Real-Time Criminal Activity Detection Using an Intelligent Video Surveillance System Based on Deep Learning Techniques
DOI:
https://doi.org/10.63252/JCBECA/2.3.2025Keywords:
Criminal activity detection, Surveillance system, Real-time monitoring, Computer vision, Deep learning, Motion analysis, Security alerts, Video recordingAbstract
The advanced, real-time surveillance system for detecting and analyzing criminal activities in video streams. The proposed solution leverages deep learning, computer vision, and motion analysis to identify suspicious behaviors such as fighting, theft, break-ins, and vandalism. The backend, built in Python, utilizes state-of-the-art CNN-LSTM models, while a Next.js-based frontend provides an interactive dashboard for live monitoring, analytics, and alert management. The system features automated incident recording, emergency SOS functionality, and comprehensive analytics, demonstrating high accuracy and practical viability in diverse security environments.
References
[1] A. Zafar, “Untargeted white-box adversarial attacks on real-time deep learning based COVID-19 monitoring face mask detection system,” Multimedia Tools Appl., vol. 83, no. 1, pp. 23783–23899, 2024.
[2] S. Sultani, C. Chen, and M. Shah, "Real-World Anomaly Detection in Surveillance Videos," Proc. CVPR, 2018.
[3] J. Carreira and A. Zisserman, "Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset," Proc. CVPR, 2017.
[4] J.Redmon et al., "YOLOv3: An Incremental Improvement," arXiv:1804.02767, 2018.
[5] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," NIPS, 2012.
[6] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2014, arXiv:1409.1556
[7] A. K. Jain, R. P. W. Duin, and J. Mao, “Statistical pattern recognition: A review,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 22, no. 1, pp. 4–37, Jan. 2000.
[8] S. Feng, C. Shen, N. Xia, W. Song, M. Fan, and B. J. Cowling, “Rational use of face masks in the COVID-19 pandemic,” Lancet Respiratory Med., vol. 8, no. 5, pp. 434–436, May 2020.
[9] Advice on the Use of Masks in the Context of COVID-19: Interim Guidance, World Health Organization, Geneva, Switzerland, Jun. 2020.
[10] A. Zafar, “Untargeted white-box adversarial attacks on real-time deep learning based COVID-19 monitoring face mask detection system,” Multimedia Tools Appl., vol. 83, no. 1, pp. 23783–23899, 2024.
[11] J. Liu, C. Liu, M. Li, Xiong, T. Zhang, and H. Liu, “High frequency spoofing based adversarial attacks on deep learning for face mask detection and social distance attack,” Comput. Secur., vol. 132, Sep. 2023, Art no. 103087.
[12] X. Chen, C. Liu, B. Li, K. Lu, and D. Song, “Targeted backdoor attacks on deep learning systems using data poisoning,” 2017, arXiv:1712.05526.
[13] M. Khosravy, K. Nakamura, Y. Hirose, N. Nitta, and N. Babaguchi, “Model inversion attack: Analysis under gray-box scenario on deep learning based face recognition system,” KSII Trans. Internet Inf. Syst., vol. 15, no. 3, pp. 1100–1118, 2021.
[14] Y. Ji, X. Zhang, J. Xi, X. Luo, and T. Wang, “Model-reuse attacks on deep learning systems,” in Proc. ACM SIGSAC Conf. Comput. Commun. Secur., Oct. 2018, pp. 349–363.
[15] X. Ren, T. Zheng, Z. Qin, and X. Liu, “Adversarial attacks and defenses in deep learning for computer vision: A survey,” Information Fusion, vol. 103, no. 3, pp. 346–360, Mar. 2024.
[16] S. L. S. Nepane, S. Paul, C. O. S. V. Krishnamurthy, A. K. Roy-Chowdhury, and A. Swami, “Adversarial perturbations against real-time video classification systems,” 2018, arXiv:1807.00458.
[17] S. Thys, W. R. Ranst, and T. Goedeme, “Foolingautomated surveillance cameras: Adversarial patches to attack person detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), 2019, pp. 1–6
[18] S. Li, J. Liu, and W. Luo, “Detecting masked faces in the wild with LLE-CNNs,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 2682–2690.
