MOVING HUMAN PATH TRACKING BASED ON VIDEO SURVEILLANCE IN 3D INDOOR SCENARIOS
- 1School of Resources and Environment, University of Electric Science and Technology of China (UESTC), Chengdu, Sichuan, China
- 2Institute of Remote Sensing Big Data, Big Data Research Center of UESTC, 2006 Xiyuan Avenue, West Hi-tech Zone, Chengdu, Sichuan 611731, China
- 3Delft University of Technology, Julianalaan 134, 2628 BL Delft, the Netherlands
- 4State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan, Hubei, China
Keywords: Moving Object Tracking, Video Surveillance, 3D Indoor Scenarios
Abstract. Video surveillance systems are increasingly used for a variety of 3D indoor applications. We can analyse human behaviour, discover and avoid crowded areas, monitor human traffic and so forth. In this paper we concentrate on use of surveillance cameras to track and reconstruct the path a person has followed. For the purpose we integrated video surveillance data with a 3D indoor model of the building and develop a single human moving path tracking method. We process the surveillance videos to detected single human moving traces; then we match the depth information of 3D scenes to the constructed 3D indoor network model and define the human traces in the 3D indoor space. Finally, the single human traces extracted from multiple cameras are connected with the help of the connectivity provided by the 3D network model. Using this approach, we can reconstruct the entire walking path. The provided experiments with a single person have verified the effectiveness and robustness of the method.