THEORY AND APPLICATIONS OF VIDEO ABNORMAL BEHAVIOR DETECTION

Authors

  • PeiChen Wu School of Information Network Security, People's Public Security University of China, Beijing 100038, China
  • DengBin Xu School of Information Network Security, People's Public Security University of China, Beijing 100038, China
  • LiNing Yuan (Corresponding Author) School of Public Security Big Data Modern Industry, Guangxi Police College, Nanning 530028, Guangxi, China

Keywords:

Abnormal behavior detection, Deep learning, Fully unsupervised, Multimodal features

Abstract

Video abnormal behavior detection is a research hotspot in the field of computer vision. By extracting the spatiotemporal characteristics of video content, we can determine whether there are abnormal events and their types in the video, and identify the location and time of the abnormal events. Based on supervised/unsupervised learning, this paper systematically combs and summarizes the existing video abnormal behavior detection methods. Starting from the current mainstream modeling idea, the supervision method is described in detail, and the completely unsupervised method is introduced to train the model. The network architectures of different models are compared, and the characteristics of various anomaly detection models in terms of test data sets, usage scenarios, advantages and limitations are summarized. Then, through common evaluation criteria such as frame level standard and pixel level standard, the model is compared and the performance is evaluated. At the same time, the performance of different methods is compared within the class, and the results are analyzed and summarized in depth. Finally, the future development direction is outlined briefly, and the development trend of video anomaly detection from virtual composite dataset, multi-modal large-scale model to lightweight model is discussed.

References

[1] Yao Huiling, Xing HU. A survey of video violence detection. Cyber-Physical Systems. 2023, 9(1): 1-24.

[2] S.Roshan, G. Srivathsan, K. Deepak, S. chandrakala, et al. Violence detection in automated video surveillance: Recent trends and comparative studies. The Cognitive Approach in Cloud Computing and Internet of Things Technologies for Surveillance Tracking Systems. 2020: 157-171.

[3] Bharathkumar Ramachandra , Michael Jones , Ranga Raju Vatsavai . A survey of single-scene video anomaly detection. IEEE on pattern analysis and machine intelligence, 2020, 44(5): 2293-2312.

[4] Kamal Kant Verma , Brij Mohan Singh , Amit Dixit . A review of supervised and unsupervised machine learning techniques for suspicious behavior recognition in intelligent surveillance system. International Journal of Information Technology, 2019: 1-14.

[5] Hu Chunyu, Chen Yiqiang, Hu Lisha, et al. A novel random forests based class incremental learning method for activity recognition. Pattern Recognition, 2018, 78: 277-290.

[6] Xiao Qinkun , Song Ren. Action recognition based on hierarchical dynamic Bayesian network. Multimedia Tools and Applications, 2018, 77(6): 6955-6968.

[7] Sok Pichleap , Xiao Ting , Azeze Yohannes , et al. Activity Recognition for Incomplete Spinal Cord Injury Subjects using Hidden Markov Models. IEEE Sensors Journal, 2018, 18(15): 6369-6374.

[8] Bilal M'hamed Abidine , Lamya Fergani , Belkacem Fergani , et al. The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition. Pattern Analysis and Applications, 2018, 21(1): 119-138.

[9] Sun Xiaohu, Yu Axiang, Shen Xulin, et al. Abnormal Behavior Recognition Based on Hybrid Attention Mechanism. Computer Engineering and Applications, 2023, 59(5): 140-147.

[10] Liu Yang, Liu Jiang, Zhao Mengyang , et al. Learning appearance-motion normality for video anomaly detection. Proceedings of the 2022 IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2022: 1-6.

[11] Li Daoheng, Nie Xiushan, Li Xiaofeng, et al. Context-related video anomaly detection via generative adversarial network. Pattern Recognition Letters, 2022, 156: 183-189.

[12] Lee Joo Yeon, NAM Woo Jeoung , Lee Seong Whan . Multi-contextual predictions with vision transformer for video anomaly detection. Proceedings of the 26th International Conference on Pattern Recognition (ICPR). Piscataway: IEEE, 2022: 1012-1018.

[13] Tarik Alafif , Anas Hadi , Manal Allahyani , et al. Hybrid classifiers for spatio-temporal abnormal behavior detection, tracking, and recognition in massive Hajj crowds. Elecronics, 2023, 12(5): 1165.

[14] Anas Al-lahham , Nurbek Tastan , Zaigham Zaheer , et al.A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection. arXiv preprint arXiv: 2310.17650, 2024.

[15] WONG Sebastien C , Stamatescu Victor , GATT Adam , et al. Track Everything: Limiting Prior Knowledge in Online MultiObject Recognition. IEEE Transactions on Image Processing, 2017, 26(10): 4669-4683.

[16] Kong Xiangjie , Ma Kai , Hou Shen, et al. Human interactive behavior: A bibliographic review. IEEE Access, 2018, 7: 4611-4628.

[17] Bahram Mohammadi , Mahmood Fathy , Mohammad Sabokrou . Image/video deep anomaly detection: A survey. arXiv preprint arXiv: 2103.01739, 2021.

[18] Xu Dan, Yan Yan, Ricci Elisa, et al. Detecting anomalous events in videos by learning deep representations of appearance and motion. Computer Vision and Image Understanding, 2017, 156: 117-127.

[19] Sabokrou Mohammad , Fathy Mahmood , Hoseini Mojtaba

Downloads

Published

2024-01-01

Issue

Vol. 6 No. 2 (2024)

Section

Research Article

DOI:

https://doi.org/10.61784/jcsee3006

How to Cite

Wu, P., Xu, D., Yuan, L. (2024). Theory And Applications Of Video Abnormal Behavior Detection. Eurasia Journal of Science and Technology, 6(2), 29-45. https://doi.org/10.61784/jcsee3006