Education, Science, Technology, Innovation and Life
Open Access
Sign In

Empowering Security Surveillance with Machine Vision: A Survey of Anomaly Detection Technologies

Download as PDF

DOI: 10.23977/jaip.2025.080320 | Downloads: 4 | Views: 92

Author(s)

Peng Yin 1

Affiliation(s)

1 School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, China

Corresponding Author

Peng Yin

ABSTRACT

Addressing the pain points of low efficiency, high missed detection rate, and high false alarm rate in manual monitoring for security surveillance, this paper systematically surveys the application of machine vision in anomaly detection. It first sorts out the full-process technical architecture from object detection and tracking to behavior judgment, focusing on analyzing the detection logic of three typical abnormal behaviors: climbing, loitering, and boundary crossing. Secondly, it details the characteristics and application scenarios of two core datasets, UCF-Crime and XD-Violence. Furthermore, it analyzes the impact of complex environments such as insufficient illumination and person occlusion on detection accuracy and corresponding countermeasures. Finally, it discusses the collaborative optimization path between privacy protection and security efficiency, and looks forward to future development directions such as multimodal fusion and common sense reasoning, providing references for the research, development, and implementation of intelligent security systems. 

KEYWORDS

Machine Vision; Security Surveillance; Anomaly Detection; Object Tracking; UCF-Crime Dataset; Privacy Protection

CITE THIS PAPER

Peng Yin, Empowering Security Surveillance with Machine Vision: A Survey of Anomaly Detection Technologies. Journal of Artificial Intelligence Practice (2025) Vol. 8: 160-165. DOI: http://dx.doi.org/10.23977/jaip.2025.080320.

REFERENCES

[1] Mohindru, Vandana, and Shafali Singla. "A review of anomaly detection techniques using computer vision." The International Conference on Recent Innovations in Computing. Singapore: Springer Singapore, 2020.
[2] Madan, Neelu, et al. "Self-supervised masked convolutional transformer block for anomaly detection." IEEE Transactions on Pattern Analysis and Machine Intelligence 46.1 (2023): 525-542.
[3] Hasan, Mahmudul, et al. "Learning temporal regularity in video sequences." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
[4] Pillai, Gargi V., Ashish Verma, and Debashis Sen. "Transformer based self-context aware prediction for few-shot anomaly detection in videos." 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022.
[5] Yu, Jiawei, et al. "Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows." arxiv preprint arxiv:2111.07677 (2021).
[6] Latapie, Hugo. "Common sense is all you need." arxiv preprint arxiv:2501.06642 (2025).

Downloads: 16401
Visits: 565677

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.