Real-time CCTV Footage Violence Detection with Alarm System using Deep Learning

Abstract

The increasing proliferation of surveillance cameras to keep an eye on human behavior has led to a rise in the need for an automated system that can identify violent incidents and suspicious activities. In smart buildings, this technology is mandatory. Violence Detection in real time will prevent any mishappenings from taking place by raising alerts to the security guards. Our model also has YOLO object detection inculcated in it in order to recognize any weapons or tools that an attacker may be using against people and the security guards will act accordingly.In this paper, we have utilized deep learning model and techniques to create a lightweight system for detecting violence that is fully automated and can act as an assistant for law enforcement officers, and can also be deployed in public areas as well as corporate buildings. When the system detects violence, it rings an alarm which can be used to alert security personals that some commotion may be happening in certain area.