A particle filter human tracking method based on HOG and Hu moment

In this paper, a vision-based human tracking approach integrating Histogram of Oriented Gradient (HOG) and Hu moment feature is presented under the Particle Filter framework. Our motivation stems from the fact that traditional Particle Filter (PF) based on single feature is not robust when the background color, illuminate and target deformation change, and it may lead to lose target or fail to detect easily. In order to solve this problem, a Particle Filter tracking method based on HOG and Hu moment feature by utilizing vision method is presented. Due to the advantages of HOG feature in describing the target contour and shape and the advantages of Hu moment in the invariance property to translation, rotation and scaling, these features are used as recognition features. Besides, PF is introduced to adjust and predict the position of the tracking human. This paper details the architecture of the presented method and gives some experimental results to verify the effectiveness of the presented method.