Published on: April 2026
DYNAMIC AI TRAFFIC CONTROLLER: REAL-TIME INTERSECTION MANAGEMENT USING YOLOV8 WITH WEIGHTED DENSITY ESTIMATION AND EMERGENCY VEHICLE OVERRIDE
A. Shashidhar V. Alfred A. Sanjay O. Rajesh
B. Sreelatha
Article Status
Available Documents
Abstract
Traditional urban traffic systems mainly rely on fixed-time signals that cannot adapt to real-time traffic changes or prioritise emergency vehicles effectively. This work presents an intelligent real-time intersection controller using the YOLOv8 deep learning model to detect and classify vehicles across four lanes simultaneously. A congestion scoring approach is used to measure traffic density by assigning different weights to vehicle types such as two-wheelers, cars, buses, and trucks. Based on these scores, green signal durations are dynamically adjusted to match actual road usage. The system also includes an emergency detection feature that identifies ambulances and instantly gives priority to their lane. This significantly reduces emergency delays from more than two minutes to under ten seconds. Experimental results show that the system reduces waiting time by up to 90% compared to traditional fixed-timer methods. A user-friendly dashboard built with Flask provides real-time analytics and visual insights. Data is stored using a lightweight SQLite database. Overall, the proposed system is a cost-effective and scalable solution for smart traffic management.
How to Cite this Paper
Shashidhar, A., Alfred, V., Sanjay, A. & Rajesh, O. (2026). Dynamic AI Traffic Controller: Real-Time Intersection Management using Yolov8 with Weighted Density Estimation and Emergency Vehicle Override. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(04). https://doi.org/10.55041/ijcope.v2i4.101
Shashidhar, A., et al.. "Dynamic AI Traffic Controller: Real-Time Intersection Management using Yolov8 with Weighted Density Estimation and Emergency Vehicle Override." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i4.101.
Shashidhar, A.,V. Alfred,A. Sanjay, and O. Rajesh. "Dynamic AI Traffic Controller: Real-Time Intersection Management using Yolov8 with Weighted Density Estimation and Emergency Vehicle Override." International Journal of Creative and Open Research in Engineering and Management 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i4.101.
Search & Index
References
- Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in Proc. IEEE CVPR, Las Vegas, NV, USA, 2016, pp. 779–788.
- Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement," arXiv:1804.02767 [cs.CV, 2018].
- Jocher et al., "Ultralytics YOLOv8," Version 8.0, 2023. [Online]. Available: https://github.com/ultralytics/ultralytics
- K. Jaiswal and P. Srivastava, "Deep Learning-Based Vehicle Detection and Classification for Smart City Applications," International Journal of Intelligent Systems and Applications, vol. 15, no. 1,
- 78–86, 2023.
- Luvizon, B. T. Macedo, and R. Schwartz, "Adaptive Traffic Signal Control with Reinforcement Learning," IEEE Trans. Intelligent Transportation Systems, vol. 21, no. 3, pp. 1019–1030, 2020.
- Bradski, "The OpenCV Library", Dr Dobb's Journal of Software Tools, 2000.
- Palffy, J. Dong, J. F. P. Kooij, and D. M. Gavrila, "CNN-Based Road User Detection Using the 3D Radar Cube," IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 1263–1270, 2020.
- -Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, "Focal Loss for Dense Object Detection," in Proc. IEEE ICCV, 2017, pp. 2980–2988.
- Pallets Projects, "Flask: A micro web framework for Python," [Online]. Available: https://flask.palletsprojects.comChart.js Contributors, "Chart.js: Simple yet flexible JavaScript charting library", 2013. [Online]. Available: https://www.chartjs.org
Ethical Compliance & Review Process
- •All submissions are screened under plagiarism detection.
- •Review follows editorial policy.
- •Authors retain copyright.
- •Peer Review Type: Double-Blind Peer Review
- •Published on: Apr 07 2026
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.