Home / Current Issue / Paper 1717964
Autonomous Traffic Violation Detection Using Machine Learning and Computer Vision
Subject area: Science,Engineering and Technology · Area of research: ML and CV
DOI: https://doi.org/10.64388/IREV9I11-1717964
Abstract
Traffic violations such as red-light jumping, over-speeding, and riding without helmets are among the leading causes of road accidents and fatalities worldwide. With the rapid increase in the number of vehicles in urban areas, traditional traffic monitoring systems based on manual observation and CCTV surveillance have become inefficient, time-consuming, and prone to human error. Existing research has explored various machine learning and deep learning approaches, such as Convolutional Neural Networks (CNN) and YOLO- based object detection models, for detecting specific traffic violations. However, most of these systems are limited to detecting a single type of violation and lack integration for real-time multi- violation detection and data analytics. This paper presents a comprehensive literature review of existing traffic violation detection techniques and identifies key research gaps in scalability, integration, and real-time performance. Based on these gaps, a novel framework is proposed that utilizes deep learning models for detecting multiple traffic violations simultaneously. The system also incorporates a structured database to store violation data and perform analytical reporting. The proposed approach aims to improve accuracy, efficiency, and scalability in intelligent transportation systems and contributes toward the development of smart city traffic management solutions.
Keywords
Traffic Violation Detection, Machine Learning, Computer Vision, Deep Learning, YOLO, Intelligent Transportation Systems, Smart Cities
References
[1] H. Sharma et al., “Automated Detection of Traffic Rule Violation using Deep Learning,” IEEE, 2024.
[2] K. Deepika et al., “Cloud IoT Model for Smart Traffic Monitoring,” IEEE, 2023.
[3] A. Yumaganov and A. Agafonov, “Comparison of Autonomous Driving Approaches,” IEEE, 2021.
[4] M. Hasan et al., “Autonomous Traffic System using YOLOR,” IEEE, 2022.
[5] M. Arshad et al., “Two-Wheeler Violation Detection using Deep Learning,” IEEE, 2022.
[6] J. Redmon and A. Farhadi, “YOLOv3: An IncrementalImprovement,”IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[7] A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv preprint arXiv:2004.10934, 2020.
[8] G. Jocher et al., “YOLOv5 by Ultralytics,” GitHub Repository, 2020.
[9] W. Liu et al., “SSD: Single Shot MultiBox Detector,” European Conference on Computer Vision (ECCV), 2016.
[10] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017.
[11] T. Lin et al., “Focal Loss for Dense Object Detection,” IEEE International Conference on Computer Vision (ICCV), 2017.
[12] M. Everingham et al., “The Pascal Visual Object Classes (VOC) Challenge,” International Journal of Computer Vision, 2010.
[13] J. Deng et al., “ImageNet: A Large-Scale Hierarchical Image Database,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.
[14] Z. Zhang et al., “Deep Learning Based Traffic Violation Detection System,” IEEE Access, 2021.
[15] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, 2015
How to cite this paper
@article{1717964,
author = {Jenisha J, Prof. Rakshitha B S},
title = {Autonomous Traffic Violation Detection Using Machine Learning and Computer Vision},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {2582-2588},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717964.pdf},
abstract = {Traffic violations such as red-light jumping, over-speeding, and riding without helmets are among the leading causes of road accidents and fatalities worldwide. With the rapid increase in the number of vehicles in urban areas, traditional traffic monitoring systems based on manual observation and CCTV surveillance have become inefficient, time-consuming, and prone to human error. Existing research has explored various machine learning and deep learning approaches, such as Convolutional Neural Networks (CNN) and YOLO- based object detection models, for detecting specific traffic violations. However, most of these systems are limited to detecting a single type of violation and lack integration for real-time multi- violation detection and data analytics.
This paper presents a comprehensive literature review of existing traffic violation detection techniques and identifies key research gaps in scalability, integration, and real-time performance. Based on these gaps, a novel framework is proposed that utilizes deep learning models for detecting multiple traffic violations simultaneously. The system also incorporates a structured database to store violation data and perform analytical reporting. The proposed approach aims to improve accuracy, efficiency, and scalability in intelligent transportation systems and contributes toward the development of smart city traffic management solutions.},
keywords = {Traffic Violation Detection, Machine Learning, Computer Vision, Deep Learning, YOLO, Intelligent Transportation Systems, Smart Cities},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717964}
}