An Integrated Approach for Multi-Object Detection and Tracking in Traffic Monitoring Using YOLOv9c and ByteTrack
Corressponding author's email:
dinhnt@huit.edu.vnDOI:
https://doi.org/10.54644/jte.2026.2077Keywords:
Object Detection, Object Tracking, YOLOv9c, ByteTrack, Traffic MonitoringAbstract
This paper proposes an integrated method for object detection and tracking in congested traffic environments, based on a combination of the YOLOv9c object detection model and the ByteTrack multi-object tracking algorithm. In this proposed method, the YOLOv9c model is trained and fine-tuned to enhance the performance of vehicle detection in complex conditions. Simultaneously, ByteTrack algorithm links objects across extracted video frames by leveraging both high- and low-confidence bounding boxes. This approach reduces the identity loss and increases the stability of object tracking in traffic, especially in conditions with high object density and severe occlusion. To implement this method, the object detection model was trained and refined on the BDD100K dataset, combined with the Vietnam Traffic Dataset, with a focus on common vehicle classes, including bicycles, motorbikes, cars, buses, and trucks. Experimental results showed that the model achieved a Precision of 89.8% and a Recall of 72.7% in the daytime traffic congestion scenario, and a recall rate of 90.1% in nighttime conditions. For the multi-object tracking problem, the system achieved an IDF1 of 84.3%, demonstrating its ability to maintain stable object identification even in the presence of obstructions, and achieved an MOTA of 69.9% under favorable observation conditions. These results confirm that the proposed method is highly effective in detecting and tracking traffic objects and has potential applications in intelligent traffic monitoring systems and real-time video analysis.
Downloads: 0
References
D. Stadler and J. Beyerer, “Modeling ambiguous assignments for multi-person tracking in crowds,” in Proc. IEEE/CVF Winter Conf. Applications of Computer Vision (WACV), 2022. DOI: https://doi.org/10.1109/WACVW54805.2022.00019
S. E. Bekhouche et al., “Driver drowsiness detection in video sequences using hybrid selection of deep features,” Knowledge-Based Systems, vol. 252, art. no. 109436, 2022, doi: 10.1016/j.knosys.2022.109436. DOI: https://doi.org/10.1016/j.knosys.2022.109436
X. Zhang et al., “SkyNet: A hardware-efficient method for object detection and tracking on embedded systems,” in Proc. Conf. Machine Learning and Systems (MLSys), 2020.
X. Lin et al., “CCTSDB dataset enhancement based on a cross-augmentation method for image datasets,” Intelligent Data Analysis, vol. 28, no. 5, pp. 1151–1169, 2024, doi: 10.3233/IDA-230075. DOI: https://doi.org/10.3233/IDA-230075
VTIS Homepage. Accessed: Feb. 2025. [Online]. Available: https://vtis.vn/
R. M. Alamgir et al., “Performance analysis of YOLO-based architectures for vehicle detection from traffic images in Bangladesh,” in Proc. 25th Int. Conf. Computer and Information Technology (ICCIT), 2022. DOI: https://doi.org/10.1109/ICCIT57492.2022.10055758
Z. Liang et al., “Vehicle and pedestrian detection based on improved YOLOv7-Tiny,” Electronics, vol. 13, no. 20, art. no. 4010, 2024, doi: 10.3390/electronics13204010. DOI: https://doi.org/10.3390/electronics13204010
C. Rana, “Artificial intelligence-based object detection and traffic prediction by autonomous vehicles: A review,” Expert Systems with Applications, vol. 255, art. no. 124664, 2024, doi: 10.1016/j.eswa.2024.124664. DOI: https://doi.org/10.1016/j.eswa.2024.124664
Y. Zhang et al., “ByteTrack: Multi-object tracking by associating every detection box,” in Proc. Eur. Conf. Computer Vision (ECCV). Cham, Switzerland: Springer, 2022. DOI: https://doi.org/10.1007/978-3-031-20047-2_1
H. S. Sim and H. C. Cho, “Enhanced DeepSORT and StrongSORT for multicattle tracking with optimized detection and re-identification,” IEEE Access, vol. 13, pp. 19353–19364, 2025, doi: 10.1109/ACCESS.2025.3535092. DOI: https://doi.org/10.1109/ACCESS.2025.3535092
J. Cao et al., “Observation-centric SORT: Rethinking SORT for robust multi-object tracking,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2023. DOI: https://doi.org/10.1109/CVPR52729.2023.00934
B. C. Krishna et al., “Real-time object detection using YOLOv9c and Flask web application,” in Proc. IEEE Delhi Section Flagship Conf. (DELCON), 2024. DOI: https://doi.org/10.1109/DELCON64804.2024.10866465
H. T. Nguyen et al., “YOLOv9c: A robust framework for insect detection,” in Proc. Int. Conf. Multi-disciplinary Trends in Artificial Intelligence. Cham, Switzerland: Springer, 2024. DOI: https://doi.org/10.1007/978-981-96-0695-5_3
Y. Wang and V. Y. Mariano, “A multi-object tracking framework based on YOLOv8s and ByteTrack,” IEEE Access, vol. 12, pp. 120711–120719, 2024, doi: 10.1109/ACCESS.2024.3450370. DOI: https://doi.org/10.1109/ACCESS.2024.3450370
H. Zhao et al., “A fish appetite assessment method based on improved ByteTrack and spatiotemporal graph convolutional network,” Biosystems Engineering, vol. 240, pp. 46–55, 2024, doi: 10.1016/j.biosystemseng.2024.02.011. DOI: https://doi.org/10.1016/j.biosystemseng.2024.02.011
P. Azevedo and V. Santos, “Comparative analysis of multiple YOLO-based target detectors and trackers for ADAS in edge devices,” Robotics and Autonomous Systems, vol. 171, art. no. 104558, 2024, doi: 10.1016/j.robot.2023.104558. DOI: https://doi.org/10.1016/j.robot.2023.104558
J. Pang et al., “Quasi-dense similarity learning for multiple object tracking,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2021. DOI: https://doi.org/10.1109/CVPR46437.2021.00023
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Journal of Technical Education Science
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © JTE.
