Deep Learning-Based Forensic Detection of Suspicious Activities in CCTV Systems
Article content
Abstract
Advancements in smart surveillance and digital forensics have been significantly influenced by artificial intelligence (AI), machine learning (ML), and cloud computing, enabling real-time forensic analysis of CCTV footage to detect suspicious activities and reduce reliance on manual monitoring. While these technologies enhance public safety and policing efficiency, they also raise important concerns related to privacy, ethics, and regulation. This study proposes a deep learning-based forensic framework for real-time detection of suspicious human activity in CCTV videos, trained without relying on any external sensors. The model utilizes EfficientNet-B5 for spatial feature extraction and a Vision Transformer (ViT) that has been adapted to model both spatial and temporal dependencies between consecutive video frames. Specifically, the ViT processes frame sequences as token embeddings, enabling temporal context learning through self-attention. The EfficientNet-B5, a convolutional neural network (CNN), functions primarily as a high-level feature extractor, capturing geometric and spatial characteristics such as scale variations, aspect ratios, and motion-relevant visual patterns from individual frames. The Binary UCF-Crime dataset is used for training and validation, with class rebalancing achieved through data augmentation and weighted loss adjustment to mitigate class imbalance. Performance is evaluated using accuracy, precision, F1-score, and AUC metrics, each averaged across 5-fold cross-validation. The reported accuracy is obtained through this cross-validation protocol and benchmarked against baseline models, including standalone EfficientNet-B5 and traditional machine learning approaches. The ViT-enhanced model achieves an accuracy of 87.23%, outperforming the EfficientNet-B5 baseline by a significant margin. To address ethical concerns, the framework incorporates anonymization of personal identities and local edge-based processing to prevent raw data exposure.
Keywords
Artificial Intelligence, Closed-Circuit Television (CCTV), Deep Learning, Surveillance, Vision Transformer (ViT), forensic sciences
Downloads
References
Murthy JS, Siddesh GM. AI-based criminal detection and recognition system for public safety and security using novel CriminalNet-228. In: Proceedings of the 4th International Conference on Frontiers in Computing and Systems (COMSYS 2023). 2024. p. 1–3.
Ali MM, Noorain S, Qaseem MS, ur Rahman A. Suspicious human behaviour detection focusing on campus sites. In: Emerging IT/ICT and AI technologies affecting society. 2022. p. 171–183.
Selvaraj A, Selvaraj J, Maruthaiappan S, Babu GC, Kumar PM. L1 norm-based pedestrian detection using video analytics technique. Comput Intell. 2020;36(4):1569–1579.
Joshi KA, Thakore DG. A survey on moving object detection and tracking in video surveillance system. Int J Soft Comput Eng. 2012;2(3):44–48.
Pustokhina IV, Pustokhin DA, Vaiyapuri T, Gupta D, Kumar S, Shankar K. An automated deep learning-based anomaly detection in pedestrian walkways for vulnerable road users’ safety. Saf Sci. 2021;142:105356. doi:10.1016/j.ssci.2021.105356.
Saluja D, Kukreja H, Saini A, Tegwal D, Nagrath P, Hemanth J. Analysis and comparison of various deep learning models to implement suspicious activity recognition in CCTV surveillance. Intell Decis Technol. 2023;17(4):917–942. doi:10.3233/IDT-220066.
Alkanhal L, Alotaibi D, Albrahim N, Alrayes S, Alshemali G, Bchir O. Super-resolution using deep learning to support person identification in surveillance video. Int J Adv Comput Sci Appl. 2020;11(7):1–10.
Singla S, Chadha R. Detecting criminal activities from CCTV by using object detection and machine learning algorithms. In: Proceedings of the 3rd International Conference on Intelligent Technologies (CONIT 2023). 2023. p. 1–6.
Sudha I, Ramesh PS, Narang S, Ponmalar A. Deep learning for image and video processing in surveillance systems: advancing security with AI-driven insights. In: Proceedings of the 3rd International Conference on Communication, Security, and Artificial Intelligence (ICCSAI 2025). 2025. p. 492–496.
Basthikodi M, Vidya B, Pinto EM, Basith M, Rao SA. AI-based automated framework for crime detection and crowd management. In: Proceedings of the Second International Conference on Advances in Information Technology (ICAIT 2024). 2024. p. 1–6.
Kumar R, Rajpurohit DS, Hanief M, Sharma S, Choudhury T, Sar A. Detection of criminal activities through CCTV by live footage analysis. In: Proceedings of the OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0 (OTCON 2024). 2024. p. 1–6.
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2009. p. 248–255.
Article details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
You must read and accept the copyright terms and conditions(click here for copyright terms).