Detection And Tracking Of Interested Moving Target Under Complex Background

As a core research topic of computer vision, detection and tracking of moving target can be widely used in many fields, such as military guidance, human-computer interaction, video surveillance, navigation system of robot vision and so on. Detection and tracking of moving target provides some important datas for analysis and understanding of video image sequence. It is very difficult to present a robust tracking algorithm for moving target under complex background.Concerning the problem of tracking interested moving target inaccurately because of complex background, an algorithm of detection and tracking was proposed. First, Three frame difference base on Gaussian mixture model was used to detect moving target. And then a robust tracking algorithm was proposed to integrate multiple cues by adaptive fusion. The algorithm obtained the weighted color distribution model of interested moving target in the HSV color space. Then invariant moment was used to eliminate the interference of the similar background color and illumination changes. The algorithm fused the two features in the particle filter by adjusting their weights and updating particle weights adaptively. Thus, the algorithm can track the moving target accurately and stably. The experimental results show that the algorithm can track interested moving target accurately when moving target is tracked under complex background such as translation, variant posture, and be blocked of the moving object, varying illumination and the interference of the similar background color. The algorithm has strong robustness to background interference.The algorithm of combining background subtraction and erosion base on embedded hardware platform was used to detect moving target. And out of real-time considerations, searching and tracking algorithm base on feature matching was proposed. Thus, the detection and tracking algorithm base on a single target can be finished accurately.