Article Details

Title · Authors · Abstract · Keywords · DOI · References

Research on Abnormal Behavior Detection Based on Improved YOLOv5-pose in Complex Scenes

CUI Yue, YANG Wang, WANG Mingqi, LI Zhenxin

(School of Information Engineering, Xinjiang Institute of Technology, Aksu 843100, China)

Section:Artificial Intelligence · 2025, Vol. 9, No. 7 · Pages:71-75,82 · 2096-4706(2025)07-0071-06 · CLC number:TP391.4 · Document code:A · DOI:10.19850/j.cnki.2096-4706.2025.07.013 · Published:2025-04-10

Abstract

This paper proposes an abnormal behavior detection algorithm based on the improved YOLOv5-pose in complex scenes. It uses FPT to replace the FPN+PAN module, enabling the feature maps to achieve global and local interaction across scales and spaces, and improving the accuracy of joint point detection. In the Neck module, a skip connection structure is employed to effectively fuse the information of the input features and the multi-scale features output through the network, improving the ability to capture detailed information and enhancing the accuracy of detecting occluded joint points. Experimental results show that the improved algorithm achieves an average accuracy of 99.5% on the CrowdPose dataset, which is 2.4% higher than that of the original model. The improved model not only has higher detection accuracy, but also significantly improves the recognition performance of small targets.

Keywords

YOLOv5-pose; behavior recognition; joint point detection; FPT; skip connection

References

  1. [1] Huang Duo, Ying Na, Cai Zhedong Optimization of Multi person Attitude Detection Algorithm Based on Reinforcement Learning [J]. Computer Applications and Software, 2019, 36 (4): 186-191
  2. [2] CHENG B,XIAO B,WANG J,et al. HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle:IEEE,2020:5386-5395.
  3. [3] Shi Yuexiang, Xu Xiangqi Human pose estimation based on improved DenseNet network [J]. Control and Decision, 2021, 36 (5): 1206-1212
  4. [4] KE L,CHANG M C,QI H,et al. DetPoseNet: Improving Multi-Person Pose Estimation via Coarse-Pose Filtering [J].IEEE Transactions on Image Processing,2022,31:2782-2795.
  5. [5] Zhu Liping, Tang Liang, Zhu Kaijie, etc Multi object human behavior estimation in motion scenarios [J]. Computer Engineering and Design, 2023, 44 (7): 2156-2162
  6. [6] CHEN Y,ZHANG J,WANG Y. Human Action Recognition and Analysis Methods Based on OpenPose and Deep Learning [C]//2024 International Conference on Integrated Circuits and Communication Systems (ICICACS).Raichur:IEEE,2024:1-5.
  7. [7] Hou Yudi, Yang Hongchen, Cai Nengbin A Fighting Behavior Detection Model in Video Based on Improved YOLOv5s [J/OL]. Criminal Technology, 2024:1-7 [2024-10-26] https://doi.org/10.16467/j.1008-3650.2024.0043.
  8. [8] MAJI D,NAGORI S,MATHEW M,et al. YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans:IEEE,2022:2637-2646.
  9. [9] ZHANG D,ZHANG H W,TANG J H,et al. Feature Pyramid Transformer [C]//Proceedings of the European Conference on Computer Vision.Glasgow:Springer,2020:323-339.
  10. [10] WANG X L,GIRSHICK R,GUPTA A,et al. Non-Local Neural Networks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:7794-7803.
  11. [11] Wang Lin, Li Conghui Pedestrian attribute recognition based on multi-level attention skip connection network [J]. Computer Engineering, 2021, 47 (2): 314-320
  12. [12] LI J F,WANG C,ZHU H,et al. CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE,2019:10863-10872.

About the authors

Cui Yue (1998-), female, Manchu, from Benxi, Liaoning, teaching assistant, master's degree, research direction: image processing, big data, and intelligent information processing; Yang Wang (1995-), male, Han ethnicity, from Wuwei, Gansu, teaching assistant, master's degree, research direction: computer vision, intelligent machinery and robots.