Automated Video Surveillance Anomaly Detection with a Deep Reinforcement Learning Framework

Nishant Deheriya; Dr. Devendra Bajpai; Dr. P. K. Sharma

doi:10.32628/CSEIT251112196

Authors

Nishant Deheriya Department of Computer Science & Engineering, NRI Institute of Research & Technology, Bhopal, Madhya Pradesh, India Author
Dr. Devendra Bajpai Department of Computer Science & Engineering, NRI Institute of Research & Technology, Bhopal, Madhya Pradesh, India Author
Dr. P. K. Sharma Principal, NRI Institute of Research & Technology, Bhopal, Madhya Pradesh, India Author

DOI:

https://doi.org/10.32628/CSEIT251112196

Keywords:

Artificial Intelligence, Deep learning, DQN, Reinforcement learning, Neural Network

Abstract

Anomaly detection in automated video surveillance is regarded as one of the most essential challenges to address, with the objective of identifying various real-world irregularities. This paper presents an innovative method for anomaly detection utilizing deep reinforcement learning. In recent years, deep reinforcement learning has demonstrated considerable success across diverse applications involving complex data, such as robotics and gaming, by emulating human learning through experience. Typically, state-of-the-art techniques categorize a video as either normal or abnormal without identifying the precise location of the anomaly within the input video, primarily due to the use of unlabeled clip-level data during training. Our focus is on adapting prioritized Dueling deep Q-networks to tackle the anomaly detection issue. This model is designed to assess anomalies in video clips by leveraging video-level labels to enhance detection accuracy.

Downloads

Download data is not yet available.

References

Seyed Mostafa Hejazi, Charith Abhayaratne, Handcrafted localized phase features for human action recognition, Image and Vision Computing,Volume 123,2022,104465, ISSN 0262-8856, https://doi.org/10.1016/j.imavis.2022.104465. DOI: https://doi.org/10.1016/j.imavis.2022.104465

Ali Khaleghi and Mohammad Shahram Moin. Improved anomaly detection in surveillance videos based on a deep learning method. 2018 8th Conference of AI & Robotics and 10th RoboCup Iranopen International Symposium (IRANOPEN), IEEE, pages 73–81, 2018. https://doi.org/10.1109/rios.2018.8406634. DOI: https://doi.org/10.1109/RIOS.2018.8406634

Yong Shean Chong and Yong Haur Tay. Abnormal event detection in videos using spatiotemporal autoencoder. International Symposium on Neural Networks, Springer, pages 189–196, 2017. https://doi.org/10.1109/ascc.2015.7244871. DOI: https://doi.org/10.1007/978-3-319-59081-3_23

M. Hasan, J. Choi, J. Neumann, A. K. RoyChowdhury, and L. S. Davis. Learning temporal regularity in video sequences. CVPR, 2016. https://doi.org/10.1109/cvpr.2016.86. DOI: https://doi.org/10.1109/CVPR.2016.86

Waqas Sultani, Chen Chen, and Mubarak Shah. Realworld anomaly detection in surveillance videos. Center for Research in Computer Vision (CRCV), 2018. https://doi.org/10.1109/cvpr.2018.00678. DOI: https://doi.org/10.1109/CVPR.2018.00678

Min-hwan Oh, Garud Iyengar. Sequential Anomaly Detection using Inverse Reinforcement Learning. arXiv:2004.10398v1 [cs.LG], 2020.

Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot and Nando de Freitas. Dueling Network Architectures for Deep Reinforcement Learning, arXiv:1511.06581v3[cs.LG], 2016.

V. Mnih, K. Kavukcuoglu, D. Silver, A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski, et al. Human-level control through deep reinforcement learning, Nature, 518(7540):529–533, 2015. DOI: https://doi.org/10.1038/nature14236

X. Wang et al., "Deep Reinforcement Learning: A Survey," in IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 4, pp. 5064-5078, April 2024, doi: 10.1109/TNNLS.2022.3207346. DOI: https://doi.org/10.1109/TNNLS.2022.3207346

Rao, P. V. ., B., V. ., Manjeet, M., Kumar, A. ., Mittal, M. ., Verma, A. ., & Dhabliya, D. . (2024). Deep Reinforcement Learning: Bridging the Gap with Neural Networks. International Journal of Intelligent Systems and Applications in Engineering, 12(15s), 576 –. Retrieved from https://www.ijisae.org/index.php/IJISAE/article/view/4792.

Anchal Pathak, Ruchi Jayaswal, Smita Mahajan. Exploring Deep Learning Techniques for Abnormality Detection: A Comparative Analysis on UCF Crime Dataset. International Journal of Intelligent Systems and Applications in Engineering, IJISAE, 2024, 12(3), 392–401.

Kim S, Kim TS, Lee WH. Accelerating 3D Convolutional Neural Network with Channel Bottleneck Module for EEG-Based Emotion Recognition. Sensors (Basel). 2022 Sep 8;22(18):6813. doi: 10.3390/s22186813. PMID: 36146160; PMCID: PMC9500982. DOI: https://doi.org/10.3390/s22186813

X. Zhang, Y. Yang, B. Li, M. Li, T. Li and J. Zhang, "Research on Activation Functions in Machine Learning Based Network Coding," 2023 International Conference on Networking and Network Applications (NaNA), Qingdao, China, 2023, pp. 307-312, doi: 10.1109/NaNA60121.2023.00058. DOI: https://doi.org/10.1109/NaNA60121.2023.00058

C. Lu, J. Shi, and J. Jia. Abnormal event detection at 150 fps in matlab. ICCV, 2013. DOI: https://doi.org/10.1109/ICCV.2013.338