture Expert Group (MPEG) have jointly, under the name of Joint Video Team (JVT), developed a new video coding standard. The standard is called H.264 and is also known as Advanced Video Coding (AVC) or MPEG-4 part 10. Comparisons shows that H.264 greatly outperforms MPEG-2, currently used in DVD and digital TV. H.264 halves the bit rate with equal image quality. The great rate - distortion performance means nevertheless a high computational complexity. Especially on the encoder side. Handling of audio and video, e.g. compressing and filtering, is quite complex and requires high performance hardware and software. A video encoder consists of a number of modules that find the best coding parameters. For each macroblock several $modes$ are evaluated in order to achieve optimal coding. The reference implementation of H.264 uses a brute force search for this mode selection which is extremely computational constraining. In order to perform video encoding with satisfactory speed there is an obvious need for reducing the amount of modes that are evaluated. This thesis proposes an algorithm which reduces the number of modes and reference frames that are evaluated. The algorithm can be regulated in order to fulfill the demand on quality versus speed. Six times faster encoding can be obtained without loosing perceptual image quality. By allowing some quality degradation the encoding becomes up to 20 times faster.

Motion estimation and compensation plays an important role in video processing applications. Two-dimensional block-based and mesh-based models are widely used in this area. A 2-D mesh-based model provides a better representation of complex real world motion than a block-based model. Mesh-based motion estimation algorithms are employed in both frame-based and object-based video compression and coding. A hierarchical mesh-based algorithm is applied to improve the motion field generated by a single-layer algorithm. 2-D mesh-based models also enable the manipulation of video objects which is included in the MPEG-4 standard. A video object in a video clip can be replaced by another object by the use of a dynamic mesh structure. In this thesis, a comparative analysis of 2-D block-based and mesh-based motion estimation algorithms in both frame-based and object-based video representations is performed. The experimental results indicate that a mesh-based algorithm produces better motion compensation results than a block-based algorithm. Moreover, a two-layer mesh-based algorithm shows improvement over a one-layer mesh-based algorithm. The application of mesh-based motion estimation and compensation to video object replacement and animation is also performed.