The recent invasion of stereoscopic 3D television technologies is expected to be followed by autostereoscopic and holographic technologies. Glasses-free multiple stereoscopic pair displaying capabilities of these technologies will advance the 3D experience. The prospective 3D format to create the multiple views for such displays is Multiview Video plus Depth (MVD) format based on the Depth Image Based Rendering (DIBR) techniques. The depth modality of the MVD format is an active research area whose main objective is to develop DIBR friendly efficient compression methods. As a part this research, the thesis proposes novel 3D planar-based depth representations. The planar approximation of the stereo depth images is formulated as an energy-based co-segmentation problem by a Markov Random Field model. The energy terms of this problem are designed to mimic the rate-distortion tradeoff for a depth compression application. A heuristic algorithm is developed ...

In this thesis, a number of novel watermarking techniques for different 3D representations are presented. A novel watermarking method is proposed for the mono-view video, which might be interpreted as the basic implicit representation of 3D scenes. The proposed method solves the common flickering problem in the existing video watermarking schemes by means of adjusting the watermark strength with respect to temporal contrast thresholds of human visual system (HVS), which define the maximum invisible distortions in the temporal direction. The experimental results indicate that the proposed method gives better results in both objective and subjective measures, compared to some recognized methods in the literature. The watermarking techniques for the geometry and image based representations of 3D scenes, denoted as 3D watermarking, are examined and classified into three groups, as 3D-3D, 3D-2D and 2D-2D watermarking, in which the pair of symbols ...

Networked 3D virtual environments allow multiple users to interact with each other over the Internet. Users can share some sense of telepresence by remotely animating an avatar that represents them. However, avatar control may be tedious and still render user gestures poorly. This work aims at animating a user‟s avatar from real time 3D motion capture by monoscopic computer vision, thus allowing virtual telepresence to anyone using a personal computer with a webcam. The approach followed consists of registering a 3D articulated upper-body model to a video sequence. This involves searching iteratively for the best match between features extracted from the 3D model and from the image. A two-step registration process matches regions and then edges. The first contribution of this thesis is a method of allocating computing iterations under real-time constrain that achieves optimal robustness and accuracy. The major ...

The dissertation deals with the problems of stereoscopic depth estimation and coding in multiview video systems, which are vital for development of the next generation three-dimensional television. The depth estimation algorithms known from literature, along with theoretical foundations are discussed. The problem of estimation of depth maps with high quality, expressed by means of accuracy, precision and temporal consistency, has been stated. Next, original solutions have been proposed. Author has proposed a novel, theoretically founded approach to depth estimation which employs Maximum A posteriori Probability (MAP) rule for modeling of the cost function used in optimization algorithms. The proposal has been presented along with a method for estimation of parameters of such model. In order to attain that, an analysis of the noise existing in multiview video and a study of inter-view correlation of corresponding samples of pictures have been ...

This thesis presents a new representation called floating polygon soup for applications like 3DTV and FTV (Free Viewpoint Television). The polygon soup is designed for compactness, compression efficiency, and view synthesis quality. The polygons are stored in 2D, with depth values at each corner. They are not necessarily connected to each other and can be deformed (or floated) w.r.t viewpoints and time. Starting from multi-view video plus depth (MVD), the construction holds in two steps: quadtree decomposition and multi-view redundancy reduction. It results in a compact set of polygons replacing the depth maps while preserving depth discontinuities and geometric details. Next, compression efficiency and view-synthesis quality are evaluated. Classical meth- ods such as inpainting and post-processing are implemented and adapted to the poly- gon soup. A new compression method is proposed. It exploits the quadtree structure and uses spatial prediction. ...

This thesis discusses approaches and techniques to convert Sparsely-Sampled Light Fields (SSLFs) into Densely-Sampled Light Fields (DSLFs), which can be used for visualization on 3DTV and Virtual Reality (VR) devices. Exemplarily, a movable 1D large-scale light field acquisition system for capturing SSLFs in real-world environments is evaluated. This system consists of 24 sparsely placed RGB cameras and two Kinect V2 sensors. The real-world SSLF data captured with this setup can be leveraged to reconstruct real-world DSLFs. To this end, three challenging problems require to be solved for this system: (i) how to estimate the rigid transformation from the coordinate system of a Kinect V2 to the coordinate system of an RGB camera; (ii) how to register the two Kinect V2 sensors with a large displacement; (iii) how to reconstruct a DSLF from a SSLF with moderate and large disparity ranges. ...

In the world of Information and communications technology (ICT), strategies for innovation and development are increasingly focusing on applications that require spatial representation and real-time interaction with and within 3D-media environments. One of the major challenges that such applications have to address is user-centricity, reflecting e.g. on developing complexity-hiding services so that people can personalize their own delivery of services. In these terms, multimodal interfaces represent a key factor for enabling an inclusive use of new technologies by everyone. In order to achieve this, multimodal realistic models that describe our environment are needed, and in particular models that accurately describe the acoustics of the environment and communication through the auditory modality are required. Examples of currently active research directions and application areas include 3DTV and future internet, 3D visual-sound scene coding, transmission and reconstruction and teleconferencing systems, to name but ...

Video signals are sequences of natural images, where images are often modeled as piecewise-smooth signals. Hence, video can be seen as a 3D piecewise-smooth signal made of piecewise-smooth regions that move through time. Based on the piecewise-smooth model and on related theoretical work on rate-distortion performance of wavelet and oracle based coding schemes, one can better analyze the appropriate coding strategies that adaptive video codecs need to implement in order to be efficient. Efficient video representations for coding purposes require the use of adaptive signal decompositions able to capture appropriately the structure and redundancy appearing in video signals. Adaptivity needs to be such that it allows for proper modeling of signals in order to represent these with the lowest possible coding cost. Video is a very structured signal with high geometric content. This includes temporal geometry (normally represented by motion ...

Dynamic textures are common in natural scenes. Examples of dynamic textures in video include fire, smoke, clouds, volatile organic compound (VOC) plumes in infra-red (IR) videos, trees in the wind, sea and ocean waves, etc. Researchers extensively studied 2-D textures and related problems in the fields of image processing and computer vision. On the other hand, there is very little research on dynamic texture detection in video. In this dissertation, signal and image processing methods developed for detection of a specific set of dynamic textures are presented. Signal and image processing methods are developed for the detection of flames and smoke in open and large spaces with a range of up to $30$m to the camera in visible-range (IR) video. Smoke is semi-transparent at the early stages of fire. Edges present in image frames with smoke start loosing their sharpness ...

An adaptive edge-enhanced correlation based robust and real-time visual tracking framework, and two machine vision systems based on the framework are proposed. The visual tracking algorithm can track any object of interest in a video acquired from a stationary or moving camera. It can handle the real-world problems, such as noise, clutter, occlusion, uneven illumination, varying appearance, orientation, scale, and velocity of the maneuvering object, and object fading and obscuration in low contrast video at various zoom levels. The proposed machine vision systems are an active camera tracking system and a vision based system for a UGV (unmanned ground vehicle) to handle a road intersection. The core of the proposed visual tracking framework is an Edge Enhanced Back-propagation neural-network Controlled Fast Normalized Correlation (EE-BCFNC), which makes the object localization stage efficient and robust to noise, object fading, obscuration, and uneven ...

Super-resolution (SR) is a filtering technique that combines a sequence of under-sampled and degraded low-resolution images to produce an image at a higher resolution. The reconstruction takes advantage of the additional spatio-temporal data available in the sequence of images portraying the same scene. The fundamental problem addressed in super-resolution is a typical example of an inverse problem, wherein multiple low-resolution (LR)images are used to solve for the original high-resolution (HR) image. Super-resolution has already proved useful in many practical cases where multiple frames of the same scene can be obtained, including medical applications, satellite imaging and astronomical observatories. The application of super resolution filtering in consumer cameras and mobile devices shall be possible in the future, especially that the computational and memory resources in these devices are increasing all the time. For that goal, several research problems need to be ...

The analysis of audiovisual data aims at extracting high level information, equivalent with the one(s) that can be extracted by a human. It is considered as a fundamental, unsolved (in its general form) problem. Even though the inverse problem, the audiovisual (sound and animation) synthesis, is judged easier than the previous, it remains an unsolved problem. The systematic research on these problems yields solutions that constitute the basis for a great number of continuously developing applications. In this thesis, we examine the two aforementioned fundamental problems. We propose algorithms and models of analysis and synthesis of articulated motion and undulatory (snake) locomotion, using data from video sequences. The goal of this research is the multilevel information extraction from video, like object tracking and activity recognition, and the 3-D animation synthesis in virtual environments based on the results of analysis. An ...

The thesis takes into account steganography and steganalysis in the pixel domain. The contribution of this thesis is threefold . From a steganalysis point of view we introduce a new steganalysis method called Amplitude of Local Extrema (ALE) which outperforms previously proposed pixel domain methods. As a second contribution we introduce a comparative methodology for the comparison of different steganalyzers and we apply it to compare ALE with the state-of-art steganalyzers. The third contribution of the thesis regards steganography, since we introduce a new embedding domain and a corresponding method, called MPSteg-color, which outperforms, in terms of undetectability, classical embedding methods as ±1 embedding.

Nowadays, richer 3D visual representation formats are emerging, notably light fields and point clouds. These formats enable new applications in many usage domains, notably virtual and augmented reality, geographical information systems, immersive communications, and cultural heritage. Recently, following major improvements in 3D visual data acquisition, there is an increasing interest in point-based visual representation, which models real-world objects as a cloud of sampled points on their surfaces. Point cloud is a 3D representation model where the real visual world is represented by a set of 3D coordinates (the geometry) over the objects with some additional attributes such as color and normals. With the advances in 3D acquisition systems, it is now possible to capture a realistic point cloud to represent a visual scene with a very high resolution. These point clouds may have up to billions of points and, thus, ...

Vision sensor networks and video cameras find widespread usage in several applications that rely on effective representation of scenes or analysis of 3D information. These systems usually acquire multiple images of the same 3D scene from different viewpoints or at different time instants. Therefore, these images are generally correlated through displacement of scene objects. Efficient compression techniques have to exploit this correlation in order to efficiently communicate the 3D scene information. Instead of joint encoding that requires communication between the cameras, in this thesis we concentrate on distributed representation, where the captured images are encoded independently, but decoded jointly to exploit the correlation between images. One of the most important and challenging tasks relies in estimation of the underlying correlation from the compressed correlated images for effective reconstruction or analysis in the joint decoder. This thesis focuses on developing efficient ...