Author(s)

Yuhong Li ¹

Affiliation(s)

¹ Shenzhen Wisdom Nebula AI Technology Co., Ltd., Xili Street, Nanshan District, Shenzhen, China

Corresponding Author

Yuhong Li

ABSTRACT

Vehicle tracking and counting are essential components of Intelligent Transportation Systems (ITS), yet achieving optimal balance between high accuracy and real-time processing remains a critical challenge, especially in high-density aerial surveillance scenarios. This paper presents a robust framework for vehicle tracking and bi-directional counting, validated on a challenging 35-second aerial traffic segment. We systematically evaluate the efficacy of the You Only Look Once (YOLOv8) architecture, comparing the YOLOv8n and YOLOv8m variants to establish the trade-off between detection precision and inference speed. Furthermore, we investigate three distinct tracking mechanisms—simple IOU-based tracking and state-of-the-art association algorithms (BoT-SORT and ByteTrack). The study's core innovation includes an optimized vector-based counting logic that significantly enhances the robustness of bi-directional counting by minimizing false positives resulting from trajectory jitter and occlusion. Experimental results, conducted on a MacBook Air M3 CPU, demonstrate that the heavier YOLOv8m paired with ByteTrack achieved the highest accuracy, realizing a perfect 100.0% counting score. The YOLOv8n paired with ByteTrack offered the optimal trade-off for real-time applications, reaching a high accuracy of 97.6% at a speed of 20.3 FPS. This work confirms that advanced, high-performance tracking is indispensable for high-accuracy counting, providing a practical benchmark for selecting efficient models and trackers for real-time aerial traffic video analytics.

KEYWORDS

YOLOv8, Multi-Object Tracking, Real-Time Efficiency, Traffic Counting

CITE THIS PAPER

Yuhong Li, Real-Time Bi-Directional Traffic Counting: A Comparative Study on the Efficiency and Accuracy Trade-offs of YOLOv8 and Advanced Association Algorithms. Journal of Image Processing Theory and Applications (2025) Vol. 8: 170-177. DOI: http://dx.doi.org/10.23977/jipta.2025.080120.

REFERENCES

[1] Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779-788.
[2] Wang, C. Y., Bochkovskiy, A., & Liao, H. Y. M. (2022) YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. arXiv preprint arXiv, 2207.02696. 
[3] Bochinski, E., Eiselein, V., and Sikora, T. (2017) High-Speed Tracking-by-Detection without Using Image Information. International Conference on Advanced Video and Signal Based Surveillance (AVSS), 1-6.
[4] Gunjal, P.R.,  Gunjal, B.R.,  Shinde, H.A.,  Vanam, S.M. and Aher, S.S. Moving Object Tracking Using Kalman Filter. (2018) International Conference On Advances in Communication and Computing Technology (ICACCT), 544-547.
[5] Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., and Wang, X. (2022) Bytetrack: Multi-Object Tracking by Associating Every Detection Box. European Conference on Computer Vision (ECCV), 1-21.  
[6] Aharon, N., Orfaig, R., and Bobrovsky, B.Z. (2022) BoT-SORT: Robust Associations Multi-pedestrian Ttracking. arXiv preprint arXiv, 2206.14651.
[7] Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., and Ling, H. (2018) The VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results. International Conference on Computer Vision Workshops (ICCVW).

Sponsors, Associates, and Links

---

• Power Systems Computation
  
  
• Internet of Things (IoT) and Engineering Applications
  
  
• Computing, Performance and Communication Systems
  
  
• Journal of Artificial Intelligence Practice
  
  
• Advances in Computer, Signals and Systems
  
  
• Journal of Network Computing and Applications
  
  
• Journal of Web Systems and Applications
  
  
• Journal of Electrotechnology, Electrical Engineering and Management
  
  
• Journal of Wireless Sensors and Sensor Networks
  
  
• Mobile Computing and Networking
  
  
• Vehicle Power and Propulsion
  
  
• Frontiers in Computer Vision and Pattern Recognition
  
  
• Knowledge Discovery and Data Mining Letters
  
  
• Big Data Analysis and Cloud Computing
  
  
• Electrical Insulation and Dielectrics
  
  
• Crypto and Information Security
  
  
• Journal of Neural Information Processing
  
  
• Collaborative and Social Computing
  
  
• International Journal of Network and Communication Technology
  
  
• File and Storage Technologies
  
  
• Frontiers in Genetic and Evolutionary Computation
  
  
• Optical Network Design and Modeling
  
  
• Journal of Virtual Reality and Artificial Intelligence
  
  
• Natural Language Processing and Speech Recognition
  
  
• Journal of High-Voltage
  
  
• Programming Languages and Operating Systems
  
  
• Visual Communications and Image Processing
  
  
• Journal of Systems Analysis and Integration
  
  
• Knowledge Representation and Automated Reasoning
  
  
• Review of Information Display Techniques
  
  
• Data and Knowledge Engineering
  
  
• Journal of Database Systems
  
  
• Journal of Cluster and Grid Computing
  
  
• Cloud and Service-Oriented Computing
  
  
• Journal of Networking, Architecture and Storage
  
  
• Journal of Software Engineering and Metrics
  
  
• Visualization Techniques
  
  
• Journal of Parallel and Distributed Processing
  
  
• Journal of Modeling, Analysis and Simulation
  
  
• Journal of Privacy, Trust and Security
  
  
• Journal of Cognitive Informatics and Cognitive Computing
  
  
• Lecture Notes on Wireless Networks and Communications
  
  
• International Journal of Computer and Communications Security
  
  
• Journal of Multimedia Techniques
  
  
• Automation and Machine Learning
  
  
• Computational Linguistics Letters
  
  
• Journal of Computer Architecture and Design
  
  
• Journal of Ubiquitous and Future Networks