Target Tracking in Colored Image Sequence Using Weighted Color Histogram Based Particle Filter

This paper presents a novel approach for visually tracking a colored target in a noisy and dynamic environment using weighted color histogram based particle filter algorithm. In order to make the tracking task robustly and effectively, color histogram based target model is integrated into particle filter algorithm, which considers the target's shape as a necessary factor in target model. Bhattacharyya distance is used to weight samples in the particle filter by comparing each sample's histogram with a specified target model and it makes the measurement matching and samples' weight updating more reasonable. The method is capable of successfully tracking moving targets in different indoor environment without initial positions information. A series of experiment results and experiment data analysis show this method's feasibility, and a surveillance system composed of two coordinating real mobile robots also given a practical application case of this method.