•  
  •  
 

Corresponding Author ORCID Identifer

Ashwani Kumar Dubey https://orcid.org/0000-0003-0778-9262
Neo Tse Kian https://orcid.org/0000-0002-5991-7409

Section

Regular Issue

Abstract

Vehicle identification and tracking play a critical role in security and surveillance, supporting the efforts of law enforcing authorities to prevent crime, monitor traffic, and enforce the vehicle rules and regulations. This research presents a proof-of-concept system that employs YOLOv8 for real time vehicle detection and car type classification using live or recorded CCTV footage. YOLOv8 was chosen after rigorous comparison, it was chosen for its ease of use and efficient image training capabilities, making it well suited for rapid prototyping that the concept needed. The system is designed to extract key vehicle features, including colour, model of the vehicle, logo, sticker (if any), its position and license plate information, and supports both real time and recorded video analysis. Although the model has not been fine-tuned, its performance provides a solid foundation for experimental development. The current implementation is at an early experimental stage and has been tested on a personal computer and is not yet ready for commercial deployment in the real world. For training and evaluation, a custom dataset was created using 5 hours of CCTV footage recorded from three different cameras at varied angles and lighting conditions, including both morning and evening scenes to ensure data diversity.

Download

Share

COinS