Study On Video-based Vehicle Detection And Tracking

The application of computer vision technology to traffic detecting and information collecting is an important subject in ITS (Intelligent Transportation System), and moving vehicle detecting and tracking is the basic part. The further study on this question is carried out systematically in this paper. Taking the natural road as the background, a kind of moving vehicle auto-detecting and auto-tracking method is brought forward. Moreover the software system is designed and implemented. A moving vehicle can be automatically tracked elementarily by using the software system.The main contents of the study include such aspects as follows: (1) Under the circumstance that the camera is still, an algorithm for detecting and tracking vehicles is proposed. The algorithm based on motion object segmentation by means of background difference and using successive frame difference to improve the performance. (2) Under the circumstance that the camera is moving, a background motion vector estimating method is proposed. In this method, we use an affine model to describe the global motion due to the camera and use a Taylor expansion algorithm to estimate the affine transform model parameters quickly and effectively. Then, use inter-frame differential technique to detect moving vehicles. Experiment shows that the moving vehicles can be effectively extracted with this method. (3) Considering moving distance and area change of one vehicle in the two consecutive frames is small, the author presented an algorithm tracking moving vehicles. Two parameters, centroid and area of moving vehicles, were used to match in the method. Because only two parameters were used and the datum was small, the moving vehicles in the frame were tracked and located the position quickly.