Surveillance Violence Detection System

Surveillance security may be a terribly tedious and long job. In this project, we build a system to automatize the task of analyzing video. we will analyze the video which we put in our model and the model determine any abnormal activities like violence. There are tons of analysis happening within the trade concerning video. Recent increased adaptation of security cameras. This paper describes a recognition and identify system for abnormal objects. The goal is to design and implement a system which will be able to detect abnormal activity using video sequences. The system uses high level reasoning to infer the existence of abnormal activity. The proposed approach was implemented using existing images, video clips and trained video. Our experiments demonstrate the effectiveness of the approach.