Abnormal Behavior Recognition Method Based on Fine-Grained Human Dynamic Skeleton Features

Chenyue Xu; Rong Wang

doi:10.54097/ca5q2416

Authors

Chenyue Xu
Rong Wang

DOI:

https://doi.org/10.54097/ca5q2416

Keywords:

Abnormal Behavior Recognition, Dynamic Skeletal Features, Fine-Grained Feature Extraction

Abstract

To address the insufficiency of feature extraction in existing video anomaly recognition methods, this paper proposes an improved graph-embedded pose clustering-based abnormal behavior recognition method. By employing fine-grained feature extraction, it enhances information representation capabilities and improves algorithm robustness. The framework is structured as follows: First, spatial and channel reconstruction convolutions are integrated into a Deep Residual Network backbone, effectively eliminating spatial-channel redundancy in extracted features while reducing computational complexity, thereby enhancing operational efficiency. Second, a hierarchical decomposed graph convolutional network (modified from spatio-temporal graph convolutional networks) is implemented for dynamic skeleton feature extraction, coupled with an attention-guided hierarchical aggregation module for multi-level feature fusion. Evaluations on ShanghaiTech and NTU-RGB+D datasets demonstrate detection accuracies of 76.4% and 74.6% respectively, validating the method's effectiveness.

Downloads

Download data is not yet available.

References

[1] Verma, Kamal Kant, Brij Mohan Singh, and Amit Dixit. "A review of supervised and unsupervised machine learning techniques for suspicious behavior recognition in intelligent surveillance system." International Journal of Information Technology 14.1 (2022): 397-410.

[2] Pogadadanda, Vikas, et al. "Abnormal activity recognition on surveillance: a review." 2023 third international conference on artificial intelligence and smart energy (ICAIS). IEEE, 2023.

[3] Qiu, Yuting, James Meng, and B. J. J. I. Li. "Automated falls detection using visual anomaly detection and pose-based approaches: experimental review and evaluation." J ISSN 2766 (2024): 2276.

[4] Duong, Huu-Thanh, Viet-Tuan Le, and Vinh Truong Hoang. "Deep learning-based anomaly detection in video surveillance: A survey." Sensors 23.11 (2023): 5024.

[5] Sato, Fumiaki, Ryo Hachiuma, and Taiki Sekii. "Prompt-guided zero-shot anomaly action recognition using pretrained deep skeleton features." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023.

[6] Cho, MyeongAh, et al. "Unsupervised video anomaly detection via normalizing flows with implicit latent features." Pattern Recognition 129 (2022): 108703.

[7] Coşar, Serhan, et al. "Toward abnormal trajectory and event detection in video surveillance." IEEE Transactions on Circuits and Systems for Video Technology 27.3 (2016): 683-695.

[8] Chen, Chunyu, Yu Shao, and Xiaojun Bi. "Detection of anomalous crowd behavior based on the acceleration feature." IEEE sensors journal 15.12 (2015): 7252-7261.

[9] Li, Jiafeng, Ying Wen, and Lianghua He. "Scconv: Spatial and channel reconstruction convolution for feature redundancy." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023.

[10] Lee, Jungho, et al. "Hierarchically decomposed graph convolutional networks for skeleton-based action recognition." Proceedings of the IEEE/CVF international conference on computer vision. 2023.

[11] Lee, Minhyeok, et al. "Edgeconv with attention module for monocular depth estimation." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2022.

[12] Siemon, Mia, et al. "Bounding boxes and probabilistic graphical models: video anomaly detection simplified." arXiv preprint arXiv:2407.06000 (2024).

[13] Le, Viet-Tuan, and Yong-Guk Kim. "Attention-based residual autoencoder for video anomaly detection." Applied Intelligence 53.3 (2023): 3240-3254.