AI-Based Emergency Vehicle Detection and Smart Traffic Signal Prioritization Using YOLOv8 and Arduino

Abstract

Traffic congestion is a major challenge in modern urban environments, often causing delays for emergency vehicles such as ambulances and fire trucks. Traditional traffic management systems operate on predefined signal timing schedules and lack mechanisms to prioritize emergency vehicles. This paper presents a Smart AI Traffic Assistance System that combines Computer Vision, Artificial Intelligence, and Internet of Things (IoT) technologies to automate traffic signal prioritization. The proposed system utilizes the YOLOv8 object detection framework to identify emergency vehicles from live video streams. Additional verification is performed using HSV-based red light detection and optional siren detection. Upon successful identification, the system communicates with an Arduino-based traffic controller to create a green corridor. A Streamlit dashboard provides real-time monitoring, status visualization, and event logging. Experimental evaluation demonstrated an overall detection accuracy of 86%, an average detection latency of 320 ms, and an end-to-end response time of approximately 405 ms. The results indicate that the proposed solution can serve as a cost-effective and scalable alternative for intelligent traffic management in smart city environments.

Introduction

Urban traffic congestion increasingly delays emergency vehicles, reducing the effectiveness of critical services like ambulances and fire trucks. Traditional traffic systems are static and cannot dynamically prioritize emergency situations, leading to potentially life-threatening delays. To solve this, the study proposes a Smart AI Traffic Assistance System that enables real-time detection and traffic signal control for emergency vehicles.

The system uses YOLOv8-based computer vision to detect vehicles from live camera feeds and identifies emergency vehicles using additional verification methods such as HSV-based flashing light detection and audio-based siren detection using FFT. Once an emergency vehicle is confirmed, the system automatically sends commands to an Arduino-based controller, which activates a “green corridor” by changing traffic signals to allow smooth passage.

The architecture is divided into four layers: sensing (camera and microphone input), processing (YOLOv8 detection and signal analysis), control (Arduino traffic signal control), and presentation (Streamlit dashboard for monitoring). The workflow includes capturing video, detecting vehicles, verifying emergency signals, and dynamically controlling traffic lights in real time.

Conclusion

This paper presented a Smart AI Traffic Assistance System that combines YOLOv8, OpenCV, Arduino, and IoT technologies to prioritize emergency vehicles at traffic intersections. Experimental evaluation demonstrated reliable performance with an overall accuracy of 86% and an end-to-end response time of 405 ms. The proposed solution offers a practical and cost-effective approach toward intelligent transportation systems and smart city infrastructure.

References

[1] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” Proc. IEEE CVPR, 2016. [2] J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” Proc. IEEE CVPR, 2017. [3] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arXiv:1804.02767, 2018. [4] G. Jocher et al., “Ultralytics YOLOv8 Documentation,” Ultralytics, 2024. [5] R. Szeliski, Computer Vision: Algorithms and Applications, 2nd ed., Springer, 2022. [6] G. Bradski, “The OpenCV Library,” Dr. Dobb’s Journal of Software Tools, 2000. [7] A. Rosebrock, Practical Python and OpenCV, PyImageSearch, 2023. [8] M. A. Khan, M. E. Ahmed, and S. A. Khan, “Intelligent Traffic Management System Using Computer Vision and IoT,” International Journal of Intelligent Transportation Systems Research, vol. 20, no. 3, pp. 245–258, 2022. [9] P. Kumar and R. Singh, “Smart Traffic Signal Control System Using Artificial Intelligence,” International Journal of Engineering Research & Technology (IJERT), vol. 11, no. 4, pp. 321–326, 2022. [10] S. Sharma and A. Gupta, “AI-Based Traffic Monitoring and Congestion Control System,” Procedia Computer Science, vol. 167, pp. 1952–1961, 2020. [11] A. K. Mishra and P. Verma, “Emergency Vehicle Detection and Traffic Signal Prioritization Using Deep Learning,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 5, pp. 215–223, 2023. [12] R. Patel, V. Shah, and D. Mehta, “Real-Time Ambulance Detection Using YOLO for Smart City Applications,” IEEE International Conference on Smart Computing, 2023. [13] S. N. Reddy and K. Rao, “Emergency Vehicle Preemption Using Computer Vision and IoT,” International Conference on Intelligent Transportation Systems, 2022. [14] Arduino, “Arduino Uno Rev3 Technical Specifications,” Arduino Documentation, 2024. [15] A. Bahga and V. Madisetti, Internet of Things: A Hands-On Approach, Universities Press, 2015. [16] O. Hersent, D. Boswarthick, and O. Elloumi, The Internet of Things: Key Applications and Protocols, Wiley, 2012. [17] D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed., Pearson, 2023. [18] M. Cowling and R. Sitte, “Comparison of Techniques for Environmental Sound Recognition,” Pattern Recognition Letters, vol. 24, no. 15, pp. 2895–2907, 2003. [19] Ministry of Road Transport and Highways, Government of India, “Intelligent Transportation Systems (ITS) Guidelines,” 2024. [20] W. Schrank, B. Eisele, and T. Lomax, “Urban Mobility Report,” Texas A&M Transportation Institute, 2023.

Copyright

Copyright © 2026 Harsh Kumar. This 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.