Crowd Scene Anomaly Detection in Online Videos

The prevalence of surveillance cameras in public places has led to an extremely pressing need for effective position and crowd monitoring, as well as anomaly detection. This paper tends to exhibit an incorporated approach that combines state-of-the-art computer vision techniques for comprehensive crowd surveillance. The main features of our approach are summarized into four steps: (a) Object detection and tracking; (b) Geometric rectification for positioning; (c) Motion extraction; and (d) Anomaly detection. First, this uses YOLOv5's Convolutional Neural Network (CNN) model in making efficient detection of objects, focusing on spotting individuals within crowded scenes. After detection, a strong mechanism for tracking is established with the help of the DeepSORT algorithm, which can track the person across frames. It must gain the people's position in the video frame and analyze motion data with the guarantee of capture of camera-scene geometry. Each frame thus gets converted from the 3D perspective to a 2D bird's eye view within the surveillance video, giving a guarantee of capture of the geometry of a camera scene. Motion anomaly detection is addressed through statistical methods, with Kernel Density Estimation (KDE) being employed to identify deviations from normal motion patterns. Extensive experiments conducted on different online crowd scene video datasets validate the effectiveness of the proposed anomaly detection mechanism. Overall, this integrated approach proposes a promising solution to crowd surveillance, further development of object detection, tracking, and anomaly analysis for monitoring public spaces.