Physical-barrier detection based collective motion analysis
- 18 Downloads
Collective motion is one of the most fascinating phenomena and mainly caused by the interactions between individuals. Physical-barriers, as the particular facilities which divide the crowd into different lanes, greatly affect the measurement of such interactions. In this paper we propose the physical-barrier detection based collective motion analysis (PDCMA) approach. The main idea is that the interaction between spatially adjacent pedestrians actually does not exist if they are separated by the physical-barrier. Firstly, the physical-barriers are extracted by two-stage clustering. The scene is automatically divided into several motion regions. Secondly, local region collectiveness is calculated to represent the interactions between pedestrians in each region. Finally, extensive evaluations use the three typical methods, i.e., the PDCMA, the Collectiveness, and the average normalized Velocity, to show the efficiency and efficacy of our approach in the scenes with and without physical barriers. Moreover, several escalator scenes are selected as the typical physical-barrier test scenes to demonstrate the performance of our approach. Compared with the current collective motion analysis methods, our approach better adapts to the scenes with physical barriers.
Keywordscrowd behavior analysis collective motion physical-barrier detection two-stage clustering local region collectiveness
Unable to display preview. Download preview PDF.
This work was funded by the National Key Research and Development Program of China (2016YFA0502300), the National Natural Science Foundation of China (Grant No. 61602175), Shanghai Municipal Commission of Economy and Informatization (150809), the Open Research Funding Program of KLGIS (KLGIS2015A05) and BUAA (BUAAVR-15KF-03), the Fundamental Research Funds for the Central Universities (222201514331), and Green Manufacturing System Integration Project of Ministry of Industry and Technology of China (9908000006).
- 2.Ihaddadene N, Djeraba C. Real-time crowd motion analysis. In: Proceedings of International Conference on Pattern Recognition. 2008, 1–4Google Scholar
- 3.Mehran R, Oyama A, Shah M. Abnormal crowd behavior detection using social force model. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2009, 935–942Google Scholar
- 4.Shao J, Kang K, Loy C C, Wang X. Deeply learned attributes for crowded scene understanding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2015, 4657–4666Google Scholar
- 5.Bai Y, Xu Y, Yang X, Yan Q. Measuring orderliness based on social force model in collective motions. Visual Communications and Image Processing, 2013, 7(2): 1–6Google Scholar
- 8.Berg J V D, Lin M, Manocha D. Reciprocal velocity obstacles for realtime multi-agent navigation. In: Proceedings of IEEE International Conference on Robotics and Automation. 2008, 1928–1935Google Scholar