You Zhi-sheng

A Real-time Vision-based Vehicle Tracking and Traffic Surveillance

A vision-based detecting and tracking vehicle in video streams is an important research in computer vision, and it plays an important role in ITS. The aim of motion detection is to get the changed region from the background image in video sequences, and it is also very important for targets classification and tracking motion objects. In this paper, a self-adaptive background subtraction method for vehicle segmentation was proposed. To indicate motion mask regions in a scene, instead of determining the threshold value manually, we use an adaptive thresholding method to automatically choose the threshold value. In order to accurately locate vehicle, we combined the projection of the difference image and the projection of the edge map from coarse to refine accurately locate vehicles. This proposed method could locate vehicle well. We formed an association graph between the regions from the previous frame and the regions from the current frame, so we modeled the vehicle tracking problem as a problem of finding maximal weight association graph. Very promising experimental results are provided using real-time video sequences, Experimental results demonstrate the validity of the approach in term of robustness, accuracy and time responses.

Face detection and facial feature extraction in color image

Face detection and facial feature extraction plays an important role in video surveillance, human computer interaction and face recognition. Color is a useful piece of information in computer vision especially for skin detection. In this paper, we propose a novel approach for skin segmentation and facial feature extraction. The proposed skin segmentation is a method for integrating the chrominance components of nonlinear YCrCb color model. The goal of skin detection is to group pixels to form possible face candidate regions and then use connected components analysis for pixels grouping. In order to detect the facial feature in scale invariant, the possible face candidate regions will be normalized, and then texture information in these regions will be segmented by means of mean and variance of face region. Edge will be detected using the method based on multi-scale morphological. Eye will be located by the PCA edge direction. The others feature, such as nose and mouth, also located using the geometrical shape information. As all the above-mentioned techniques are simple and efficient, the proposed method is computational effective and suitable for practical applications. In our experiments, the proposed method has been successfully evaluated using two different test datasets. The detection accuracy is around 98%, the average run time ranged from 0.1-0.3 sec per frame.

An Improved Video Compression Algorithm for Lane Surveillance

In order to process huge volume of data efficiently in video surveillance system, it is very necessary and important to find out high efficient video retrieval techniques and advanced video compression techniques. This paper presents an improved video compression algorithm for lane supervision, which considers the implementation of video retrieval at the stage of video compression. This improved video compression algorithm combines the following three parts: shot segmentation based on detection of moving vehicle; key frame extraction based on vehicle-license- plate locating; video compression in which the I frame, B frame and P frame is decided by the former two steps. Experimental results show that the algorithm presented in this paper not only increases the compression ratio, but also improves the quality of the video reverting from compressed video and improves the efficiency and performance of the later video retrieval.

A Background Reconstruction Method Based on Double-background

In this paper, we show a new method to reconstruct and update the background. This approach is based on double-background. We use the statistical information of the pixel intensity to construct a background that represents the status during a long time, and construct another background with feedback information in motion detection that represents the recent changes at a short time. This couple of background images is fused to construct and update the background image used to motion detection. The background reconstruction algorithm can perform well on the tests that we have applied it to.

Segment the metallograph images using Gabor filter

We have implemented a texture-based supervised segmentation method to segment a variety of metallograph images which are considered to contain different textured regions. Texture features are computed by using a set of even symmetric Gabor filters which have been successfully used earlier for a variety of texture classification and segmentation tasks. The performance of the proposed method has been shown on a number of test images. These results also demonstrate the ability of our improved approach to separate the untextured regions from the textured regions in the same image.<<ETX>>

A New Cellular Automata Model Considering Finite Deceleration and Braking Distance

We present a new cellular automata model for one-lane traffic flow. In this model, we consider the driver prejudgment according to the state of the leading car. We also consider that the vehicle deceleration capability is finite and the braking distance of the high-speed running cars cannot be ignored, which is not considered in most models. Furthermore, comfortable driving is considered, too. Using computer simulations we obtain some basic qualitative results and the fundamental diagram of the proposed model. In comparison with the known models, we find that the fundamental diagram of the proposed model is more realistic than that of the known models.

Development of the ATC Simulators

In the ATC domain, simulated training is an effective approach to cultivate controllers, and ATC simulators providing vivid simulated environment for the trainees are the key devices with high complexity. In this paper, the software product line approach is proposed to build a group of ATC simulators from a common set of core assets. As the core assets shared across our ATC simulators, the high-level procedural model, architecture, real-time network communication component, primitive-based aerostats? operation command mechanism and multi-PC based 3D virtual scene rendering system are analyzed and described in detail, which is helpful to the development of other similar simulation applications. Additionally, the development of a tower simulator is presented as an example with a few screenshots, which shows our solution is effective and helpful to the complex simulation applications family such as ATC simulators.

ARMAX: a new cinema technology for casting both common and VR-based interactive films

This paper presents a new cinema technology---ARMAX, which can not only cast common films and stereoscopic films in a high quality, but also be compatible with VR-based interactive films (except game films). Three key technologies in ARMAX are highlighted, as well as the methods of facilitating interaction between the audiences and 3D roles by using out-of-screen distance and highly precise positioning technology. Then, we discuss several problems currently encountered by ARMAX. Finally, we conclude the paper with some development trends of ARMAX in the near future.

A novel face recognition method based on 3D face model

A new algorithm that project 3D face model to 2D planes is proposed. 3D face models are projected to different directions and a series of 2D face images are obtained. The projected 2D results are used as templates to match the input face images with different poses. The method that constructs 3D face model with 2.5D scans acquired by Minolta Vivid 910 is studied and a 3D face database containing 10 persons is built. Experimental results show that the proposed algorithm improves the recognition rate greatly for face images with pose variations than the method that uses just frontal images as templates.