International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Based Real-Time Multi-Class Abnormal Activity Detection Using Slow-Fast 3D CNN for Smart Surveillance Systems |
|---|---|
| ABSTRACT | Modern surveillance systems are becoming increasingly important for maintaining safety in public, commercial, and institutional environments. Traditional monitoring methods depend heavily on human operators to continuously observe CCTV footage, which can often be inefficient, time-consuming, and prone to delayed responses. This work presents an AI-based real-time surveillance system designed to detect violence and abnormal activities from live video streams. The proposed framework utilizes a Slow-Fast 3D Convolutional Neural Network (SF-3D CNN) to capture both spatial and temporal motion features from video sequences. By analyzing video frames at multiple temporal speeds, the model effectively distinguishes abnormal behavior from normal activities in environments such as colleges, hotels, public areas, and smart city infrastructures. Whenever suspicious or violent activity is identified, the system automatically generates alerts to support faster response from the concerned authorities. Experimental results demonstrate that the system can detect violence and abnormal events with good accuracy and efficient real-time performance, making it suitable for practical surveillance applications. |
| AUTHOR | OM ANERAO, SANDEEP DHARURKAR, AJINKYA JADHAV, VARDHAN JADHAV, PRIYANKA JADHAV Student, Department of Computer Engineering, RMD Sinhgad School of Engineering, Warje, Pune, Maharashtra, India Assistant Professor, Department of Computer Engineering, RMD Sinhgad School of Engineering, Warje, Pune, Maharashtra, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406054 |
| pdf/54_AI-Based Real-Time Multi-Class Abnormal Activity Detection Using Slow-Fast 3D CNN for Smart Surveillance Systems.pdf | |
| KEYWORDS | |
| References | [1] A. K. Tripathi, S. Mukherjee, and A. K. Dubey, “Toward Fast and Accurate Violence Detection for Automated Video Surveillance Applications,” IEEE Access, vol. 11, pp. 38177–38191, 2023. [2] R. K. Sharma, S. K. Singh, and A. Tiwari, “Remote Monitoring System Using Slow-Fast Deep CNN Model for Identifying Anti-Social Activities,” Measurement: Sensors, vol. 25, pp. 100712–100721, 2023. [3] T. Nguyen, H. Zhang, and M. Abdel-Mottaleb, “Enhancing Situational Awareness: Anomaly Detection Using Real-Time Video Across Multiple Domains,” IEEE Access, vol. 13, pp. 50541–50556, 2025. [4] M. N. Nahar and S. Paul, “Real-Time Violence Detection in Video Using Deep Learning,” Multimedia Tools and Applications, vol. 81, no. 14, pp. 20321–20340, 2022. [5] C. Feichtenhofer, H. Fan, J. Malik, and K. He, “SlowFast Networks for Video Recognition,” IEEE/CVF International Conference on Computer Vision (ICCV), pp. 6201–6210, 2019. [6] C. Feichtenhofer, “X3D: Expanding Architectures for Efficient Video Recognition,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 203–213, 2020. [7] A. Ullah, K. Muhammad, W. Ding, S. W. Baik, and M. Sajjad, “Violence Detection Using Spatio-Temporal Features with 3D Convolutional Neural Network,” Sensors, vol. 19, no. 20, pp. 4470–4484, 2019. [8] A. Hassner, Y. Itcher, and O. Kliper-Gross, “Violent Flows: Real-Time Detection of Violent Crowd Behavior,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1–6, 2012. [9] Y. Tian, G. Lu, and D. Zhang, “Anomaly Detection in Surveillance Videos Using Deep Learning: A Review,” IEEE Access, vol. 9, pp. 102363–102391, 2021. [10] D. Wu, L. Shao, and Y. Fu, “Deep Learning for Video Classification and Captioning: A Review,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 10, pp. 4159–4177, 2018. |
