VEHICLE SPEED DETECTION USING OPENCV FOR INTELLIGENT TRANSPORTATION SYSTEMS

This research presented a Vehicle Speed Detection System using OpenCV and computer vision techniques for intelligent transportation applications. The proposed framework successfully detects moving vehicles, tracks their trajectories, and estimates speed using displacement and temporal analysis. Experimental evaluation demonstrated an average vehicle detection accuracy of approximately 93%, tracking accuracy of 94%, and speed estimation accuracy exceeding 91%. The results confirm that computer vision-based traffic monitoring systems can serve as viable alternatives to traditional sensor-based approaches. The modular architecture, low deployment cost, and scalability make the proposed system suitable for smart city environments and intelligent transportation systems. Future enhancements involving deep learning, IoT integration, and cloud analytics can further improve performance and broaden application scope.

[1] Kumar, A., & Singh, R., “Vehicle Speed Estimation Using Optical Flow,” IEEE Access, 2020. [2] Rahman, M., et al., “Real-Time Vehicle Speed Detection Using OpenCV,” International Journal of Computer Vision, 2020. [3] Gupta, P., & Yadav, S., “Computer Vision Based Traffic Monitoring,” IEEE Transactions on ITS, 2021. [4] Kumar, R., et al., “YOLOv3-Based Vehicle Detection and Tracking,” IEEE Access, 2021. [5] Sharma, N., & Kaur, P., “Deep Learning for Vehicle Detection,” Expert Systems with Applications, 2022. [6] Ali, M., & Mehta, K., “Night-Time Vehicle Detection Using OpenCV,” Pattern Recognition Letters, 2022. [7] Das, R., & Nair, S., “Deep SORT Based Multi-Vehicle Tracking,” IEEE Access, 2023. [8] Priya, R., & Sahu, A., “OpenCV-Python Speed Monitoring System,” Journal of Transportation Engineering, 2023. [9] Gupta, S., & Iqbal, H., “IoT-Based Traffic Monitoring,” Sensors, 2024. [10] Wang, L., & Zhang, T., “YOLOv5 Vehicle Speed Estimation,” IEEE Access, 2024.