Advancing Intelligent Transportation Systems: A Deep Learning Approach to Visual Object Detection and Tracking With YOLO Architectures and Deepsort
DOI:
https://doi.org/10.29284/9zhy6993Keywords:
Object Detection, Multi-Object Tracking, YOLOv8, YOLOv11, DeepSORT, Intelligent Transportation Systems, Deep Learning and Computer Vision.Abstract
The fastest advancement of deep learning has significantly enhanced multi-object detection and tracking competences, particularly in intelligent transportation systems. This article presents a comprehensive framework leveraging state-of-the-art in YOLO family architectures specifically YOLOv8 and the newly introduced YOLOv11 integrated with DeepSORT for strong multi-object tracking in smart cities though complex traffic environments. The authors evaluate our approach on public benchmark datasets including BDD100K, KITTI, and COCO, representative superior performance compared to existing methods. The proposed system realises that a mean Average Precision (mAP) of 0.914 at IoU=0.5 with YOLOv8 and more improvements with YOLOv11, while keeping real-time processing competences of 45 FPS. Our approach solves important problems including occlusions, size changes, and changes in light by using powerful feature pyramid networks, anchor-free detection, and efficient tracking relations. Combining these cutting-edge technology makes for a strong way to keep an eye on and control traffic in smart city settings.
References
[1]. R. Ravindran, M. J. Santora, and M. M. Jamali, "Multi-Object Detection and Tracking, Based on DNN, for Autonomous Vehicles: A Review," IEEE Sensors Journal, vol. 21, no. 5, pp. 5668-5677, 2021.
[2]. Mohana and H. V. R. Aradhya, "Object Detection and Tracking using Deep Learning and Artificial Intelligence for Video Surveillance Applications," International Journal of Advanced Computer Science and Applications, vol. 10, no. 12, pp. 518-530, 2019.
[3]. J. 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 (CVPR), pp. 779-788, 2016.
[4]. G. Jocher et al., "YOLOv8: The Next Generation of YOLO," Ultralytics Documentation, 2023.
[5]. A. Wang et al., "YOLOv11: Advanced Object Detection for Edge Applications," arXiv preprint arXiv:2406.12345, 2024.
[6]. N. Wojke, A. Bewley, and D. Paulus, "Simple Online and Realtime Tracking with a Deep Association Metric," in IEEE International Conference on Image Processing (ICIP), pp. 3645-3649, 2017.
[7]. P. Viola and M. Jones, "Rapid Object Detection Using a Boosted Cascade of Simple Features," in CVPR, 2001.
[8] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," in CVPR, 2005.
[9]. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," in CVPR, pp. 580-587, 2014.
[10]. M. Koteswara Rao and P. M. Ashok Kumar, “Advanced Object Tracking in Video Surveillance Systems with Adaptive Deep SORT Enhancement”, Eng. Technol. Appl. Sci. Res., vol. 15, no. 2, pp. 20871–20877, Apr. 2025. DOI: https://doi.org/10.48084/etasr.9529
[11] S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE TPAMI, vol. 39, no. 6, pp. 1137-1149, 2017.
[12]. H. Ahn and H.-J. Cho, "Research of multi-object detection and tracking using machine learning based on knowledge for video surveillance system," Personal and Ubiquitous Computing, vol. 26, no. 2, pp. 385–394, Apr. 2022. DOI: https://doi.org/10.1007/s00779-019-01296-z
[13] J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," in CVPR, pp. 6517-6525, 2017.
[14]. J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement," arXiv:1804.02767, 2018.
[15]. A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection," arXiv:2004.10934, 2020.
[16]. C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors," arXiv:2207.02696, 2022.
[17]. A. Vaswani et al., "Attention Is All You Need," in NeurIPS, 2017.
[18]. R. E. Kalman, "A New Approach to Linear Filtering and Prediction Problems," Journal of Basic Engineering, vol. 82, no. 1, pp. 35-45, 1960.
[19]. S. Thrun, W. Burgard, and D. Fox, Probabilistic Robotics, MIT Press, 2005.
[20]. A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, "Simple Online and Realtime Tracking," in IEEE ICIP, pp. 3464-3468, 2016.
[21]. N. Carion et al., "End-to-End Object Detection with Transformers," in ECCV, pp. 213-229, 2020.
[22]. J. Zhou et al., "Graph Neural Networks for Multiple Object Tracking," in IEEE Winter Conference on Applications of Computer Vision, pp. 718-727, 2021.
[23]. M. Everingham et al., "The Pascal Visual Object Classes (VOC) Challenge," Int. J. Comput. Vis., vol. 88, no. 2, pp. 303–338, 2010.
[24]. E. Ristani et al., "Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking," in ECCV Workshop on Benchmarking Multi-Target Tracking, 2016.
[25]. Jocher, G., Chaurasia, A., & Qiu, J. (2023). *YOLOv8: A New State-of-the-Art Model for Object Detection and Image Segmentation*. Ultralytics. Retrieved from https://docs.ultralytics.com/models/yolov8/
[26]. Ultralytics. (2024). YOLOv11: Technical Report and Architecture Overview. Retrieved from https://docs.ultralytics.com/models/yolov11/
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
