Volume 9 • Issue 2 • PP: 14–23 • 2025
Real-Time Violence Detection in Smart Cities Using Lightweight Spatiotemporal Deep Learning Models
Open Access & Copyright
© 2025 The Author(s). Published by ASPG. This article is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Editorial responsibility:
This article was handled by an independent editor. The author serving on the Editorial Board had no involvement in the peer-review process or the final editorial decision.
View PDF Abstract
The rapid development of smart-city infrastructure and the complexity of urban environments increase the need for automated systems that detect violence in surveillance footage. This paper presents a deep-learning architecture for detecting violence and weapon-related activity in CCTV footage using the Smart-City CCTV Violence Detection (SCVD) dataset. MobileNetV2 extracts spatial features from video frames through TimeDistributed layers, and a stacked Long Short-Term Memory (LSTM) network models temporal dependencies. The system processes 15-frame sequences at a resolution of 128 × 128 pixels. Batch normalization and dropout are used to improve generalization and limit overfitting, while a sigmoid output produces binary classifications. On the SCVD evaluation, the model achieved 99.58% accuracy and a binary cross-entropy loss of 0.0139. The Normal class achieved precision, recall, and F1-score values of 0.99; the Violence class metrics were reported as 1.00 after rounding. These results indicate the potential of compact spatiotemporal models for reliable surveillance and deployment on edge devices such as smart cameras and embedded systems.
Keywords
References
[1] R. Vijeikis, V. Raudonis, and G. Dervinis, “Efficient violence detection in surveillance,” Sensors, vol. 22, no. 6, p. 2216, 2022.
[2] F. U. M. Ullah, M. S. Obaidat, A. Ullah, K. Muhammad,
M. Hijji, and S. W. Baik, “A comprehensive review on vision-based violence detection in surveillance videos,” ACM Computing Surveys, vol. 55, no. 10, pp. 1–44, 2023.
[3] J. Wensel, H. Ullah, and A. Munir, “ViT-ReT: Vision and recurrent transformer neural networks for human activity recognition in videos,” IEEE Access, vol. 11, pp. 72227–72249, 2023.
[4] M. Xu, Y. Xiong, H. Chen, X. Li, W. Xia, Z. Tu, and S. Soatto, “Long short-term transformer for online ac-tion detection,” in Advances in Neural Information Pro-cessing Systems, vol. 34, pp. 1086–1099, 2021.
[5] W. Ullah, T. Hussain, F. U. M. Ullah, M. Y. Lee, and S. W. Baik, “TransCNN: Hybrid CNN and transformer mechanism for surveillance anomaly detection,” Engi-neering Applications of Artificial Intelligence, vol. 123, p. 106173, 2023.
[6] X. Wu, R. Wang, J. Hou, H. Lin, and J. Luo, “Spatial–temporal relation reasoning for action prediction in videos,” International Journal of Computer Vision, vol. 129, no. 5, pp. 1484–1505, 2021.
[7] W. Tan and J. Liu, “Detection of fights in videos: A com-parison study of anomaly detection and action recog-nition,” in European Conference on Computer Vision, pp. 676–688, Springer, 2022.
[8] H.-T. Duong, V.-T. Le, and V. T. Hoang, “Deep learning-based anomaly detection in video surveillance: A sur-vey,” Sensors, vol. 23, no. 11, p. 5024, 2023.
[9] S. Narejo, B. Pandey, D. Esenarro Vargas, C. Rodriguez, and M. R. Anjum, “Weapon detection using YOLO v3 for smart surveillance system,” Mathematical Problems in Engineering, vol. 2021, no. 1, p. 9975700, 2021.
[10] P. Y. Ingle and Y.-G. Kim, “Real-time abnormal object detection for video surveillance in smart cities,” Sensors, vol. 22, no. 10, p. 3862, 2022.
[11] T. Aremu, Z. Li, R. Alameeri, M. Aloqaily, and M. Guizani, “Towards smart city security: Violence and weaponized violence detection using DCNN,” preprint, arXiv, 2022.
[12] R. Ramya, C. Lasya, N. M. Sai, and S. Paneerselvam, “An intelligent surveillance system for weapon detection based on EfficientDet algorithm,” in 2023 5th Interna-tional Conference on Inventive Research in Computing Applications (ICIRCA), pp. 453–459, IEEE, 2023.
[13] M. Khan, W. Gueaieb, A. El Saddik, G. De Masi, and F. Karray, “An efficient violence detection approach for smart cities surveillance system,” in 2023 IEEE Interna-tional Smart Cities Conference (ISC2), pp. 1–5, IEEE, 2023.
[14] F. J. Rendón-Segador, J. A. Álvarez-García, J. L. Salazar-González, and T. Tommasi, “CrimeNet: Neural structured learning using vision transformer for violence detection,” Neural Networks, vol. 161, pp. 318–329, 2023.
[15] C. Vilalta, P. Lopez-Ramirez, and G. Fondevila, “Test-ing the local and spatial spillover effects of police mon-itored CCTV systems on crime,” Applied Geography, vol. 151, p. 102873, 2023.
[16] M. A. J. Maktoof, I. H. M. Ibrahim, M. A. A. Razzaq, A. Abbas, and A. Majdi, “Machine learning-based in-telligent video surveillance in smart city framework,” Fusion: Practice & Applications, vol. 11, no. 2, pp. 35–47, 2023.
[17] Y. Myagmar-Ochir and W. Kim, “A survey of video surveillance systems in smart city,” Electronics, vol. 12, no. 17, p. 3567, 2023.
[18] S. Mathur and K. Sood, “Policing perspective on pre-emptive and probative value of CCTV architecture in the security of the smart city–gandhinagar, gujarat,” In-ternational Journal of Electronic Security and Digital Forensics, vol. 15, no. 3, pp. 252–258, 2023.
[19] M. S. N. B. Abdullah, H. Abdul Karim, and N. Al-Dahoul, “A combination of light pre-trained convolu-tional neural networks and long short-term memory for real-time violence detection in videos,” International Journal of Technology, vol. 14, no. 6, pp. 1228–1236, 2023.
[20] N. D. Ha, N. Y. Tran, L. N. L. Thuy, I. Shimizu, and P. T. Bao, “Violence region localization in video and the school violent actions classification,” Frontiers in Computer Science, vol. 5, p. 1274928, 2023.
[21] P. Wang, P. Wang, and E. Fan, “Violence detection and face recognition based on deep learning,” Pattern Recognition Letters, vol. 142, pp. 20–24, 2021.
[22] M. Patel, “Real-time violence detection using CNN-LSTM,” preprint arXiv:2107.07578, arXiv, 2021.
[23] C. El Morr, M. Jammal, H. Ali-Hassan, and W. El-Hallak, “Data preprocessing,” in Machine Learning for Practical Decision Making: A Multidisciplinary Perspective with Applications from Healthcare, Engi-neering and Business Analytics, pp. 117–163, Springer, 2022.
[24] S. Alam and N. Yao, “The impact of preprocessing steps on the accuracy of machine learning algorithms in sentiment analysis,” Computational and Mathematical Organization Theory, vol. 25, no. 3, pp. 319–335, 2019.
[25] A. A. Khan, “Balanced split: A new train-test data splitting strategy for imbalanced datasets,” preprint arXiv:2212.11116, arXiv, 2022.
[26] A. Mosavi, S. Ardabili, and A. R. Varkonyi-Koczy, “List of deep learning models,” in International Confer-ence on Global Research and Education, pp. 202–214, Springer, 2019.
[27] D. Saluja, H. Kukreja, A. Saini, D. Tegwal, P. Nagrath, and J. Hemanth, “Analysis and comparison of various deep learning models to implement suspicious activity recognition in CCTV surveillance,” Intelligent Decision Technologies, vol. 17, no. 4, pp. 917–942, 2023.
[28] C. Shripriya, J. Akshaya, R. Sowmya, and M. Poonkodi, “Violence detection system using ResNet,” in 2021 5th International Conference on Electronics, Communica-tion and Aerospace Technology (ICECA), pp. 1069–1072, IEEE, 2021.
[29] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Ima-geNet classification with deep convolutional neural net-works,” in Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105, 2012.
[30] S. Zargar, “Introduction to sequence learning models: RNN, LSTM, GRU,” tech. rep., Department of Mechan-ical and Aerospace Engineering, North Carolina State University, 2021.
Cite This Article
Choose your preferred format
Publisher's Note
The statements, opinions, and data presented in this article are solely those of the author(s) and do not necessarily represent those of ASPG, the journal, or its editors. ASPG and the editors disclaim responsibility for any harm arising from the use of any ideas, methods, instructions, or products described in this article, to the fullest extent permitted by applicable law.