Moving Target Tracking via Particle Filter Based on Color and Contour Features

Target tracking based only on color feature often leads to an inaccurate result when the background is complex. In this paper, a novel particle filter tracking algorithm based on color and contour features is proposed. We first obtain the contour information of a moving target from its motion segmentation, then use Harris corner detector to extract feature points of a contour. Afterwards, Hausdorff distance is applied to measure the similarity of feature points between a hypothetical candidate and the target. Experiments show that with the fusion of the two features, the algorithm can track the target robustly and accurately in the condition of illumination changes and similar color clutters.