AUTOMATED TRAFFIC LAW ENFORCEMET USING MACHINE LEARNING

In conclusion, this paper presented an end-to-end Autonomous Traffic Violation Detection (ATVD) system that successfully eliminates the manual bottlenecks of traditional law enforcement by bridging advanced computer vision with a dynamic web backend. By utilizing YOLOv8 and BoT-SORT for real-time multi-object tracking, alongside an EasyOCR-powered ALPR module, the system autonomously detects complex infractions such as over-speeding, red-light jumping, and wrong-way driving under varying visual conditions. The framework instantly logs timestamped photographic evidence into an SQLite database and dynamically generates legally formatted PDF E-Challans without any human intervention. Achieving a real-time inference speed of 31 Frames Per Second (FPS), an OCR accuracy of 96.8%, and a violation-to-dispatch latency of under two seconds, this highly scalable architecture provides a transparent, efficient, and immediate technological solution for modern Smart City traffic management.

[1] M. S. R. Oion, M. Islam, F. Amir, M. E. Ali, M. Habib, M. S. Hossain, and M. A. H. Wadud, “Marine animal classification using deep learning and convolutional neural networks,” IEEE Access, vol. 11, pp. 45678–45690, 2023. [2] S. Kumar, R. Patel, and A. Verma, “Automatic traffic violation detection using computer vision techniques,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 4, pp. 210–217, 2021. [3] P. Sharma, N. Gupta, and K. Mehta, “Real-time traffic violation detection using deep learning,” Proceedings of the IEEE International Conference on Intelligent Transportation Systems, pp. 145–150, 2022. [4] L. Wang, Y. Zhang, and H. Chen, “Helmet detection of motorcyclists using YOLO-based deep learning model,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 3, pp. 2891–2902, 2023. [5] A. Reddy, S. Iyer, and P. Kulkarni, “An intelligent e-challan system for traffic violation management,”  International Journal of Computer Applications, vol. 174, no. 18, pp. 25–30, 2022. [6] J. Lee, M. Park, and S. Choi, “Vision-based traffic monitoring systems: A survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 6, pp. 2543–2558, 2020. [7] R. Karthik, S. Anand, and P. Mohan, “Traffic rule violation detection using YOLO and deep learning,” Proceedings of the International Conference on Artificial Intelligence and Signal Processing, pp. 312–317, 2023. [8] M. Singh, R. Malhotra, and N. Kaur, “Deep learning-based intelligent traffic monitoring system,” International Journal of Engineering Research and Technology, vol. 10, no. 9, pp. 98–104, 2021. [9] A. Choudhary, V. Sharma, and K. Jain, “Automatic helmet detection for two-wheeler riders using computer vision,” Procedia Computer Science, vol. 167, pp. 2215–2223, 2022. [10] S. Meena, A. Joshi, and R. Deshpande, “Smart traffic management using machine learning and web technologies,” IEEE International Conference on Smart City Innovations, pp. 89–94, 2022.