Vehicle Theft Detection Using YOLO Based on License Plates and Vehicle Ownership

Abstract

Detection of vehicle theft requires innovative approaches to address an increasing number of cases in Indonesia. This study presents a YOLOv11-based system for detecting vehicle theft by combining real-time object detection with a vehicle ownership database. The proposed system identifies license plates, detects vehicle owners using facial recognition, and analyzes suspicious activity to determine theft occurrences. The proposed method can produce model effectiveness with an accuracy = 70%. Key improvements in architecture, including enhanced feature fusion and dynamic anchor assignment, contribute to the object’s detection in complex environments. This research can be a potential technique to provide efficient, scalable, and real-time security solutions in dynamic surveillance applications.