A robust system for real-time pedestrian detection and tracking
来源期刊：中南大学学报(英文版)2014年第4期
论文作者：LI Qi(李琦) SHAO Chun-fu(邵春福) ZHAO Yi(赵熠)
文章页码：1643 - 1653
Key words：image processing technique; pedestrian detection; tracking; video camera
Abstract: A real-time pedestrian detection and tracking system using a single video camera was developed to monitor pedestrians. This system contained six modules: video flow capture, pre-processing, movement detection, shadow removal, tracking, and object classification. The Gaussian mixture model was utilized to extract the moving object from an image sequence segmented by the mean-shift technique in the pre-processing module. Shadow removal was used to alleviate the negative impact of the shadow to the detected objects. A model-free method was adopted to identify pedestrians. The maximum and minimum integration methods were developed to integrate multiple cues into the mean-shift algorithm and the initial tracking iteration with the competent integrated probability distribution map for object tracking. A simple but effective algorithm was proposed to handle full occlusion cases. The system was tested using real traffic videos from different sites. The results of the test confirm that the system is reliable and has an overall accuracy of over 85%.
LI Qi(李琦), SHAO Chun-fu(邵春福), ZHAO Yi(赵熠)
(Key Laboratory for Urban Transportation Complex Systems Theory and Technology of Ministry of Education
(Beijing Jiaotong University), Beijing 100000, China)
Abstract:A real-time pedestrian detection and tracking system using a single video camera was developed to monitor pedestrians. This system contained six modules: video flow capture, pre-processing, movement detection, shadow removal, tracking, and object classification. The Gaussian mixture model was utilized to extract the moving object from an image sequence segmented by the mean-shift technique in the pre-processing module. Shadow removal was used to alleviate the negative impact of the shadow to the detected objects. A model-free method was adopted to identify pedestrians. The maximum and minimum integration methods were developed to integrate multiple cues into the mean-shift algorithm and the initial tracking iteration with the competent integrated probability distribution map for object tracking. A simple but effective algorithm was proposed to handle full occlusion cases. The system was tested using real traffic videos from different sites. The results of the test confirm that the system is reliable and has an overall accuracy of over 85%.
Key words:image processing technique; pedestrian detection; tracking; video camera
