The increasing number of vehicles on roads has made traffic monitoring and enforcement more challenging for authorities. Manual observation of violations such as riding without a helmet, triple-seat riding, and improper vehicle usage requires significant effort and often leads to delays in enforcement. This paper presents an intelligent traffic surveillance system that automatically detects traffic violations and generates digital challans. The proposed solution combines YOLOv8-based object detection with Optical Character Recognition (OCR) to identify riders, helmets, motorcycles, and vehicle registration numbers from video streams. When a violation is detected, the system records the relevant information, stores it in a database, and generates an electronic challan along with supporting evidence. A dashboard is provided for monitoring and managing violation records. The system minimizes human intervention, improves monitoring efficiency, and supports modern traffic management initiatives. Experimental evaluation demonstrates that the proposed approach can effectively identify violations while maintaining reliable performance in a local processing environment.

This work presents an AI-driven traffic violation detection system designed to automate the identification of helmetless riders, triple-seat riding violations, and vehicle number plate recognition. The integration of YOLOv8 and OCR technologies enables accurate detection and efficient extraction of vehicle information from traffic video streams. By automatically recording violations and generating digital challans, the system reduces dependency on manual monitoring and improves operational efficiency. Experimental results indicate that the proposed approach is capable of delivering reliable performance while operating in a local computing environment. The developed framework can assist traffic authorities in enhancing enforcement processes and promoting road safety. Future improvements may include support for additional traffic violations, deployment on edge devices, and enhanced performance under adverse weather and lighting conditions.

[1]J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, 2016. doi:10.1109/CVPR.2016.91 [2]A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv preprint, Apr. 2020. doi:10.48550/arXiv.2004.10934 [3]G. Jocher, A. Chaurasia, and J. Qiu, “YOLO by Ultralytics: Real-Time Object Detection,” 2023. Available:https://github.com/ultralytics/ultral ytics [4]A. Rosebrock, “Automatic License/Number Plate Recognition using Computer Vision,” PyImageSearch, 2021. [5]J. Matas, L. Neumann, and J. Matas, “Real-Time Scene Text Localization and Recognition,” in IEEE Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6248097 [6]J. Smith and R. Kumar, “Helmet Detection for Motorcyclists using Deep Learning,” International Journal of Computer Vision and Robotics, vol. 14, no. 3, pp. 145–156, 2022. [7]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, vol. 39, no. 6, pp. 1137–1149, 2017. doi:10.1109/TPAMI.2016.2577031 [8]R. Girshick, “Fast R-CNN,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448,2015. doi:10.1109/ICCV.2015.169 [9]A. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” arXiv preprint, Apr. 2017. doi:10.48550/arXiv.1704.04861 [10]B. A. Raj, P. Venkatesh, and S. Kumar, “Automated Traffic Rule Violation Detection System using Deep Learning,” IEEE Access, vol. 10, pp. 35412–35425, 2022. doi:10.1109/ACCESS.2022.3154789 [11]R. Smith, “An Overview of the Tesseract OCR Engine,” in Proceedings of the Ninth International Conference on Document Analysis and Recognition, pp. 629–633, 2007. doi:10.1109/ICDAR.2007.4376991 [12]J. Deng et al., “ImageNet: A Large-Scale Hierarchical Image Database,” in IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255, 2009. doi:10.1109/CVPR.2009.5206848 [13]X. Liu and H. Wang, “Smart Traffic Monitoring System using Artificial Intelligence and Computer Vision,” International Journal of Smart Systems, vol. 18, no. 2, pp. 102–117, 2023. [14]M. Patel and S. Shah, “Real-Time Vehicle Number Plate Detection and Recognition using OCR Techniques,” International Journal of Engineering Research and Technology, vol. 11, no. 5, pp. 411–419, 2022. [15]S. Gupta and R. Verma, “AI-Based Traffic Surveillance for Smart Cities,” IEEE International Conference on Smart Computing, pp. 211–218, 2023. doi:10.1109/SMARTCOMP.2023.10124567 [16]D. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv preprint, Dec. 2014. doi:10.48550/arXiv.1412.6980 [17]C. Szegedy et al., “Going Deeper with Convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9, 2015. doi:10.1109/CVPR.2015.7298594 [18]H. Law and J. Deng, “CornerNet: Detecting Objects as Paired Keypoints,” in European Conference on Computer Vision (ECCV), pp. 734–750, 2018. [19]Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, pp. 436–444, 2015. doi:10.1038/nature14539 [20]P. Viola and M. Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features,” in IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 511–518, 2001. doi:10.1109/CVPR.2001.990517

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close