Pedestrian tracking system by using human shape prior model
Ke-Chun Li, Hui-Chun Wang, Jing‐Ming Chiu · 2014
In this paper, we present a pedestrian tracking system by using image segmentation algorithm, which incorporated pedestrian shape prior into Random Walks segmentation [1] from a static image, and tracking people by Connected Component Labeling Algorithm. We improve the random walks segmentation algorithm by using prior shape information, which provides appropriate seeds for the pedestrian segmentation from the input image. By using the human shape prior information, we develop a fully automatic pedestrian image segmentation algorithm to detect pedestrians. Then we can find the region of interest (ROI) often performed on using a mapping-based detection approach by Connected Component Labeling Algorithm. After these previous steps, we provide a pedestrians tracking system.