Vi-SAFE: A Spatial-Temporal Framework for Efficient Violence Detection in Public Surveillance
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911157960310784 |
|---|---|
| author | Chang, Ligang Xu, Shengkai Shen, Liangchang Xu, Binhan Wang, Junqiao Shi, Tianyu Du, Yanhui |
| author_facet | Chang, Ligang Xu, Shengkai Shen, Liangchang Xu, Binhan Wang, Junqiao Shi, Tianyu Du, Yanhui |
| contents | Violence detection in public surveillance is critical for public safety. This study addresses challenges such as small-scale targets, complex environments, and real-time temporal analysis. We propose Vi-SAFE, a spatial-temporal framework that integrates an enhanced YOLOv8 with a Temporal Segment Network (TSN) for video surveillance. The YOLOv8 model is optimized with GhostNetV3 as a lightweight backbone, an exponential moving average (EMA) attention mechanism, and pruning to reduce computational cost while maintaining accuracy. YOLOv8 and TSN are trained separately on pedestrian and violence datasets, where YOLOv8 extracts human regions and TSN performs binary classification of violent behavior. Experiments on the RWF-2000 dataset show that Vi-SAFE achieves an accuracy of 0.88, surpassing TSN alone (0.77) and outperforming existing methods in both accuracy and efficiency, demonstrating its effectiveness for public safety surveillance. Code is available at https://anonymous.4open.science/r/Vi-SAFE-3B42/README.md. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13210 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vi-SAFE: A Spatial-Temporal Framework for Efficient Violence Detection in Public Surveillance Chang, Ligang Xu, Shengkai Shen, Liangchang Xu, Binhan Wang, Junqiao Shi, Tianyu Du, Yanhui Computer Vision and Pattern Recognition I.2.10; I.4.8 Violence detection in public surveillance is critical for public safety. This study addresses challenges such as small-scale targets, complex environments, and real-time temporal analysis. We propose Vi-SAFE, a spatial-temporal framework that integrates an enhanced YOLOv8 with a Temporal Segment Network (TSN) for video surveillance. The YOLOv8 model is optimized with GhostNetV3 as a lightweight backbone, an exponential moving average (EMA) attention mechanism, and pruning to reduce computational cost while maintaining accuracy. YOLOv8 and TSN are trained separately on pedestrian and violence datasets, where YOLOv8 extracts human regions and TSN performs binary classification of violent behavior. Experiments on the RWF-2000 dataset show that Vi-SAFE achieves an accuracy of 0.88, surpassing TSN alone (0.77) and outperforming existing methods in both accuracy and efficiency, demonstrating its effectiveness for public safety surveillance. Code is available at https://anonymous.4open.science/r/Vi-SAFE-3B42/README.md. |
| title | Vi-SAFE: A Spatial-Temporal Framework for Efficient Violence Detection in Public Surveillance |
| topic | Computer Vision and Pattern Recognition I.2.10; I.4.8 |
| url | https://arxiv.org/abs/2509.13210 |