With the development of the MPEG4, the concept of video object plane (VOP) is more and more important. Before the MPEG4 video coding, it requires a prior process to decompose the video sequences into several video segmented object planes. As moving objects cause local intensities changes, these changes provide the most important information of the segmentation. Whereas the camera motion also changes intensities, we have to remove the changes caused by camera moving. The experimentation is using a fixed and single global lens CCD to detect the objects which are not belong to the environment. When global lens CCD finds the objects, the system will pass the objects information to PTZ lens CCD, which is able to capture the better image of the objects. When PTZ lens CCD is tracing objects, CCD`s moving causes global motion between frames. As extracting the objects in these frames, we use an efficient affine model to remove the image intensities changes caused by PTZ lens camera moving. After motion compensation, find the changes due to moving objects, and select the region of the objects. On purpose to find the precise contours of the objects, we use SRG algorithm to erode the background inside the objects region, and finally extract the objects. In the last step, we return back the image of the PTZ lens CCD with global lens CCD`s background and the extracted objects. By this method, we are able to reduce the redundancy and lower the data translation bit rate.

This thesis focuses on the design of a foveated stereo video compression algorithm for visual telepresence applications. In a typical telepresence application, a user at the local site views real-time stereo video recorded and transmitted from a robotic camera platform located at a remote site. The robotic camera platform tracks the user's head motion producing the sensation of being present at the remote site. The design of the stereo video compression algorithm revolved around a fast spatio-temporal block-based motion estimation algorithm, with a foveated SPIHT algorithm used to compress and foveate the independent frames and error residues. Also, the redundancy between the left and right video streams was exploited by disparity compensation. Finally, position feedback from the robotic camera platform was used to perform global motion compensation, increasing the compression performance without raising computation requirements. The algorithm was analysed by introducing the above mentioned components separately. It was found that each component increased the compression rate significantly, producing compressed video with similar compression and quality as MPEG2. The implementation of the algorithm did not meet the real-time requirements on the experiment computers. However, the algorithm does not contain any intrinsic delays. Therefore, given faster processors or optimized software implementation, the design should be able to run in real-time.

This thesis focuses on the design of a foveated stereo video compression algorithm for visual telepresence applications. In a typical telepresence application, a user at the local site views real-time stereo video recorded and transmitted from a robotic camera platform located at a remote site. The robotic camera platform tracks the user's head motion producing the sensation of being present at the remote site. The design of the stereo video compression algorithm revolved around a fast spatio-temporal block-based motion estimation algorithm, with a foveated SPIHT algorithm used to compress and foveate the independent frames and error residues. Also, the redundancy between the left and right video streams was exploited by disparity compensation. Finally, position feedback from the robotic camera platform was used to perform global motion compensation, increasing the compression performance without raising computation requirements. The algorithm was analysed by introducing the above mentioned components separately. It was found that each component increased the compression rate significantly, producing compressed video with similar compression and quality as MPEG2. The implementation of the algorithm did not meet the real-time requirements on the experiment computers. However, the algorithm does not contain any intrinsic delays. Therefore, given faster processors or optimized software implementation, the design should be able to run in real-time.

In this thesis, we proposed the series methods of moving object segmentation and object application. These methods are the moving object segmentation method in wavelet domain, double change detection method, global motion estimation method, and the moving object segmentation in the motion background. First, we proposed the Video Object Segmentation Method in Wavelet Domain. We use the Change Detection Method with the different thresholds in four wavelet sub-bands. The experiment results show that we obtain further object shape information and more accurately extracting the moving object. In the double change detection method, we proposed the method for moving object segmentation using three successive frames. We use change detection method twice in wavelet domain. After applying the Intersect Operation, we obtain the accurately moving object edge map and further object shape information. Besides, we proposed the global motion estimation method in motion scene. We propose a novel global motion estimation using cross point for the reconstruction of background scene in video sequences. Due to the robust character and limit number of cross points, we can get the Affine parameters of global motion in video sequences efficiency. At last, we proposed the object segmentation method in motion scene. We use the motion estimation method to estimate the global motion between the consecutive frames. We reconstruct a wide scene background without moving objects by the consecutive frames. At last, the moving objects will be segmented easily by comparing the object frame and the relative part in wide scene background. The Results of our proposed have good performance in the different type of video sequences. Hence, the methods of our thesis contribute to the video coding in Mpeg-4 and multimedia technology.

Object trajectory tracking is an important topic in many different areas. It is widely used in robot technology, traffic, movie industry, and others. Optical flow is a useful method in the object tracking branch and it can calculate the motion of each pixel between two frames, and thus it provides a possible way to get the trajectory of objects. There are numerous papers describing the implementation of optical flow. Some results are acceptable, but in many projects, there are limitations. In most previous applications, because the camera is usually static, it is easy to apply optical flow to identify the moving targets in a scene and get their trajectories. When the camera moves, a global motion will be added to the local motion, which complicates the issue. In this thesis we use a combination of optical flow and image correlation to deal with this problem, and have good experimental results. For trajectory estimation, we incorporate a Kalman Filter with the optical flow. Not only can we smooth the motion history, but we can also estimate the motion into the next frame. The addition of a spatial-temporal filter improves the results in our later process.

Two very different classes of theoretical models have been proposed to explain visual perception. One class of models assume that there is a point at which we become consciously aware of a stimulus, known as a threshold. This threshold is the foundation of discrete process models all of which describe an all-or-none transition between the mental state of perceiving a stimulus and the state of not perceiving a stimulus. In contrast, the other class of models assume that mental states change continuously. These continuous models are founded in signal detection theory and the more contemporary models in Bayesian inference frameworks. The continuous model is the more widely accepted model of perception, and as such discrete process models were mostly discarded. Nonetheless, there has been a renewed debate on continuous versus discrete perception, and recent work has renewed the idea that perception can be all-or-none. In this dissertation, we developed an experimental platform and modeling framework to test whether visual perception exhibits measurable characteristics consistent with discrete perception. The results of this study revealed a selective influence of stimulus type on the way that a visual stimulus is processed. Moreover this selective influence implied perception can either be discrete or continuous depending on the underlying perceptual processing. These qualitative differences in the way perception occurs even for highly similar stimuli such as motion or orientation have crucial implications for models of perception, as well as our understanding of neurophysiology and conscious perception.

Este trabalho propõe um novo enfoque em visão computacional aplicado a sequências de vídeo, de pessoas em movimento, para reconhecê-las por meio da marcha. O movimento humano carrega diferentes informações, considerando-se diferentes maneiras de analisá-lo. O esqueleto carrega as informações do movimento global de articulações do corpo humano e como se comportam durante a caminhada e a silhueta carreia informações referentes ao comportamento global do contorno do corpo humano. Além disso, imagens binárias e em escala de cinza possuem diferentes informações sobre o movimento humano. O método proposto considera o conjunto de frames segmentados de cada indivíduo como uma classe e cada frame como um objeto desta classe. A metodologia aplica o Modelo de Mistura de Gaussianas (GMM) para subtração de fundo, redução de escala realizada por meio de técnicas de multiresolução baseadas na Transformada Wavelet (TW) e a extração dos padrões por meio da Análise dos Componentes Principais (PCA). São propostos e ensaiados quatro novos modelos de captura de movimentos globais do corpo humano durante a marcha: o modelo Silhouette-Gray-Wavelet (SGW) captura o movimento baseado nas variações em nível de cinza; o modelo Silhouette-Binary-Wavelet (SBW) captura o movimento baseado nas informações binárias da silhueta; o modelo Silhouette-Edge-Wavelet (SEW) captura o movimento baseado nas informações contidas na borda das silhuetas e o modelo Silhouette-Skeleton-Wavelet (SSW) captura o movimento baseado do esqueleto humano. As taxas de classificações corretas obtidas separadamente a partir destes quatro diferentes modelos são então combinadas utilizando-se uma nova técnica de fusão. Os resultados demonstram excelente desempenho e mostraram a viabilidade para reconhecimento de pessoas. / This paper proposes a novel computer vision approach that processes video sequences of people walking and then recognises those people by their gait. Human motion carries different information that can be analysed in various ways. The skeleton carries motion information about human joints, and the silhouette carries information about boundary motion of the human body. Moreover, binary and gray-level images contain different information about human movements. Our proposed method considers the set of the segmented frames of each individual as a distinct class and each frame as an object of this class. The methodology applies background extraction using the Gaussian Mixture Model (GMM), a scale reduction based on the Wavelet Transform (WT) and feature extraction by Principal Component Analysis (PCA). We propose four new schemas for motion information capture: the Silhouette-Gray-Wavelet model (SGW) captures motion based on grey level variations; the Silhouette-Binary-Wavelet model (SBW) captures motion based on binary information; the Silhouette-Edge-Binary model (SEW) captures motion based on edge information and the Silhouette-Skeleton-Wavelet model (SSW) captures motion based on skeleton movement. The classification rates obtained separately from these four different models are then merged using a new proposed fusion technique. The results suggest excellent performance in terms of recognising people by their gait.

Este trabalho propõe um novo enfoque em visão computacional aplicado a sequências de vídeo, de pessoas em movimento, para reconhecê-las por meio da marcha. O movimento humano carrega diferentes informações, considerando-se diferentes maneiras de analisá-lo. O esqueleto carrega as informações do movimento global de articulações do corpo humano e como se comportam durante a caminhada e a silhueta carreia informações referentes ao comportamento global do contorno do corpo humano. Além disso, imagens binárias e em escala de cinza possuem diferentes informações sobre o movimento humano. O método proposto considera o conjunto de frames segmentados de cada indivíduo como uma classe e cada frame como um objeto desta classe. A metodologia aplica o Modelo de Mistura de Gaussianas (GMM) para subtração de fundo, redução de escala realizada por meio de técnicas de multiresolução baseadas na Transformada Wavelet (TW) e a extração dos padrões por meio da Análise dos Componentes Principais (PCA). São propostos e ensaiados quatro novos modelos de captura de movimentos globais do corpo humano durante a marcha: o modelo Silhouette-Gray-Wavelet (SGW) captura o movimento baseado nas variações em nível de cinza; o modelo Silhouette-Binary-Wavelet (SBW) captura o movimento baseado nas informações binárias da silhueta; o modelo Silhouette-Edge-Wavelet (SEW) captura o movimento baseado nas informações contidas na borda das silhuetas e o modelo Silhouette-Skeleton-Wavelet (SSW) captura o movimento baseado do esqueleto humano. As taxas de classificações corretas obtidas separadamente a partir destes quatro diferentes modelos são então combinadas utilizando-se uma nova técnica de fusão. Os resultados demonstram excelente desempenho e mostraram a viabilidade para reconhecimento de pessoas. / This paper proposes a novel computer vision approach that processes video sequences of people walking and then recognises those people by their gait. Human motion carries different information that can be analysed in various ways. The skeleton carries motion information about human joints, and the silhouette carries information about boundary motion of the human body. Moreover, binary and gray-level images contain different information about human movements. Our proposed method considers the set of the segmented frames of each individual as a distinct class and each frame as an object of this class. The methodology applies background extraction using the Gaussian Mixture Model (GMM), a scale reduction based on the Wavelet Transform (WT) and feature extraction by Principal Component Analysis (PCA). We propose four new schemas for motion information capture: the Silhouette-Gray-Wavelet model (SGW) captures motion based on grey level variations; the Silhouette-Binary-Wavelet model (SBW) captures motion based on binary information; the Silhouette-Edge-Binary model (SEW) captures motion based on edge information and the Silhouette-Skeleton-Wavelet model (SSW) captures motion based on skeleton movement. The classification rates obtained separately from these four different models are then merged using a new proposed fusion technique. The results suggest excellent performance in terms of recognising people by their gait.

「動跡剪輯」是將多個不同內容的影片片段，根據影片中特定物體移動的關係，剪接成新的影片，使得產生的新影片能維持動作連貫及流暢的特性。本論文提出一套方法能夠自動找尋不同影片間相似的剪輯點，作為「動跡剪輯」的參考。此方法之重點在於建立影片的時空資訊，作為找尋剪輯點的依據。建立影片時空資訊的過程中，我們先將影片依偵測出的鏡頭轉換點分割成不同的影片片段，再將影片片段中前景物件的位置、大小與動作等資訊分離而成影片物件平面，並結合影片片段中的背景動作資訊與影片物件平面資訊，成為該影片片段之時空資訊，從而進行剪輯點之找尋與比對，擇其最佳點進行剪輯。 運用影片時空資訊於找尋影片間之剪輯點時，是以影片物件平面作為搜尋單位，此方式有助於提升結果的正確性，同時也提供了搜尋時的靈活度。 / With the rapid increasing of the multimedia applications in modern commercial and movie business, it becomes more desirable to have efficient video editing tools. However, conventional video editing requires too many manual interventions that reduce productivities as well as opportunities in better performance. In this thesis, we propose a MOtion-based Video Editing (MOVE) mechanism that can automatically select the most similar or suitable transition points from a given set of raw videos. A given video can be divided into a set of video clips using a shot detection algorithm. For each video clip, we provide an algorithm that can separate the global motions as well as the local motions using the principles of video object plane and accumulated difference. We introduce the concept of spatio-temporal information, a condensed information that associated with a video clip. We can use this information in finding a good video editing point. Since the spatio-temporal information is a concise representation of a video clip, searching in this domain will reduce the complexity of the problem and achieve better performance. We implemented our mechanism with successful experiments.

No description available.