Learning behavior patterns from video for agent-based crowd modeling and simulation
This paper proposes a novel data-driven modeling framework to construct agent-based crowd model based on real-world video data. The constructed crowd model can generate crowd behaviors that match those observed in the video and can be used to predict trajectories of pedestrians in the same scenario....
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/89559 http://hdl.handle.net/10220/47082 |
| _version_ | 1826109751145005056 |
|---|---|
| author | Zhong, Jinghui Cai, Wentong Luo, Linbo Zhao, Mingbi |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Zhong, Jinghui Cai, Wentong Luo, Linbo Zhao, Mingbi |
| author_sort | Zhong, Jinghui |
| collection | NTU |
| description | This paper proposes a novel data-driven modeling framework to construct agent-based crowd model based on real-world video data. The constructed crowd model can generate crowd behaviors that match those observed in the video and can be used to predict trajectories of pedestrians in the same scenario. In the proposed framework, a dual-layer architecture is proposed to model crowd behaviors. The bottom layer models the microscopic collision avoidance behaviors, while the top layer models the macroscopic crowd behaviors such as the goal selection patterns and the path navigation patterns. An automatic learning algorithm is proposed to learn behavior patterns from video data. The learned behavior patterns are then integrated into the dual-layer architecture to generate realistic crowd behaviors. To validate its effectiveness, the proposed framework is applied to two different real world scenarios. The simulation results demonstrate that the proposed framework can generate crowd behaviors similar to those observed in the videos in terms of crowd density distribution. In addition, the proposed framework can also offer promising performance on predicting the trajectories of pedestrians. |
| first_indexed | 2024-10-01T02:23:23Z |
| format | Journal Article |
| id | ntu-10356/89559 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:23:23Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/895592020-03-07T11:49:00Z Learning behavior patterns from video for agent-based crowd modeling and simulation Zhong, Jinghui Cai, Wentong Luo, Linbo Zhao, Mingbi School of Computer Science and Engineering Crowd Modeling And Simulation Agent-based Modeling DRNTU::Engineering::Computer science and engineering This paper proposes a novel data-driven modeling framework to construct agent-based crowd model based on real-world video data. The constructed crowd model can generate crowd behaviors that match those observed in the video and can be used to predict trajectories of pedestrians in the same scenario. In the proposed framework, a dual-layer architecture is proposed to model crowd behaviors. The bottom layer models the microscopic collision avoidance behaviors, while the top layer models the macroscopic crowd behaviors such as the goal selection patterns and the path navigation patterns. An automatic learning algorithm is proposed to learn behavior patterns from video data. The learned behavior patterns are then integrated into the dual-layer architecture to generate realistic crowd behaviors. To validate its effectiveness, the proposed framework is applied to two different real world scenarios. The simulation results demonstrate that the proposed framework can generate crowd behaviors similar to those observed in the videos in terms of crowd density distribution. In addition, the proposed framework can also offer promising performance on predicting the trajectories of pedestrians. 2018-12-19T03:35:05Z 2019-12-06T17:28:22Z 2018-12-19T03:35:05Z 2019-12-06T17:28:22Z 2016 Journal Article Zhong, J., Cai, W., Luo, L., & Zhao, M. (2016). Learning behavior patterns from video for agent-based crowd modeling and simulation. Autonomous Agents and Multi-Agent Systems, 30(5), 990-1019. doi:10.1007/s10458-016-9334-8 1387-2532 https://hdl.handle.net/10356/89559 http://hdl.handle.net/10220/47082 10.1007/s10458-016-9334-8 en Autonomous Agents and Multi-Agent Systems © The Author(s) (Published by Springer). |
| spellingShingle | Crowd Modeling And Simulation Agent-based Modeling DRNTU::Engineering::Computer science and engineering Zhong, Jinghui Cai, Wentong Luo, Linbo Zhao, Mingbi Learning behavior patterns from video for agent-based crowd modeling and simulation |
| title | Learning behavior patterns from video for agent-based crowd modeling and simulation |
| title_full | Learning behavior patterns from video for agent-based crowd modeling and simulation |
| title_fullStr | Learning behavior patterns from video for agent-based crowd modeling and simulation |
| title_full_unstemmed | Learning behavior patterns from video for agent-based crowd modeling and simulation |
| title_short | Learning behavior patterns from video for agent-based crowd modeling and simulation |
| title_sort | learning behavior patterns from video for agent based crowd modeling and simulation |
| topic | Crowd Modeling And Simulation Agent-based Modeling DRNTU::Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/89559 http://hdl.handle.net/10220/47082 |
| work_keys_str_mv | AT zhongjinghui learningbehaviorpatternsfromvideoforagentbasedcrowdmodelingandsimulation AT caiwentong learningbehaviorpatternsfromvideoforagentbasedcrowdmodelingandsimulation AT luolinbo learningbehaviorpatternsfromvideoforagentbasedcrowdmodelingandsimulation AT zhaomingbi learningbehaviorpatternsfromvideoforagentbasedcrowdmodelingandsimulation |