Creating realistic virtual humans has been a challenging objective in the areas of computer science research and technology industry. While there are a number of aspects to create realistic virtual humans, this paper focuses on the comprehensive integrated framework of modeling virtual humans with high level autonomy, which aim to reproduce human-like believable behaviors and movements of virtual humans in virtual environment. In the framework, the perception module enables virtual human to explore the virtual environment and gets vision and audition information; the decision networks based behavioral decision-making module allows virtual human react appropriately to the perceived surrounding environment; the hierarchical movement animation control module is designed to generate autonomous character navigation and realistic motions for character animation in virtual environment. The integrated framework presented is tested in the simulated virtual environment.

Robust detection of moving objects in complex and dynamic scenes is one of the most challenging issues in computer vision. In this paper, we present an approach to segmenting moving objects with nonparametric estimated local kernel histogram (ELKH) in dynamic scenes. By using the correlation and texture of spatially proximal pixels, local kernel histogram background model is constructed. Then probability distribution of local kernel histogram is estimated with nonparametric techniques. We employ Bhattacharyya distance to measure the similarity of local kernel histogram between estimated background model with each pixel in current frame, and decide whether the pixel belongs to moving objects or not. Our approach can reduce false detections due to disturbing noise and small motions in dynamic scenes, such as swaying branches, flickering water surface, rain. Experiments show that the proposed approach achieves promising results in real dynamic videos robustly.

Foreground segmentation is one of the most challenging problems in computer vision. In this paper, we propose a new algorithm for static camera foreground segmentation. It combines Gaussian mixture model (GMM) and active contours method, and produces much better results than conventional background subtraction methods. It formulates foreground segmentation as an energy minimization problem and minimizes the energy function using curve evolution method. Because of the integration of GMM background model, shadow elimination term and curve evolution edge stopping term into energy function, it achieves more accurate segmentation than existing method of the same type. Promising results on real images demonstrate the potential of the presented method.

Current markerless model-based human body motion capture methods always aim at accurate human body model and reconstruction surface contour. Unfortunately, because of the factors such as loose clothing, image noise and background segmentation errors, the efforts of these methods get very limited effects. In this paper, we propose a new algorithm for markerless model-based human body motion capture which is robust to the inaccurate human body reconstruction caused by the factors mentioned above. We extracted a volume data (voxel) representation from silhouettes in multiple video images. In the consideration of the human body model, we construct an articulated model with a potential energy which emphasize the skeleton of the human body and is not sensitive to the outline details of the human body surface. Then, we fit the human body model to the volume data in an expectation-maximization framework and recover the pose of the human body.

This paper presents a 3D object classification system based on volumetric parts. As the constituents of 3D object, the parts are described by superquadric-based geons, which enables a more compact 3D object representation. In the developed classification system, the improved interpretation tree method is implemented for classification, where a set of novel integrated features and corresponding constraints are proposed, which not only reflect individual parts’ shape, but model’s topological structure among 3D parts. The constraints are used to define efficient interpretation tree search rules, and the feasible correspondences of unknown object data and the stored models are obtained. Then a similarity measure computation algorithm is proposed to evaluate the shape similarity of the correspondence. The classification system can achieve both whole match and partial match between unknown object data and 3D models with shape similarity ranks; particularly, focus match can be accomplished, in which different key parts may be labeled and all the matched models with corresponding key parts can be obtained. The performance of the presented 3D object classification system is evaluated with a series of experiments.

This paper presents two evolutionary agent-based approaches to fundamental matrix estimation. In order to improve the search ability and computational efficiency of the simple evolutionary agent, new methods, the competitive evolutionary agent (CEA) and finite multiple evolutionary agent (FMEA), are proposed by applying better evolutionary strategies and decision rules. CEA mainly focuses on the reproduction behavior and FMEA concentrates on the diffusion process. Experiments show that the improved approaches perform better than the original one in terms of accuracy and speed, and are more robust to noise and outliers.

In the development of spoken dialog systems, domain adaptation and dialog state-dependent language model are usually researched separately. This paper proposes a new approach for domain adaptation augmented by the dialog state-dependence, which means a dialog turn based cache model decaying synchronously with the dialog state change. Through this approach it’s more simple and rapid to adapt a Chinese spoken dialog system to a new task. Two different tasks, the train ticket reservation and the park guide are selected respectively as the target task in the experiments. The consistent reductions of perplexity and character error rate are observed during the adaptation.

Abstract: The paper gives an overall discussion on problems in Chinese natural speech generation. We considered not only how to convert text into speech but also how to generate the necessary text in text-to-speech conversion.A Chinese Bi-directional Grammar is developed to suit for Chinese Language under-standing and generation. The system gets the right text and generates speech which have good quality in naturalness and intelligibility using Chinese Text-to-

The fractal image coding technique has attracted a degree of interest for its low bit rate. But the reconstructed image is of medium quality. This problem has prevented the fractal technique from being used practically. In order to improve the compression fidelity, a new affine transformation is proposed. Meanwhile, its contractivity requirement is analyzed, and the optimal parameters are derived using the least square method. The new affine transformation has been practically used in image coding. Experiments show that the PSNR can reach 28.7 dB at a compression ratio (CR) of 16.4 for the 256/spl times/256/spl times/8 "Lena" image. Comparison with other fractal coding schemes shows that the new affine transformation can improve the reconstructed image quality efficiently.

Ellipses are a powerful feature and are useful in computer vision. Most techniques pr ellipse fitting can be divided into two main classifications: one is the least square estimation (LSE) method and the other is the Hough transform (HT). They either make certain assumptions about the type of noise distribution, or require input parameters. This often prevents the techniques working robustly over a large range of data. A simple algorithm for partial ellipse detection using seperate parameters estimation techniques is proposed. The new method consists of two steps: (1) detect the elliptical center using its skewed symmetry properties; (2) estimate the other three parameters (A. B, 6) using the median of the intercepts (MI). The new method has been tested on both the synthetic and real images. The experimental results show that the method is reliable and accurate.