Abstract

Traditional Camshift algorithm has low location accuracy and loses target usually in intelligent video tracking. In view of these, this paper puts forwards a modified Camshift algorithm based on intelligent video tracking, which firstly predicts the location and size of the search window of the target, modify the predicted values and optimize the original algorithm in the case of occlusion. The simulation results show that, the improved Camshift algorithm has stronger robustness and higher accuracy than the original algorithm whether in the case of occlusion or not.

Paper Details