ADAPTIVE FOUR-JUNCTION TRAFFIC LIGHT CONTROLLER USING COMPUTER VISION
Keywords:
Object Detection, dataset, YOLO V5, traffic management, ArduinoAbstract
Traffic light control systems are essential elements of urban infrastructure, as they significantly contribute to road safety by maintaining an organized flow of traffic and promoting the efficient and smooth movement of vehicles. This study developed an adaptive traffic light control system for four-junction intersections, employing computer vision and real-time data processing. Using the YOLOV5 object detection algorithm, the system identifies vehicles and adjusts signal timings based on traffic density to optimize flow and reduce congestion. Trained on extensive datasets, the model achieved over 90% precision and recall in most scenarios, with low training and validation loss, indicating strong generalization. An Arduino Mega microcontroller processes data from a USB webcam to control LED traffic signals. Real-world tests demonstrated a 40% reduction in vehicle wait times compared to fixed-timing systems. This research highlights the effectiveness of intelligent traffic systems in improving urban mobility while offering a scalable solution to modern traffic challenges. Future enhancements may include pedestrian detection, predictive analytics, and integration of additional sensors to improve system adaptability and overall performance.
References
Aavani P, Sawant M. K, Sawant S.D, and Deshmukh R.S. 2017. Review on Adaptive Traffic Control Systems. International Journal of Latest Engineering and Management Research, 2(1): 52-57.
Al-Haija, Q. A., Gharaibeh, M., & Odeh, A. 2022. Detection in Adverse Weather Conditions for Autonomous Vehicles via Deep Learning. AI. 3(2): 303–317. https://doi.org/10.3390/ai3020019
Aleko D.R. and. Djahel S. 2020. An Efficient Adaptive Traffic Light Control System for Urban Road Traffic Congestion Reduction in Smart Cities. Information 11 (2):119.
Asadi, F., & Pongswatd, S. 2021. Programming the ARM® Cortex®-M4-based STM32F4 Microcontrollers with Simulink®. Synthesis Lectures on Digital Circuits and Systems 16(2): 1–183.
Dilek, E., & Dener, M. 2023. Computer Vision Applications in Intelligent Transportation Systems: A Survey. Sensors 23(6): 29–38. https://doi.org/10.3390/s23062938.
Gangadhar, N. S. 2010. An intelligent road traffic control system. IEEE Students’ Technology Symposium. https://doi.org/10.1109/techsym.2010.5469286
Hamilton, A., Waterson, B., Cherrett, T., Robinson, A., & Snell, I. 2013. The evolution of urban traffic control: changing policy and technology. Transportation Planning and Technology 36(1): 24–43.
Hidiyati, E. F., Nugroho, L. D., & Muhammadun, H. 2024. Optimization of Intersection Performance and Vehicle Traffic Flow at Intersection Four Dhoho Plaza Kediri City Using Mkji Method. International Journal on Advanced Technology, Engineering, and Information Systems 3(1): 41-56.
Jamebozorg, M., Hami, M., & Jani, S. D. D. 2024. Traffic control using intelligent timing of traffic lights with reinforcement learning technique and real-time processing of surveillance camera images. arXiv preprint arXiv:2405:13256.
Mahajan, N., Rai, N., Srivastava, A., Balutia, R., & Nandanwar, T. 2024. Optimizing Smart Cities Traffic Flow for the Carbon Emission Control through Modern Technologies. In 2024 International Conference on Signal Processing and Advance Research in Computing (SPARC) 1: 1-6). IEEE.
McShane C. 1999. The Origins and Globalization of Traffic Control Signals. Journal of Urban History 25(3): 379–404.
Pan, Y., Wu, Y., Xu, L., Xia, C., & Olson, D. L. (2024). The impacts of connected autonomous vehicles on mixed traffic flow: A comprehensive review. Physica A: Statistical Mechanics and its Applications, 129454.
Ren Y. L. 2024. A Review of Adaptive Signal Control Systems Based on Changes in Traffic Environments. Journal of Scientific and Engineering Research 11(2): 129–134. https://jsaer.com/download/vol-11-iss-2-2024/JSAER2024-11-2-129-134.pdf
Shamsul Arifin, Md., Alimur Razi, S., Haque, A., & Mohammad, N. 2019. A Microcontroller-Based Intelligent Traffic Control System. American Journal of Embedded Systems and Applications 7(1): 21. https://doi.org/10.11648/j.ajesa.20190701.13
Steingrover, M., Schouten, R., Peelen, S., Nijhuis, E. H. J., & Bakker, B. 2005. Reinforcement Learning of Traffic Light Controllers Adapting to Traffic Congestion. In Belgium-Netherlands Conference on Artificial Intelligence. Belgium-Netherlands Conference on Artificial Intelligence. https://api.semanticscholar.org/CorpusID:1195897
Talukder, M. Z., Towqir, S. S., Remon, A. R., & Zaman, H. U. 2017. An IoT-Based Automated Traffic Control System with Real-time Update Capability. 2017 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT). https://doi.org/10.1109/icccnt.2017.8204095
Trivedi, Janak & Sarada Devi, Mandalapu & Dhara, Dave. 2021. A Vision-Based Real-Time Adaptive Traffic Light Control System Using Vehicular Density Value and Statistical Block Matching Approach. Transport and Telecommunication. 22. 87-97. 10.2478/ttj-2021-0007.
Weerasak Karoon, Peeranut Chuasuai, Pearploy Thipprasert, Nachasa Khongchu, Piyaboon Kunakornjittirak, and Thitirat Siriborvornratanakul. 2024. Adaptive traffic light control using vision-based deep learning for vehicle density estimation. In Proceedings of the 2024 6th Asia Pacific Information Technology Conference (APIT '24). Association for Computing Machinery, New York, NY, USA, 37–42. https://doi.org/10.1145/3651623.3651629
Zahwa, F., Cheng, C.-T. and Simic, M. 2024. Novel Intelligent Traffic Light Controller Design. Machines 12(7):469–485. doi: https://doi.org/10.3390/machines12070469
