Car tracking algorithm based on Kalman filter and compressive tracking

摘要

According to the features of traffic supervisory video, Compressive Tracking (CT) algorithm is adopted to detect and track the moving car. When the camera angle, moving vehicle scale and background changed, the CT algorithm still has a strong robustness. However, the algorithm is invalid when car is sheltered so that the tracked car cannot be located. In order to overcome this problem, a new method which uses Kalman filter to predict the sheltered car moving position is proposed. Experimental results show that despite changed in tracking window size and target location or sheltered overall or partly, the proposed algorithm can also track that car successfully, and has good real-time performance which meets the requirements of engineering application.