Urban-Trafficnet: Novel Stereo-Based Yolo Model for Vehicle‎Categorization, Position, and Speed Analysis in Dense Urban ‎Environment

  • Authors

    • Ms. Apoorva A. Shah Research Scholar, Department of CSE, Drs. Kiran and Pallavi Patel Global University, Vadodara, Gujarat, India
    • Dr. Nitesh Sureja Professor, Department of CSE, Drs. Kiran and Pallavi Patel Global University, Vadodara, Gujarat, India
    • Dr. Betty Paulraj Assistant Professor Grade III, Amity University, Uttar Pradesh, Noida, India
    https://doi.org/10.14419/qrj60s20

    Received date: July 7, 2025

    Accepted date: August 6, 2025

    Published date: August 12, 2025

  • Speed Estimation; Stereo Vision; Traffic Management; Vehicle Classification; YOLOv5

  • Abstract

    Accurate vehicle classification and speed estimation are essential for effective traffic monitoring and management in urban environments. ‎This study presents a YOLOv5-based deep learning model integrated with an attenuation layer to enhance detection precision across diverse ‎vehicle categories. The system classifies stereo vision-based footage into seven major groups. A stereo camera setup captures live traffic ‎scenarios, allowing for depth estimation to determine object positions and velocities. The attenuation layer refines feature extraction by ‎reducing background noise, thereby increasing reliability in dense urban conditions. The YOLOv5 model achieved a high detection precision ‎of 99%, validating its effectiveness in multi-class vehicle recognition. The speed estimation method demonstrated high accuracy, with a low ‎margin of error of ±0.05, confirming its suitability for real-time applications. Integration of the attenuation layer significantly improved noise ‎resistance and overall model robustness in complex scenes. Thus, the proposed method enhances both detection accuracy and speed estimation capabilities, supporting advanced intelligent transportation systems for smarter urban traffic management‎.

  • References

    1. Zhang, P., Li, X., Lin, X., He, L.: A New Literature Review of 3D Object Detection on Autonomous Driving. Journal of Artificial Intelligence Re-search. 82, 973–1015 (2025). https://doi.org/10.1613/jair.1.15961.
    2. Rachidi, O., Ed-Dahmani, C., Idrissi, B.B.: A stereo-vision system for real-time person detection in ADAS applications using a fine-tuned version of YOLOv5. Bulletin of Electrical Engineering and Informatics. 14, 250–260 (2025). https://doi.org/10.11591/eei.v14i1.8417.
    3. Ahad, A., Kidwai, F.A.: Mitigating Urban Traffic Congestion Through OPSAM in Delhi: A YOLO-v4 Based Parking Guidance and Information System. Journal of The Institution of Engineers (India): Series A. (2025). https://doi.org/10.1007/s40030-024-00860-y.
    4. Lian, H., Li, M., Li, T., Zhang, Y., Shi, Y., Fan, Y., Yang, W., Jiang, H., Zhou, P., Wu, H.: Vehicle speed measurement method using monocular cameras. Scientific reports. 15, 2755 (2025). https://doi.org/10.1038/s41598-025-87077-6.
    5. Rahman, M.H., Sejan, M.A.S., Aziz, M.A., Tabassum, R., Baik, J.I., Song, H.K.: A Comprehensive Survey of Unmanned Aerial Vehicles Detec-tion and Classification Using Machine Learning Approach: Challenges, Solutions, and Future Directions. Remote Sensing. 16, (2024). https://doi.org/10.3390/rs16050879.
    6. Rodriguez-Quiñonez, J.C., Sanchez-Castro, J.J., Real-Moreno, O., Galaviz, G., Flores-Fuentes, W., Sergiyenko, O., Castro-Toscano, M.J., Hernan-dez-Balbuena, D.: A real-time vehicle safety system by concurrent object detection and head pose estimation via stereo vision. Heliyon. 10, (2024). https://doi.org/10.1016/j.heliyon.2024.e35929.
    7. Sharma, T., Chehri, A., Fofana, I., Jadhav, S., Khare, S., Debaque, B., Duclos-Hindie, N., Arya, D.: Deep Learning-Based Object Detection and Classification for Autonomous Vehicles in Different Weather Scenarios of Quebec, Canada. IEEE Access. 12, 13648–13662 (2024). https://doi.org/10.1109/ACCESS.2024.3354076.
    8. Nosheen, I., Naseer, A., Jalal, A.: Efficient Vehicle Detection and Tracking using Blob Detection and Kernelized Filter. 2024 5th International Conference on Advancements in Computational Sciences, ICACS 2024. (2024). https://doi.org/10.1109/ICACS60934.2024.10473292.
    9. Luo, Z., Bi, Y., Yang, X., Li, Y., Yu, S., Wu, M., Ye, Q.: Enhanced YOLOv5s + DeepSORT method for highway vehicle speed detection and multi-sensor verification. Frontiers in Physics. 12, 1–16 (2024). https://doi.org/10.3389/fphy.2024.1371320.
    10. Mani, P., Komarasamy, P.R.G., Rajamanickam, N., Shorfuzzaman, M., Abdelfattah, W.M.: Enhancing Sustainable Transportation Infrastructure Management: A High-Accuracy, FPGA-Based System for Emergency Vehicle Classification. Sustainability (Switzerland). 16, (2024). https://doi.org/10.3390/su16166917.
    11. Olaye, E., Owraigbo, E., Bello, N.: Estimating cost of pothole repair from digital images using Stereo Vision and Artificial Neural Network. Inter-national Journal of Applied Methods in Electronics and Computers. 12, 1–9 (2024). https://doi.org/10.58190/ijamec.2024.77.
    12. Shekhar, C., Debadarshini, J., Saha, S.: LiVeR: Lightweight Vehicle Detection and Classification in Real-Time. ACM Transactions on Internet of Things. 5, 1–39 (2024). https://doi.org/10.1145/3674150.
    13. Magar, A.T., Osthi, S., Adhikari, N., C, S. K. K.: Multi-model Deep Learning Approaches for Vehicle Speed Estimation. Kathford Journal of En-gineering and Management. 4, 21–30 (2024). https://doi.org/10.3126/kjem.v4i1.74702.
    14. Tahir, N.U.A., Zhang, Z., Asim, M., Chen, J., ELAffendi, M.: Object Detection in Autonomous Vehicles under Adverse Weather: A Review of Traditional and Deep Learning Approaches. Algorithms. 17, 1–36 (2024). https://doi.org/10.3390/a17030103.
    15. Shabbir, A., Cheema, A.N., Ullah, I., Almanjahie, I.M., Alshahrani, F.: Smart City Traffic Management: Acoustic-Based Vehicle Detection Using Stacking-Based Ensemble Deep Learning Approach. IEEE Access. 12, 35947–35956 (2024). https://doi.org/10.1109/ACCESS.2024.3370867.
    16. Yusuf, M.O., Hanzla, M., Jalal, A.: Vehicle Detection and Classification via YOLOv4 and CNN over Aerial Images. Proceedings - 2024 Interna-tional Conference on Engineering and Computing, ICECT 2024. (2024). https://doi.org/10.1109/ICECT61618.2024.10581252.
    17. Zhang, L., Xu, W., Shen, C., Huang, Y.: Vision-Based On-Road Nighttime Vehicle Detection and Tracking Using Improved HOG Features. Sen-sors. 24, 1–14 (2024). https://doi.org/10.3390/s24051590.
    18. Farid, A., Hussain, F., Khan, K., Shahzad, M., Khan, U., Mahmood, Z.: A Fast and Accurate Real-Time Vehicle Detection Method Using Deep Learning for Unconstrained Environments. Applied Sciences (Switzerland). 13, (2023). https://doi.org/10.3390/app13053059.
    19. Kumar, S., Singh, S.K., Varshney, S., Singh, S., Kumar, P., Kim, B.G., Ra, I.H.: Fusion of Deep Sort and Yolov5 for Effective Vehicle Detection and Tracking Scheme in Real-Time Traffic Management Sustainable System. Sustainability (Switzerland). 15, (2023). https://doi.org/10.3390/su152416869.
    20. Li, S., Yoon, H.-S.: Sensor Fusion-Based Vehicle Detection and Tracking Using a Single Camera and Radar at a Traffic Intersection. Sensors. 23, 4888 (2023). https://doi.org/10.3390/s23104888.
    21. Ultralytics. “YOLOv8 vs YOLOv5: A Detailed Comparison.” Ultralytics YOLO Docs, updated July 2025, https://docs.ultralytics.com/compare/yolov5-vs-yolov8/. Accessed 5 Aug. 2025
    22. Khanam, R., Asghar, T., Hussain, M.: Comparative Performance Evaluation of YOLOv5, YOLOv8, and YOLOv11 for Solar Panel Defect Detec-tion. Solar. 5, 1–25 (2025). https://doi.org/10.3390/solar5010006.
    23. An, H., Tang, J., Fan, Y., Liu, M.: Improved Vehicle Object Detection Algorithm Based on Swin-YOLOv5s. Processes. 13, (2025). https://doi.org/10.3390/pr13030925.

  • Downloads

  • How to Cite

    Shah , M. A. A. ., Sureja , D. N. ., & Paulraj , D. B. . (2025). Urban-Trafficnet: Novel Stereo-Based Yolo Model for Vehicle‎Categorization, Position, and Speed Analysis in Dense Urban ‎Environment. International Journal of Basic and Applied Sciences, 14(4), 330-338. https://doi.org/10.14419/qrj60s20