Collective interaction filtering approach for detection of group in diverse crowded scenes
Crowd behavior analysis research has revealed a central role in helping people to find safety hazards or crime optimistic forecast. Thus, it is significant in the future video surveillance systems. Recently, the growing demand for safety monitoring has changed the awareness of video surveillance stu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Korean Society for Internet Information
2019
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/80956/1/COLLECTIVE.pdf |
| _version_ | 1825951362965307392 |
|---|---|
| author | Wong, Pei Voon Mustapha, Norwati Affendey, Lilly Suriani Khalid, Fatimah |
| author_facet | Wong, Pei Voon Mustapha, Norwati Affendey, Lilly Suriani Khalid, Fatimah |
| author_sort | Wong, Pei Voon |
| collection | UPM |
| description | Crowd behavior analysis research has revealed a central role in helping people to find safety hazards or crime optimistic forecast. Thus, it is significant in the future video surveillance systems. Recently, the growing demand for safety monitoring has changed the awareness of video surveillance studies from analysis of individuals behavior to group behavior. Group detection is the process before crowd behavior analysis, which separates scene of individuals in a crowd into respective groups by understanding their complex relations. Most existing studies on group detection are scene-specific. Crowds with various densities, structures, and occlusion of each other are the challenges for group detection in diverse crowded scenes. Therefore, we propose a group detection approach called Collective Interaction Filtering to discover people motion interaction from trajectories. This approach is able to deduce people interaction with the Expectation-Maximization algorithm. The Collective Interaction Filtering approach accurately identifies groups by clustering trajectories in crowds with various densities, structures and occlusion of each other. It also tackles grouping consistency between frames. Experiments on the CUHK Crowd Dataset demonstrate that approach used in this study achieves better than previous methods which leads to latest results. |
| first_indexed | 2024-03-06T10:28:53Z |
| format | Article |
| id | upm.eprints-80956 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T10:28:53Z |
| publishDate | 2019 |
| publisher | Korean Society for Internet Information |
| record_format | dspace |
| spelling | upm.eprints-809562020-10-14T19:55:56Z http://psasir.upm.edu.my/id/eprint/80956/ Collective interaction filtering approach for detection of group in diverse crowded scenes Wong, Pei Voon Mustapha, Norwati Affendey, Lilly Suriani Khalid, Fatimah Crowd behavior analysis research has revealed a central role in helping people to find safety hazards or crime optimistic forecast. Thus, it is significant in the future video surveillance systems. Recently, the growing demand for safety monitoring has changed the awareness of video surveillance studies from analysis of individuals behavior to group behavior. Group detection is the process before crowd behavior analysis, which separates scene of individuals in a crowd into respective groups by understanding their complex relations. Most existing studies on group detection are scene-specific. Crowds with various densities, structures, and occlusion of each other are the challenges for group detection in diverse crowded scenes. Therefore, we propose a group detection approach called Collective Interaction Filtering to discover people motion interaction from trajectories. This approach is able to deduce people interaction with the Expectation-Maximization algorithm. The Collective Interaction Filtering approach accurately identifies groups by clustering trajectories in crowds with various densities, structures and occlusion of each other. It also tackles grouping consistency between frames. Experiments on the CUHK Crowd Dataset demonstrate that approach used in this study achieves better than previous methods which leads to latest results. Korean Society for Internet Information 2019-02 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/80956/1/COLLECTIVE.pdf Wong, Pei Voon and Mustapha, Norwati and Affendey, Lilly Suriani and Khalid, Fatimah (2019) Collective interaction filtering approach for detection of group in diverse crowded scenes. KSII Transactions on Internet and Information Systems, 13 (2). pp. 912-928. ISSN 1976-7277 http://www.itiis.org/ 10.3837/tiis.2019.02.023 |
| spellingShingle | Wong, Pei Voon Mustapha, Norwati Affendey, Lilly Suriani Khalid, Fatimah Collective interaction filtering approach for detection of group in diverse crowded scenes |
| title | Collective interaction filtering approach for detection of group in diverse crowded scenes |
| title_full | Collective interaction filtering approach for detection of group in diverse crowded scenes |
| title_fullStr | Collective interaction filtering approach for detection of group in diverse crowded scenes |
| title_full_unstemmed | Collective interaction filtering approach for detection of group in diverse crowded scenes |
| title_short | Collective interaction filtering approach for detection of group in diverse crowded scenes |
| title_sort | collective interaction filtering approach for detection of group in diverse crowded scenes |
| url | http://psasir.upm.edu.my/id/eprint/80956/1/COLLECTIVE.pdf |
| work_keys_str_mv | AT wongpeivoon collectiveinteractionfilteringapproachfordetectionofgroupindiversecrowdedscenes AT mustaphanorwati collectiveinteractionfilteringapproachfordetectionofgroupindiversecrowdedscenes AT affendeylillysuriani collectiveinteractionfilteringapproachfordetectionofgroupindiversecrowdedscenes AT khalidfatimah collectiveinteractionfilteringapproachfordetectionofgroupindiversecrowdedscenes |