Detection of Abnormal Human Behavior using YOLO and CNN for Enhanced Surveillance

The detection of abnormal human behavior is vital for safeguarding public spaces and ensuring the well-being of individuals. This study leverages advanced algorithms, specifically YOLO (You Only Look Once) and Convolutional Neural Networks (CNN), to develop a robust system for detecting and analyzing human behavior in real-world scenarios. Designed for application in surveillance footage from CCTV cameras, the system employs YOLOv5 for accurate identification of human behaviors and anomalies within video data. Subsequently, a CNN extracts action features from each tracked trajectory, enabling precise recognition of suspicious activities. By integrating these algorithms, the proposed model effectively identifies and predicts abnormal human behavior, offering a powerful tool for enhancing security and situational awareness.