Crowd Abnormal Behaviour Detection Using YOLO V

Abstract: is paper presents a Crowd Abnormal Behavior Detection system using advanced deep learning techniques for real-time surveillance and safety monitoring. The system utilizes the YOLO (You Only Look Once) object detection algorithm to identify human activities in crowded environments and classify them as normal or abnormal. Abnormal behaviors such as fighting, running, panic situations, and sudden crowd movements are detected with high accuracy. The proposed system processes video streams in real-time and provides quick alerts, helping authorities take immediate action. The integration of computer vision and artificial intelligence enhances public safety in areas such as railway stations, shopping malls, and public gatherings.

Keywords: Crowd Analysis, Abnormal Behavior Detection, YOLO, Deep Learning, Computer Vision