Target Tracking Algorithm Based on Sparse Representation of Cooperative Template

摘要

Aiming at the problem that the matching error between the target template and the candidate template. In this paper, a new target tracking algorithm based on sparse representation of cooperative template is proposed. When constructing the target template, the global and local templates were used to set up the collaborative template to describe the target; in order to further deal with the influence of occlusion factors, the sparse coefficient were weighted pretreatment; Making full use of the local information of the target, and combining the global information, the measurement function was designed to calculate the similarity between the candidate target and the target template. Experimental results show that the proposed method is robust to rotation, partial occlusion and scale change.