In order to implement shape-based image retrieval in the wavelet domain effectively and efficiently, a new method is introduced to improve the moment-based shape descriptor. Firstly, several morphological operations a...
详细信息
In order to implement shape-based image retrieval in the wavelet domain effectively and efficiently, a new method is introduced to improve the moment-based shape descriptor. Firstly, several morphological operations are used to incorporate isolated significant points of a wavelet coefficient domain into a meaningful object region, which leads to a more accurate shape description. Then, by using the invariant properties of certain moments, a compact moment representation method is also proposed to integrate shape information spread at various directional wavelet subbands. Experimental results show that the proposed algorithm outperforms the existing shape-based image retrieval method in the wavelet domain.
The paper presents an advanced animation framework for virtual characters within the MPEG-4 standard. The bone-based animation (BBA) specifications are described and it is shown how they extend the MPEG-4 face and bod...
详细信息
The paper presents an advanced animation framework for virtual characters within the MPEG-4 standard. The bone-based animation (BBA) specifications are described and it is shown how they extend the MPEG-4 face and body animation (FBA) specifications. Specifically, the scene graph concept, the BBA nodes related to bone and muscle modeling, the animation parameters and the compression capabilities are successively addressed and discussed within a specific application related to a sign language communication system.
The MPEG-4 face and body animation (FBA) specifications aims at standardizing an interchange format for specifying virtual face and body modeling and related animation parameters. The scene graph concept, the FBA node...
详细信息
The MPEG-4 face and body animation (FBA) specifications aims at standardizing an interchange format for specifying virtual face and body modeling and related animation parameters. The scene graph concept, the FBA nodes, semantics and representation of the animation parameters as well as compression and streaming capabilities are successively addressed. The compatibility between virtual character animation techniques and MPEG-4 FBA is analyzed in terms of modeling, deformation behavior and animation capabilities.
It is generally agreed that video conferencing today is limited in its support of natural human-centered communication. Body postures and subtle movement, gaze direction, room acoustics, and joint object/data interact...
详细信息
It is generally agreed that video conferencing today is limited in its support of natural human-centered communication. Body postures and subtle movement, gaze direction, room acoustics, and joint object/data interactions are often misrepresented, lacking, or wholly absent within these systems. To obviate these shortcomings, a so-called immersive teleconferencing system is being developed at HHI within the German ITI project and in cooperation with the IST project VIRTUE. Following the principle of a shared table, it subtends a class of teleconferencing systems enabling conferees located in different geographical places to meet around a virtual table, appearing at each station in such a way as to create a convincing impression of presence. This system enables the participants to make use of rich communication modalities as similar as possible to those used in a face-to-face meeting (e.g., gestures, eye contact, realistic images, correct sound direction, etc.). The author presents the following topics: state-of-the-art in video conferencing; the shared table approach; 3D image analysis and synthesis; image and disparity coding; architecture of the conference table; conclusions and outlook.
It is presented how Photonics is addressed in the "Information Society Technology" thematic priority of the 6 th Framework Program. The Photonics research areas to be addressed and the funding instruments ar...
详细信息
It is presented how Photonics is addressed in the "Information Society Technology" thematic priority of the 6 th Framework Program. The Photonics research areas to be addressed and the funding instruments are presented.
The optical flow equation (OFE) is usually used to estimate the two-dimensional (2-D) apparent motion field of the moving objects in the digital video processing. But sometimes using the OFE directly for high-speed mo...
详细信息
The optical flow equation (OFE) is usually used to estimate the two-dimensional (2-D) apparent motion field of the moving objects in the digital video processing. But sometimes using the OFE directly for high-speed motion analysis, we will find the obvious error in the final results. In this paper, the reason for this is discussed from the theoretical model of the OFE. Then we propose a new method to eliminate this kind of error. After approximate displacement compensation for high-speed motion, the OFE is used to estimate the residual velocity field. The sum of the compensational value and the residual velocity field becomes the final optical flow field. We analyze the validity of the new method and give the one-dimensional (1-D) example so as to explain this problem clearly. In the end, the experiments have demonstrated that the result of optical flow estimation with displacement compensation is much more accurate than the usual one for high-speed motion.
The following topics are dealt with: power system modelling, planning and operation; power electronics and machines; electromagnetics and optics; antenna theory, design and applications; remote sensing; SAR ; acoustic...
The following topics are dealt with: power system modelling, planning and operation; power electronics and machines; electromagnetics and optics; antenna theory, design and applications; remote sensing; SAR ; acoustic ranging; microelectronics and VLSI; nanotechnology and micromachining; instrumentation and sensors; circuits and systems; robotics and mechatronics; reliability engineering; computers and digital hardware; real-time systems; software and information technology; computational intelligence; neural networks; genetic algorithms and fuzzy logic; pattern recognition; imageprocessing; video processing; signal processing and filter design; biomedical engineering; health-care systems; communications systems; computer networks; wireless networks; telecommunication traffic analysis; QoS; industrial applications.
A novel approach to Bayesian structure from motion (SfM) using inertial information and sequential importance sampling (SIS) is presented. The inertial information is obtained from camera-mounted inertial sensors and ...
详细信息
A novel approach to Bayesian structure from motion (SfM) using inertial information and sequential importance sampling (SIS) is presented. The inertial information is obtained from camera-mounted inertial sensors and is used in the Bayesian SfM approach as prior knowledge of the camera motion in the sampling algorithm. Experimental results using both synthetic and real images show that, when inertial information is used, more accurate results can be obtained or the same estimation accuracy can be obtained at a lower cost.
In this paper, a novel method of the surface reconstruction from a single monocular image is proposed. Our proposed approach (called shape from knowledge) is based on the knowledge of objects, which is acquired by lea...
详细信息
In this paper, a novel method of the surface reconstruction from a single monocular image is proposed. Our proposed approach (called shape from knowledge) is based on the knowledge of objects, which is acquired by learning from a number of samples. To achieve this, we investigate making use of the hidden Markov model (HMM) framework, which models the correspondence between an intensity image an its depth information. We have applied our algorithm to the 3-D face and 3-D hand reconstruction from single images, and the results show the effectiveness of the proposed method.
In this paper, an hybrid filter is presented for restoration of color images in a mixed noise environment, where both impulsive and correlation noise may be present. The proposed hybrid filter is composed of two stage...
详细信息
In this paper, an hybrid filter is presented for restoration of color images in a mixed noise environment, where both impulsive and correlation noise may be present. The proposed hybrid filter is composed of two stages, the first stage to remove the impulsive noise and the second to remove the correlated noise. The median filters and their variants are the most popular filter types used for impulsive noise suppression. However, median filters and their variants tend to remove fine image details and destroy fine texture in the mixed noise environment or when the signal to noise ratio is low. In order to overcome the limitations of the median filters, an adaptive simplified-model Kalman filter (ASMKF) is propsed for the suppression of impulsive noise in the first stage of the hybrid filter. In the second stage of the proposed hybrid filter, to remove correlated noise, discrete Wavelet Transform (DWT) filter is applied on the impulsive-noise-free image obtained from the first stage. The efficacy of the proposed hybrid filter is illustrated through implementation results obtained on the restoration of a color image.
暂无评论