An Improved Moving Tracking Algorithm With Multiple Information Fusion Based on 3D Sensors

The continuously adaptive mean shift algorithm suffers from the tracking offset phenomenon while tracking targets with colors similar to that of the background. In this paper, to improve the performance of this algorithm, the depth information is combined with the back-projection color image and the information from the moving prediction algorithm. The target search window is predicted based on switching filtering algorithm with the Extended Kalman Filter (EKF) method. The moving tracking synthesis algorithm which used 3D sensors and combines color, depth and prediction information is used to solve the problems that the continuously adaptive mean shift algorithm encounters, namely disturbance and the tendency to enlarge the tracking window. The experimental results show that the proposed algorithm can accurately track a moving target in the presence of a complex background, and greatly improves the interference resistance and robustness of the system.