Tracking algorithm of improved spatio-temporal context with particle filter

Aiming at the problem that spatio-temporal context tracking algorithm is easy to generate drift when the target is in the occlusion condition and complex background, a visual tracking algorithm of improved spatio-temporal context with particle filter is proposed. During the target tracking process, first, the Bhattacharyya coefficient is used as a judgment criterion when the target is occluded. Then the particle filter is used to estimate and predict the position and trajectory of the target in the subsequent frame, and the target can be traced accurately. The experimental results show that the proposed algorithm can not only be applied to visual target tracking when the target is in complex conditions such as illumination changes, target rotation and background interference, but also is robust to the occlusion of the target and satisfies the requirements of real-time tracking.