Optimizing traffic management in Danang: a comparative study of multi-object tracking techniques for real-time vehicle flow monitoring

DOI https://doi.org/10.31130/ud-jst.2024.022ICT

Abstract: 1019 | PDF: 752

##plugins.themes.academic_pro.article.main##

Author

  • Hai T. Ton
    The University of Danang - University of Science and Technology, Vietnam
    Hung V. Nguyen
    The University of Danang - University of Science and Technology, Vietnam
    Hanh T. M. Tran
    The University of Danang - University of Science and Technology, Vietnam
    Tien V. Thai
    The University of Danang - University of Science and Technology, Vietnam
    Phong-Phu Le
    National Cheng Kung University, Tainan, Taiwan
    Tung T. Huynh
    The University of Danang - University of Science and Technology, Vietnam
    Duy-Tuan Dao
    The University of Danang - University of Science and Technology, Vietnam

Keywords:

Traffic Flow Monitoring
Object Detection
YOLOv8
Multiple Object Tracking (MOT)

Abstract

This study evaluates the effectiveness of various detection-based object-tracking algorithms to optimize accuracy and efficiency in traffic flow monitoring. Due to its high accuracy in detecting objects, YOLOv8 was chosen as the vehicle detector for this research, where precise and rapid vehicle detection was critical. Regarding object tracking, our focus centered on the evaluation of five prominent Multiple Object Tracking (MOT) algorithms, including BoTSORT, ByteTrack, DeepOCSORT, OCSORT, and StrongSORT. We introduce a comprehensive traffic urban dataset collected from intricate street networks in Danang City. Our experimental results show that the system has practical applicability in urban traffic monitoring. Notably, the best model achieves a detection accuracy of 0.721 on mAP@0.5-0.95, and the High Overlap Tracking Accuracy (HOTA) surpasses 72% for tracking performance across diverse traffic scenarios. This shows the applicability of MOT algorithms and provides a detailed view of traffic flow monitoring, especially in Danang City, Vietnam.

References

    [1] Nam, "Summary of number of vehicles delivered nationwide”, http://www.vr.org.vn, 2022. [Online]. Available: http://www.vr.org.vn/thong-ke/Pages/tong-hop-so-lieu-phuong-tien-giao-thong-trong-ca-nuoc.aspx [Accessed August 09, 2023].
    [2] Mandal and Y. Adu-Gyamfi, "Object detection and tracking algorithms for vehicle counting: a comparative analysis”, Journal of Big Data Analytics in Transportation, vol. 2, pp. 251-261, 2020.
    [3] Kumar, P. Sharma, and N. Pal, "Object tracking and counting in a zone using YOLOv4, DeepSORT and TensorFlow”, in Proceeding of 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), 2021, pp. 1017-1022.
    [4] H. Hung, N. V. Phu, and N. Tuong, "Red Light and Wrong Parking Violation Detection System Based on Deep Learning", The University of Danang - Journal of Science and Technology, vol. 18, no. 5, 2020, pp. 101-105.
    [5] Yang and S. Qu, "Real-time vehicle detection and counting in complex traffic scenes using background subtraction model with low-rank decomposition”, Wiley Online Library, vol. 12, no. 1, pp. 75-85, 2018.
    [6] Li, F. Chang, C. Liu, and N. Li, "Vehicle counting and traffic flow parameter estimation for dense traffic scenes”, Wiley Online Library, vol. 14, no. 12, pp. 1517-1523, 2020.
    [7] P. Mien, T. T. Vu, and N. V. Si, “Estimating Traffic Density in Uncertain Environment: A Case Study of Danang, Vietnam”, The University of Danang - Journal of Science and Technology, vol. 21, no. 6.2, pp. 33-38, 2023.
    [8] T. Minh, Q. V. Dinh, T. D. Nguyen, and T. N. Nhut, "Vehicle Counting on Vietnamese Street”, in Proceeding 2023 IEEE Statistical Signal Processing Workshop (SSP), IEEE, 2023, pp. 160--164.
    [9] Neamah and A. Karim, "Real-time Traffic Monitoring System Based on Deep Learning and YOLOv8”, Aro-the scientific journal of koya university, vol. 11, no. 2, pp. 137-150, 2023.
    [10] Redmon, S. Divvala, R. Girshick, and A. Farhadi "You only look once: Unified, real-time object detection”, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Elsevier, 2016, pp. 779-788.
    [11] Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, and A. C. Berg, "Ssd: Single shot multibox detector”, in Proceeding Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part I 14, Springer, 2016, pp. 21-37.
    [12] Girshick, J. Donahue, T. Darrell, and J. Malik "Rich feature hierarchies for accurate object detection and semantic segmentation”, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 580-587.
    [13] Yilmaz, O. Javed, and M. Shah "Object tracking: A survey”, ACM computing surveys (CSUR), vol. 38, no. 2, pp. 13-es, 2006.
    [14] Zhang et al., "Bytetrack: Multi-object tracking by associating every detection box”, in Proceeding of European Conference on Computer Vision, Springer, 2022, pp. 1-21.
    [15] Cao, J. Pang, X. Weng, R. Khirodkar, and K. Kitani "Observation-centric sort: Rethinking sort for robust multi-object tracking”, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9686-9696.
    [16] Maggiolino, A. Ahmad, J. Cao, and K. Kitani, "Deep OC-Sort: Multi-Pedestrian Tracking by Adaptive Re-Identification”, 2023 in Proceeding of IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia, 2023, pp. 3025-3029, doi: 10.1109/ICIP49359.2023. 10222576.
    [17] Aharon, R. Orfaig, and B. Z. Bobrovsky "BoT-SORT: Robust associations multi-pedestrian tracking”, arXiv preprint arXiv:2206.14651, 2022.
    [18] Du et al., "StrongSORT: Make DeepSORT Great Again”, in IEEE Transactions on Multimedia, vol. 25, pp. 8725-8737, 2023, doi: 10.1109/TMM.2023.3240881.
    [19] Milan, L. Leal-Taixé, I. Reid, S. Roth, and K. Schindler, "MOT16: A benchmark for multi-object tracking”, arXiv preprint arXiv:1603.00831, 2016.
    [20] Sun, J. Cao, Y. Jiang, Z. Yuan, S. Bai, K. Kitani, and P. Luo, "Da Aharon track: Multi-object tracking in uniform appearance and diverse motion”, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 20993-21002.
    [21] Kang, C. Xie, J. Yao, L. Xuan, and G. Liu, "Online Multiple Object Tracking with Recurrent Neural Networks and Appearance Model”, 2020 13th International Congress on Image and Signal Processing, BioMedical Engineering, and Informatics (CISP-BMEI), Chengdu, China, 2020, pp. 34-38, doi: 10.1109/CISP-BMEI51763.2020. 9263623.
    [22] Ristani, F. Solera, R. Zou, R. Cucchiara, and C. Tomasi "Performance measures and a data set for multi-target, multi-camera tracking”, in European conference on computer vision, 2016, pp. 17-35.
    [23] J. Luiten, A. Osep, P. Dendorfer, P. Torr, A. Geiger, L. Leal-Taixé, and B. Leibe, "Hota: A higher order metric for evaluating multi-object tracking”, International Journal of Computer Vision, vol. 129, pp. 548-578, 2021.
Read more

##plugins.themes.academic_pro.article.sidebar##

Published

Jun 30, 2024
Download
PDF
How to Cite
Ton, H. T., H. V. Nguyen, H. T. M. Tran, T. V. Thai, P.-P. Le, T. T. Huynh, and D.-T. Dao. “Optimizing Traffic Management in Danang: A Comparative Study of Multi-Object Tracking Techniques for Real-Time Vehicle Flow Monitoring”. The University of Danang - Journal of Science and Technology, vol. 22, no. 6B, June 2024, pp. 32-39, doi:10.31130/ud-jst.2024.022ICT.

##plugins.themes.academic_pro.article.details##