A robust object detection algorithm based on background difference and LK optical flow
Guang Han, Xiaofei Li, Ning Sun, Jixin Liu · 2014
A robust object detection algorithm based on background difference and LK (Lucas-Kanade, LK) optical flow is proposed. Firstly the object detection algorithms based on background difference and LK optical flow are improved respectively, and then these two algorithms are effectively fused with a novel fusion method, the problems caused by using single algorithm in practical application are solved. The experimental results show that the proposed fusion algorithm can effectively make up for the defects of using single algorithm, the performance of the moving object detection under complex scene is better than the other algorithms, the results show that the proposed algorithm is a robust and accurate object detection method.1.