Monocular vision tracking based on Particle Filter and Hu moment
Xiuzhi Li, Xue Zhao, Songmin Jia · 2012
In this paper, we present a monocular vision tracking approach based on Hu moment recognition in Particle Filter framework. Our motivation stems from the fact that when the target rotates, translates and scales, target losing or mistracking always happens in image. To solve this problem, we propose an object tracking technique based on Particle Filter and Hu moment by using monocular vision method. Because of its inherent invariance property to the regional scaling, translation and rotation, Hu moment is used as identification features. In addition, PF is adopted to correct and predict the location of the tracking object. This paper details the architecture of the proposed method and gives some experimental results to verify the effectiveness of the proposed method.