Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter
Most multi-object tracking methods have achieved good results in tracking multiple pedestrians with Kalman filter, but their tracking performance in crowded scenes is still poor due to pedestrian avoidance and frequent occlusion. In crowded scenes, the pedestrian trajectory prediction with Kalman fi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9941077/ |
| _version_ | 1811225529733349376 |
|---|---|
| author | Jianhong Yan Shuailing Du Yanan Wang |
| author_facet | Jianhong Yan Shuailing Du Yanan Wang |
| author_sort | Jianhong Yan |
| collection | DOAJ |
| description | Most multi-object tracking methods have achieved good results in tracking multiple pedestrians with Kalman filter, but their tracking performance in crowded scenes is still poor due to pedestrian avoidance and frequent occlusion. In crowded scenes, the pedestrian trajectory prediction with Kalman filter alone is unreliable. In this paper, a two-dimensional field-of-view avoidance force model (AFM) is proposed to assist the Kalman filter prediction by sensing the avoidance force and then complete pedestrian tracking. In the model, each pedestrian has a two-dimensional field of view to perceive the avoidance force, which determines the next predicted trajectory. In real scenes, pedestrians tend to be more concerned about the surrounding area, so different areas are set to simulate the attention mechanisms of pedestrians in real scenes. In the FairMOT model, AFM is used to optimize the pedestrian state values of Kalman filter prediction and the optimized model is trained on the MOT16 dataset. The experimental results on the MOT20 dataset show that compared with the mainstream tracking model FairMOT, our method respectively improves MOTA by 2.7% and IDF1 by 2.2%. Our method also achieves the good performance on MOT15, MOT16, and MOT17 tracking benchmarks. |
| first_indexed | 2024-04-12T09:08:48Z |
| format | Article |
| id | doaj.art-f524f6f001f94beb97f07f969e57704a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T09:08:48Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f524f6f001f94beb97f07f969e57704a2022-12-22T03:39:02ZengIEEEIEEE Access2169-35362022-01-011011851211852110.1109/ACCESS.2022.32206359941077Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman FilterJianhong Yan0https://orcid.org/0000-0001-5673-4706Shuailing Du1Yanan Wang2College of Computer Science and Technology, Taiyuan Normal University, Taiyuan, ChinaCollege of Computer Science and Technology, Taiyuan Normal University, Taiyuan, ChinaCollege of Computer Science and Technology, Taiyuan Normal University, Taiyuan, ChinaMost multi-object tracking methods have achieved good results in tracking multiple pedestrians with Kalman filter, but their tracking performance in crowded scenes is still poor due to pedestrian avoidance and frequent occlusion. In crowded scenes, the pedestrian trajectory prediction with Kalman filter alone is unreliable. In this paper, a two-dimensional field-of-view avoidance force model (AFM) is proposed to assist the Kalman filter prediction by sensing the avoidance force and then complete pedestrian tracking. In the model, each pedestrian has a two-dimensional field of view to perceive the avoidance force, which determines the next predicted trajectory. In real scenes, pedestrians tend to be more concerned about the surrounding area, so different areas are set to simulate the attention mechanisms of pedestrians in real scenes. In the FairMOT model, AFM is used to optimize the pedestrian state values of Kalman filter prediction and the optimized model is trained on the MOT16 dataset. The experimental results on the MOT20 dataset show that compared with the mainstream tracking model FairMOT, our method respectively improves MOTA by 2.7% and IDF1 by 2.2%. Our method also achieves the good performance on MOT15, MOT16, and MOT17 tracking benchmarks.https://ieeexplore.ieee.org/document/9941077/Kalman filtermulti-object trackingmovement behaviormulti-pedestrian trackingAFM |
| spellingShingle | Jianhong Yan Shuailing Du Yanan Wang Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter IEEE Access Kalman filter multi-object tracking movement behavior multi-pedestrian tracking AFM |
| title | Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter |
| title_full | Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter |
| title_fullStr | Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter |
| title_full_unstemmed | Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter |
| title_short | Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter |
| title_sort | multi pedestrian tracking in crowded scenes by modeling movement behavior and optimizing kalman filter |
| topic | Kalman filter multi-object tracking movement behavior multi-pedestrian tracking AFM |
| url | https://ieeexplore.ieee.org/document/9941077/ |
| work_keys_str_mv | AT jianhongyan multipedestriantrackingincrowdedscenesbymodelingmovementbehaviorandoptimizingkalmanfilter AT shuailingdu multipedestriantrackingincrowdedscenesbymodelingmovementbehaviorandoptimizingkalmanfilter AT yananwang multipedestriantrackingincrowdedscenesbymodelingmovementbehaviorandoptimizingkalmanfilter |