A data fusion-based method for pedestrian detection and flow statistics across different crowd densities
Accurate tracking and statistics analysis of pedestrian flow have wide applications in public scenarios. However, the conventional tracking-by-detection approaches are prone to missing individuals in densely populated or poorly lit environments. This study introduces a pedestrian detection and flow...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-03-01
|
| Series: | Journal of Safety Science and Resilience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666449624000665 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087410686558208 |
|---|---|
| author | Ranpeng Wang Hang Gao Yi Liu |
| author_facet | Ranpeng Wang Hang Gao Yi Liu |
| author_sort | Ranpeng Wang |
| collection | DOAJ |
| description | Accurate tracking and statistics analysis of pedestrian flow have wide applications in public scenarios. However, the conventional tracking-by-detection approaches are prone to missing individuals in densely populated or poorly lit environments. This study introduces a pedestrian detection and flow statistics method based on data fusion, which effectively tracks pedestrians across varying crowd densities. The proposed method amalgamates object detection strategies with crowd counting technique to determine the locations of all pedestrians. By observing the coordinates of pedestrians' foot points, this approach assesses the interaction dynamics between the movement trajectories of pedestrians and designated spatial areas, thereby enabling the collection of flow statistics. Experimental results indicate that the proposed method identifies 2.7 times more pedestrians than object detection methods alone and decreases false positives by 58% compared to crowd counting techniques in crowded settings. In conclusion, the proposed method exhibits considerable promise for achieving accurate pedestrian detection and flow analysis. |
| format | Article |
| id | doaj-art-abc4faa038ea4b7da0b1e13a71f040d7 |
| institution | Kabale University |
| issn | 2666-4496 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Safety Science and Resilience |
| spelling | doaj-art-abc4faa038ea4b7da0b1e13a71f040d72025-02-06T05:12:52ZengKeAi Communications Co., Ltd.Journal of Safety Science and Resilience2666-44962025-03-0161105113A data fusion-based method for pedestrian detection and flow statistics across different crowd densitiesRanpeng Wang0Hang Gao1Yi Liu2Institute of Public Safety Research, School of Safety Science, Tsinghua University, Beijing, 100084, ChinaCollege of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, 300450, ChinaInstitute of Public Safety Research, School of Safety Science, Tsinghua University, Beijing, 100084, China; Corresponding author.Accurate tracking and statistics analysis of pedestrian flow have wide applications in public scenarios. However, the conventional tracking-by-detection approaches are prone to missing individuals in densely populated or poorly lit environments. This study introduces a pedestrian detection and flow statistics method based on data fusion, which effectively tracks pedestrians across varying crowd densities. The proposed method amalgamates object detection strategies with crowd counting technique to determine the locations of all pedestrians. By observing the coordinates of pedestrians' foot points, this approach assesses the interaction dynamics between the movement trajectories of pedestrians and designated spatial areas, thereby enabling the collection of flow statistics. Experimental results indicate that the proposed method identifies 2.7 times more pedestrians than object detection methods alone and decreases false positives by 58% compared to crowd counting techniques in crowded settings. In conclusion, the proposed method exhibits considerable promise for achieving accurate pedestrian detection and flow analysis.http://www.sciencedirect.com/science/article/pii/S2666449624000665Object detectionCrowd countingData fusionPedestrian flow statistics |
| spellingShingle | Ranpeng Wang Hang Gao Yi Liu A data fusion-based method for pedestrian detection and flow statistics across different crowd densities Journal of Safety Science and Resilience Object detection Crowd counting Data fusion Pedestrian flow statistics |
| title | A data fusion-based method for pedestrian detection and flow statistics across different crowd densities |
| title_full | A data fusion-based method for pedestrian detection and flow statistics across different crowd densities |
| title_fullStr | A data fusion-based method for pedestrian detection and flow statistics across different crowd densities |
| title_full_unstemmed | A data fusion-based method for pedestrian detection and flow statistics across different crowd densities |
| title_short | A data fusion-based method for pedestrian detection and flow statistics across different crowd densities |
| title_sort | data fusion based method for pedestrian detection and flow statistics across different crowd densities |
| topic | Object detection Crowd counting Data fusion Pedestrian flow statistics |
| url | http://www.sciencedirect.com/science/article/pii/S2666449624000665 |
| work_keys_str_mv | AT ranpengwang adatafusionbasedmethodforpedestriandetectionandflowstatisticsacrossdifferentcrowddensities AT hanggao adatafusionbasedmethodforpedestriandetectionandflowstatisticsacrossdifferentcrowddensities AT yiliu adatafusionbasedmethodforpedestriandetectionandflowstatisticsacrossdifferentcrowddensities AT ranpengwang datafusionbasedmethodforpedestriandetectionandflowstatisticsacrossdifferentcrowddensities AT hanggao datafusionbasedmethodforpedestriandetectionandflowstatisticsacrossdifferentcrowddensities AT yiliu datafusionbasedmethodforpedestriandetectionandflowstatisticsacrossdifferentcrowddensities |