Published Paper Details:

In this paper, we propose a novel approach for anomaly detection in surveillance videos using YOLOv5, a state-of-the-art object detection model, integrated with deep learning methodologies. The YOLOv5 model is trained on a diverse dataset of normal activities to learn representative features and patterns. Subsequently, anomalies are identified by detecting deviations from the learned normal behaviour present experimental results on benchmark datasets, demonstrating the effectiveness and robustness of our proposed method in detecting various anomalies, including intrusions, unusual movements, and abandoned objects. Comparative analysis with existing techniques highlights the superior performance and efficiency of our approach. we discuss practical applications and deployment scenarios of our proposed anomaly detection system, emphasizing its potential contributions to enhancing surveillance capabilities in real-world environments. Finally, we conclude with insights into future research directions aimed at further improving the accuracy, scalability, and adaptability of anomaly detection systems in surveillance videos.