Copyright © 2025 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{185813,
        author = {Ms. Sakina H. Bharmal and Dr. Sangram T. Patil and Dr. Jaydeep B. Patil},
        title = {Traffic Rule Violation Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {12},
        number = {no},
        pages = {108-116},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185813},
        abstract = {The detection of traffic rule violators is a highly desired but tough task because of several challenges including occlusion, illumination, etc., which make it difficult to enforce safety measures on Indian roadways. In order to improve decision-making about traffic laws policy, we present in this paper an end-to-end system for detecting violations, alerting offenders, and storing them for analysis and statistic generation. The suggested method first uses object detection, which is done with YOLO, to identify automobiles. Each vehicle is then examined for the relevant infractions, such as failing to wear a helmet or failing to use a crosswalk. A classifier based on convolutional neural networks (CNNs) is used to identify helmet violations. The Instance Segmentation by Mask R-CNN architecture is used to detect crosswalk violations. Following the detection of infractions, the offenders are alerted and their vehicle numbers are retrieved using OCR. Therefore, a comprehensive autonomous system will support the enforcement of strict traffic regulations.},
        keywords = {Object Detection, convolutional neural networks (CNNs), R-CNN, OCR, etc},
        month = {},
        }