Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198291,
        author = {Mrs. A. Srujana Reddy and Ponna Sri Nikethan and Ranabothu sravya and U Ganesh and Ravutla Gourav},
        title = {Vision-Based Multi-Vehicle Red Light Violation Detection Computer Science and Engineering},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {9373-9381},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198291},
        abstract = {Red-light violations contribute significantly to road accidents and urban traffic inefficiencies, accounting for a considerable proportion of intersection-related incidents worldwide. Studies indicate that nearly 20–30% of urban crashes occur at signalized intersections, with red-light jumping being a primary cause. Traditional monitoring systems relying on manual supervision or sensor-based infrastructure often exhibit reduced accuracy under challenging conditions such as low illumination, heavy traffic, and adverse weather. This paper presents a vision-based multi-vehicle red-light violation detection system using deep learning and computer vision techniques for real-time enforcement. The proposed framework employs YOLO-based object detection for vehicle and traffic signal recognition, combined with multi-object tracking algorithms to ensure continuous monitoring across frames. Experimental evaluation using datasets comprising over 18,000 traffic images and 5,000+ annotated signal instances demonstrate detection accuracy exceeding 90% and robust performance across varied environmental conditions. The system detects violations when vehicles cross the stop line during a red signal phase and integrates optical character recognition for automatic license plate extraction. Statistical analysis further reveals improved detection consistency and reduced false positives compared to conventional approaches. The proposed solution enhances enforcement efficiency, minimizes human intervention, and supports scalable deployment in smart city traffic management systems.},
        keywords = {Red-Light Violation Detection, Deep Learning, YOLO, Computer Vision, Multi-Object Tracking, OCR, Intelligent Transportation Systems, Smart Cities.},
        month = {April},
        }