Unusual Crowd Activity Detection

In this project, we propose a novel method for unusual human activity detection in crowded scenes. Suspicious behavior is dangerous in public areas that may cause heavy causalities. There are various systems developed on the basis of video frame acquisition where motion or pedestrian detection occurs. Still, those systems are not intelligent enough to identify unusual activities even in real-time. It is required to recognize scamper situations at real-time from video surveillance for quick and immediate management before any casualties. The proposed system focuses on recognizing suspicious activities and targets to achieve a technique which is able to detect suspicious activity automatically using computer vision. Here system uses the OpenCV library to classify different actions in real time. The motion influence map has been used to represent the motion analysis that frequently changes the position from one place to another. The system uses CNN and YOLO algorithms for real-time object detection.