An Intelligent Deep Learning-Based Framework for Suspicious Criminal Activity Detection in Surveillance Systems: Design, Implementation, and Evaluation
DOI:
https://doi.org/10.70454/JRIST.2025.10105Keywords:
Suspicious Activity Detection, Video Surveillance, Deep Learning, Transformer, Edge Computing, Ethical AIAbstract
The rapid expansion of smart cities and widespread deployment of surveillance infrastructure have highlighted the need for intelligent systems capable of detecting suspicious and criminal activities in real-time. Traditional surveillance systems primarily rely on manual monitoring, which is error-prone and unable to scale with the increasing volume of video data. To address these challenges, this paper presents a novel deep learning-based framework that integrates convolutional neural networks (CNNs) for spatial feature extraction with Transformer encoders for temporal sequence modeling. The proposed system effectively captures both short-term motion anomalies and long-term behavioral patterns, thereby enhancing detection accuracy in diverse environments. Experimental evaluations on benchmark datasets such as UCF-Crime and Avenue demonstrate significant improvements over state-of-the-art approaches across metrics including accuracy, F1 score, and AUC. Furthermore, edge deployment on NVIDIA Jetson Xavier NX confirms the framework’s viability for real-time operations, achieving sub-300 ms inference latency without compromising detection quality. The framework is modular, interpretable, and scalable, making it suitable for integration into smart city surveillance ecosystems. In addition to technical contributions, ethical considerations such as fairness, transparency, and privacy are addressed to ensure responsible deployment of automated surveillance systems.
References
[1] Samet Akcay, Amir Atapour-Abarghouei, and Toby P Breckon. “GANomaly: Semi- Supervised Anomaly Detection via Adversarial Training”. In: Asian Conference on Computer Vision (2018).
[2] H. A. Alberry, M. E. Khalifa, and A. Taha. “Abnormal Behavior Detection in Surveil- lance Systems Using a Hybrid EfficientNet-Transformer Model”. In: Statistics, Opti- mization & Information Computing 13.4 (2025), pp. 1610–1622. DOI: 10.19139/soic- 2310-5070-2259.
[3] Bahareh R. Ardabili, Ali D. Pazho, and Ghasem A. Noghre. “Understanding Policy and Technical Aspects of AI-enabled Smart Video Surveillance to Address Public Safety”. In: Computational Urban Science 3 (2023), p. 21. DOI: 10.1007/s43762-023-00097-8.
[4] R. Binns et al. “Algorithmic Accountability and Transparency”. In: ACM Computing Surveys (2018).
[5] Alexey Dosovitskiy et al. “An image is worth 16x16 words: Transformers for im- age recognition at scale”. In: International Conference on Learning Representations (ICLR) (2021).
[6] Mahmudul Hasan et al. “Learning Temporal Regularity in Video Sequences”. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 2016.
[7] Altaf Hussain et al. “Shots Segmentation-Based Optimized Dual-Stream Framework for Robust Human Activity Recognition in Surveillance Video”. In: Alexandria Engi- neering Journal 91 (2024), pp. 632–647. DOI: 10.1016/j.aej.2023.11.017.
[8] Radu Tudor Ionescu et al. “Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video”. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 2019.
[9] Sabah Abdulazeez Jebur et al. “A Scalable and Generalised Deep Learning Framework for Anomaly Detection in Surveillance Videos”. In: International Journal of Intelligent Systems (2025), pp. 1–22. DOI: 10.1155/int/1947582.
[10] Hyun Jeong, Minjun Lee, and K. Kim. “Multimodal Anomaly Detection for Urban Surveillance Using Audio-Visual Fusion”. In: IEEE Transactions on Multimedia (2023).
[11] Jae-hyeok Jeong et al. “Intelligent Complementary Multi-Modal Fusion for Anomaly Surveillance and Security System”. In: Sensors 23.22 (2023), p. 9214. DOI: 10.3390/ s23229214.
[12] S. Kim et al. “Real-Time Anomaly Detection Using MobileNet on Edge Devices”. In:
Sensors (2021).
[13] Wen Liu et al. “Future Frame Prediction for Anomaly Detection – A New Baseline”. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 2018.
[14] Cewu Lu, Jian Shi, and Jiaya Jia. “Abnormal event detection at 150 fps in MAT- LAB”. In: Proceedings of the IEEE international conference on computer vision (2013),
pp. 2720–2727.
[15] Asif Mehmood. “LightAnomalyNet: A Lightweight Framework for Efficient Abnormal Behavior Detection”. In: Sensors 21.24 (2021), p. 8501. DOI: 10.3390/s21248501.
[16] Md. Muktadir Mukto et al. “Design of a Real-Time Crime Monitoring System Us- ing Deep Learning Techniques”. In: Intelligent Systems with Applications 21 (2024),
p. 200311. DOI: 10.1016/j.iswa.2023.200311.
[17] D. R. Patrikar and M. R. Parate. “Anomaly Detection Using Edge Computing in Video Surveillance System: Review”. In: International Journal of Multimedia Information Retrieval 11 (2022), pp. 85–110. DOI: 10.1007/s13735-022-00227-8.
[18] F. Perazzi et al. “A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation”. In: 2016 IEEE Conference on Computer Vision and Pattern Recogni- tion (CVPR). 2016, pp. 724–732. DOI: 10.1109/CVPR.2016.85.
[19] Bharathkumar Ramachandra, Michael J. Jones, and Ranga Raju Vatsavai. “A Survey of Single-Scene Video Anomaly Detection”. In: IEEE Transactions on Pattern Analysis and Machine Intelligence 44.5 (2022), pp. 2293–2312. DOI: 10.1109/TPAMI.2020.
3040591.
[20] Mahdyar Ravanbakhsh et al. “Abnormal Event Detection in Videos Using Genera- tive Adversarial Nets”. In: 2017 IEEE International Conference on Image Processing (ICIP). 2017, pp. 1577–1581. DOI: 10.1109/ICIP.2017.8296547.
[21] Mohammad Sabokrou et al. “Deep-anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes”. In: Computer Vision and Image Under- standing 172 (2018), pp. 88–97. DOI: 10.1016/j.cviu.2018.02.006.
[22] Kishan Bhushan Sahay et al. “A Real Time Crime Scene Intelligent Video Surveil- lance Systems in Violence Detection Framework Using Deep Learning Techniques”. In: Computers and Electrical Engineering 103 (2022), p. 108319. DOI: 10.1016/j. compeleceng.2022.108319.
[23] Lei Shi et al. “Two-Stream Adaptive Graph Convolutional Networks for Skeleton- Based Action Recognition”. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 2019.
[24] Waqas Sultani, Chen Chen, and Mubarak Shah. “Anomaly detection in surveillance videos”. In: Proceedings of the IEEE conference on computer vision and pattern recog- nition (2018), pp. 6479–6488.
[25] Chang-Soo Sung and Joo Yeon Park. “Correction to: Design of an Intelligent Video Surveillance System for Crime Prevention: Applying Deep Learning Technology”. In: Multimedia Tools and Applications 80.26 (2021), p. 34311. DOI: 10.1007/s11042- 021-10931-y.
[26] R. Williams et al. “Fairness and Bias in Algorithmic Surveillance”. In: ACM FAT. 2020.
[27] Dan Xu et al. “Detecting Anomalous Events in Videos by Learning Deep Representa- tions of Appearance and Motion”. In: Computer Vision and Image Understanding 156 (2017), pp. 117–127. DOI: 10.1016/j.cviu.2016.10.010.
[28] Dan Xu et al. “Detecting Anomalous Events in Videos by Learning Deep Representa- tions of Appearance and Motion”. In: Computer Vision and Image Understanding 156 (2017), pp. 117–127.
[29] Jing Zhang et al. “Intelligent Crowd Sensing Pickpocketing Group Identification Us- ing Remote Sensing Data for Secure Smart Cities”. In: Mathematical Biosciences and Engineering 20.8 (2023), pp. 13777–13797. DOI: 10.3934/mbe.2023613
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Sunil Kumar Mishra, Dr. Rajat Kumar, Yogesh Kumar Sharma (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This is an Open Access article distributed under the term's of the Creative Common Attribution 4.0 International License permitting all use, distribution, and reproduction in any medium, provided the work is properly cited.
