Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175575,
        author = {Uppala Sobhini and G .Lohit Sharma and K bhargavi and Garrepalli Shivani and C. Surekha},
        title = {Suspicious Activity Detection Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4186-4190},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175575},
        abstract = {This project focuses on developing a machine learning model using deep learning techniques, specifically YOLO (You Only Look Once) and CNNs (Convolutional Neural Networks), to detect and recognize suspicious activities from surveillance images. The model is trained on the Dangerous Action Detection dataset, which includes classes such as weapons (knives, crowbars, guns) and suspicious human poses. The objective is to accurately identify potentially dangerous behaviors in real-time, improving safety in public and sensitive areas like airports, banks, and schools, where continuous monitoring is difficult. Intelligent video surveillance enables automatic distinction between normal and abnormal activities, triggering alerts to prevent crimes such as theft, vandalism, and terrorism. The project reviews advancements in suspicious activity detection over the past decade, addressing challenges in visual surveillance, including object detection, activity recognition, and foreground extraction. The results emphasize the effectiveness of deep learning models in enhancing crime prevention through automated surveillance systems. This solution contributes to public safety by enabling rapid, accurate detection of threats, reducing response times, and improving security measures.},
        keywords = {Deep Learning, YOLO, CNN, Real-Time Surveillance, Visual Surveillance, Object Detection, Human Activity Recognition, Abnormal Behavior Detection, Dangerous Action Detection Dataset, Automated Alert System, Feature Extraction, Crime Prevention, Intrusion Detection, Computer Vision, Smart Surveillance, Public Safety, Security Monitoring, Foreground Extraction, Video Analytics.},
        month = {April},
        }