Yolov8-Based Vehicle Detection and Traffic Density Estimation for Adaptive Traffic Signal Applications

Fixed-time traffic signals cannot respond to short-term changes in vehicle demand and may allocate green time inefficiently at urban intersections. This study developed and evaluated a YOLOv8-based vehicle-detection and traffic-density estimation prototype for adaptive signal applications. Two public traffic-intersection datasets supplied 3,300 images, of which 2,932 were retained after quality screening. Images were resized to 640 × 640 pixels, annotated with vehicle bounding boxes, and augmented through ±25% brightness and saturation adjustments. YOLOv8 was trained for 50 epochs using 70:30, 80:20, and 90:10 training-testing splits and was compared with Faster R-CNN under the 70:30 configuration. YOLOv8 achieved mAP@0.5 values of 0.989–0.992 and mAP@0.5:0.95 values of 0.962–0.965. Under the direct comparison, YOLOv8 obtained 0.989 mAP@0.5, 0.962 mAP@0.5:0.95, and 0.980 recall, while requiring 1.9 ms per image compared with 28.4 ms for Faster R-CNN. The detector was integrated into a web prototype that displayed vehicle counts, estimated density, and signal duration. The results support YOLOv8 as an efficient traffic-monitoring component, although density-classification accuracy and traffic-flow improvement require separate validation.

YOLOv8, vehicle detection, traffic density estimation, adaptive traffic signal, computer vision

1. Agafonov, A. (2022). Adaptive traffic light control using a distributed processing approach. In 2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON) (pp. 186–189). IEEE. https://doi.org/10.1109/SIBIRCON56155.2022.10016941 [Google Scholar] [Crossref]

2. Biradar, V., Chandra Mohanty, S., Kumar Jana, A., & Krishna Goswami, B. (2022). Image processing based intelligent traffic lighting system. In 2022 IEEE International Women in Engineering Conference on Electrical and Computer Engineering (pp. 290–293). IEEE. https://doi.org/10.1109/WIECON-ECE57977.2022.10151401 [Google Scholar] [Crossref]

3. Bouderba, S. I., & Moussa, N. (2019). Reinforcement learning using Q-learning for a traffic light controller within an intersection traffic system. In Proceedings of the International Conference on Intelligent Systems and Computer Vision. Association for Computing Machinery. https://doi.org/10.1145/3372938.3372999 [Google Scholar] [Crossref]

4. Gaouar, N., & Lehsaini, M. (2021). A cloud computing-based intelligent traffic control system for vehicular networks. In Proceedings of the ACM International Conference. Association for Computing Machinery. https://doi.org/10.1145/3454127.3456600 [Google Scholar] [Crossref]

5. Kanungo, A., Sharma, A., & Singla, C. (2014). Smart traffic lights switching and traffic density calculation using video processing. In 2014 Recent Advances in Engineering and Computational Sciences (pp. 1–6). IEEE. https://doi.org/10.1109/RAECS.2014.6799542 [Google Scholar] [Crossref]

6. Kumar, N., Rahman, S. S., & Dhakad, N. (2021). Fuzzy inference-enabled deep reinforcement learning-based traffic light control for intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems, 22(8), 4919–4928. https://doi.org/10.1109/TITS.2020.2984033 [Google Scholar] [Crossref]

7. Minh, Q. T., Tran, C. M., Le, T. A., Nguyen, B. T., Tran, T. M., & Balan, R. K. (2018). FogFly: A traffic light optimization solution based on fog computing. In UbiComp/ISWC 2018: Adjunct proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2018 ACM International Symposium on Wearable Computers (pp. 1130–1139). Association for Computing Machinery. https://doi.org/10.1145/3267305.3274169 [Google Scholar] [Crossref]

8. Mou, A. R., Milanova, M., & Piya, S. S. (2023). Intelligent traffic control system using YOLO algorithm for traffic-congested cities. In Proceedings of the 2023 Congress in Computer Science, Computer Engineering, and Applied Computing (pp. 2014–2019). IEEE. https://doi.org/10.1109/CSCE60160.2023.00331 [Google Scholar] [Crossref]

9. Sankaranarayanan, M., Yerramsetty, S., Kakkera, S., & Kumar, N. (2024). Adaptive genetic algorithm for reducing average waiting time for road traffic signals. In 2024 5th International Conference on Innovative Trends in Information Technology. IEEE. https://doi.org/10.1109/ICITIIT61487.2024.10580688 [Google Scholar] [Crossref]

10. Septyanto, A. W., Rosyida, I., & Suryono, S. (2021). A fuzzy rule-based fog-cloud system for controlling traffic light duration based on road density. In 2021 6th International Conference on Informatics and Computing. IEEE. https://doi.org/10.1109/ICIC54025.2021.9632941 [Google Scholar] [Crossref]

11. Shankaran, S., & Rajendran, L. (2021). Real-time adaptive traffic control system for smart cities. In 2021 International Conference on Computer Communication and Informatics. IEEE. https://doi.org/10.1109/ICCCI50826.2021.9402597 [Google Scholar] [Crossref]

12. Siripatana, B., Nopchanasuphap, K., & Chuai-Aree, S. (2021). Intelligent traffic light system using image processing. In 2021 2nd SEA-STEM International Conference (pp. 14–18). IEEE. https://doi.org/10.1109/SEA-STEM53614.2021.9668057 [Google Scholar] [Crossref]

13. Sirphy, S., & Thanga Revathi, S. (2023). Adaptive traffic control system using YOLO. In 2023 International Conference on Computer Communication and Informatics. IEEE. https://doi.org/10.1109/ICCCI56745.2023.10128619 [Google Scholar] [Crossref]

14. Talukdar, R., Dutta, S., & Das, S. (2023). Enhancing skin disease diagnosis through convolutional neural networks and YOLOv8 object detection. In 2023 7th International Conference on Electronics, Materials Engineering and Nano-Technology. IEEE. https://doi.org/10.1109/IEMENTech60402.2023.10423482 [Google Scholar] [Crossref]

15. Tigga, A., Hota, L., Patel, S., & Kumar, A. (2022). A deep Q-learning-based adaptive traffic light control system for urban safety. In Proceedings of the 2022 4th International Conference on Advances in Computing, Communication Control and Networking (pp. 2430–2435). IEEE. https://doi.org/10.1109/ICAC3N56670.2022.10074123 [Google Scholar] [Crossref]

16. Ultralytics. (2024, January 15). YOLOv8 architecture: Deep dive into its architecture. YOLOv8. https://yolov8.org/yolov8-architecture/#Key_Innovations_in_YOLOv8 [Google Scholar] [Crossref]

17. Xu, Z., Wang, P., Zhang, L., Qi, F., & Wang, G. (2022). Adaptive traffic signal control based on a dueling deep Q-learning network. In Proceedings of the ACM International Conference (pp. 297–301). Association for Computing Machinery. https://doi.org/10.1145/3584376.3584431 [Google Scholar] [Crossref]

18. Zaatouri, K., & Ezzedine, T. (2018). A self-adaptive traffic light control system based on YOLO. In 2018 International Conference on Internet of Things, Embedded Systems and Communications (pp. 16–19). IEEE. https://doi.org/10.1109/IINTEC.2018.8695293 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet