An Intelligent Crime Surveillance Video System For Real-Time Applications

The increasing frequency of violent incidents underscores the need for advanced real-time surveillance systems. This work proposes an intelligent camera system based on deep learning algorithms for crime monitoring, capable of accurately detecting violence. The system integrates YOLO for high-precision object detection, DeepSort for tracking, OpenPose for pose estimation, and LSTM networks for action Classification. The goal is to create a compact and accurate device that detects hostile activities in real time, triggers an alarm, and stores the offenders’ images in a database. YOLO is used to detect faces in video frames while minimizing false positives, and DeepSort tracks individuals by assigning each a unique ID, enabling continuous surveillance in crowded areas. OpenPose evaluates body positions by identifying key points and their affinities, while an LSTM network classifies actions as violent or non-violent based on posture data. When violence is detected, the system triggers an alarm and captures images, which are securely stored on a Firebase server with timestamps for easy access. This real-time, efficient, and lightweight surveillance system improves crime detection and response across various environments.