A moving target detection algorithm based on combination of GMM and LBP texture pattern
Jiyun Zhai, Xin Zhou, Congqing Wang · 2016
It is important and difficult to improve the robustness of target detection in the field of computer vision. In order to realize the accurate extraction of moving objects in the context of complex scenes, this paper proposes a new algorithm for object detection based on texture feature and background modeling. Firstly, the traditional Gaussian mixture model is improved, and then the improved Gaussian mixture model and the LBP texture model are fused by probability matching. The experimental results show that the proposed algorithm has better performance for detecting moving targets compared with the traditional algorithm.