About this document
1352 Submission by aarthir3 is a document available to read on EtoBox.
This document presents a deep learning-based crime detection system designed for public security using video surveillance, addressing the inefficiencies of traditional methods. The proposed hybrid system integrates YOLO for object detection and LSTM for temporal behavior analysis, achieving high accuracy in identifying crimes such as gun violence and theft. Empirical results demonstrate superior performance over conventional techniques, with reduced false alarms and robust real-time capabilities suitable fo
- Author
- aarthir3
- Language
- EN