Real-Time Traffic Surveillance: Aerial Vehicle Detection, Tracking, and Counting with YOLOv7

Article Sidebar

PDF
Published: Jun 19, 2025
Keywords:
Aerial surveillance system Detection Intelligent traffic management Vehicle classification YOLOv7

Main Article Content

Vishakha Singh
Department of Electrical and Computer Engineering, Faculty of Engineering, Thammasat School of Engineering, Thammasat University, Pathum Thani 12120, Thailand
Phisan Kaewprapha
Department of Electrical and Computer Engineering, Faculty of Engineering, Thammasat School of Engineering, Thammasat University, Pathum Thani 12120, Thailand

Abstract

In this research, we present an advanced aerial surveillance system powered by the YOLOv7 object detection model, designed for automatic and on-demand collection of traffic data. The system uses unmanned aerial vehicles (UAVs) to capture real-time video, making it especially valuable in areas without fixed surveillance cameras, such as rural roads and busy highways. It accurately detects, classifies, and tracks eight types of vehicles, and includes vehicle counting with directional analysis (left, right, or straight). This comprehensive approach enables the extraction of detailed traffic statistics, including flow rates, movement patterns, and vehicle density. Our classification model achieved an overall accuracy of 98.6%, with some vehicle types reaching up to 99.6%, demonstrating the system’s strong performance and practical utility for traffic monitoring.

Article Details

How to Cite
Vishakha Singh, & Phisan Kaewprapha. (2025). Real-Time Traffic Surveillance: Aerial Vehicle Detection, Tracking, and Counting with YOLOv7. Science & Technology Asia, 30(2), 193–203. retrieved from https://ph02.tci-thaijo.org/index.php/SciTechAsia/article/view/252821
Issue
Vol.30 No.2 (April-June 2025)
Section
Engineering
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

References

World Health Organization. Road traffic injuries. Geneva: World Health Organiza-tion; [cited 2022 Jun 20]. Available from:

https://www.who.int/news-room/factsheets/detail/road-traffic-injuries.

Caputo AC. Digital Video Surveillance and Camera. 2nd ed. Oxford: Butterworth-Heinemann; 2014.

Li K, Deng R, Cheng Y, Hu R, Shen K. Research on vehicle detection and recognition based on infrared image and feature extraction. Mob Inf Syst. 2022;2022:1–10.

Nelson A. Computer Vision: You Only Look Once (YOLO) Custom Object Detection with Colab GPU. 1st ed. Birmingham: Packt Publishing; 2020.

Jang DM, Turk M. Car-Rec: A real time car recognition system. In: IEEE Workshop on Applications of Computer Vision (WACV); 2011 Jan 5–7; Kona, HI, USA. IEEE; 2011. p. 599–605.

Song H, Liang H, Li H, Dai Z, Yun X. Vision-based vehicle detection and counting system using deep learning in highway scenes. Eur Transp Res Rev. Springer; [cited 2023 Feb 19]. Available from: https://link.springer.com/article/10.1186/s12544-020-00431-6.

Rajagopalan AN, Burlina P, Chellappa R. Higher order statistical learning for vehicle detection in images. In: Proceedings of the Seventh IEEE International Conference on Computer Vision; 1999 Sep 20–27; Kerkyra, Greece. IEEE; 1999. p. 1204–9. vol. 2.

Ammar A, Koubbaa A, Ahmed M, Saad A, Benjdira B. Vehicle detection from aerial images using deep learning: A comparative study. Electronics. 2021;10(7):820.

Berwo MA, Khan A, Fang Y, Fahim H, Javaid S, Mahmood J, et al. Deep learning techniques for vehicle detection and classification from images/videos: A survey. Sensors (Basel). 2023;23(10):4832.

Alamgir RM, Rahman M, Khan F, Fattah SA, Ahmed MR, Ali MH, et al. Performance analysis of YOLO-based architectures for vehicle detection from traffic images in Bangladesh. In: 2022 5th International Conference on Computer and Information Technology (ICCIT); 2022 Dec 17–19; Cox’s Bazar, Bangladesh. IEEE; 2022. p. 982–7.

Rahman Z, Ami AM, Ullah MA. A real-time wrong-way vehicle detection based on YOLO and centroid tracking. In: 2022 IEEE Region 10 Symposium (TENSYMP); 2022 Jul 1–3; Dhaka, Bangladesh. IEEE; 2022. p. 916–20.

Zhang R, Zheng K, Shi P, Mei Y, Li H, Qiy T. Traffic sign detection based on the improved YOLOv5. Appl Sci. 2023;13(17):9748.

Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, realtime object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun 27–30; Las Vegas, NV, USA. IEEE; 2016. p. 779–88.

Wang C, Bochkovskiy A, Liao L. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [Preprint]. arXiv:2207.02696 [cs.CV]. 2022. Available from: https://doi.org/10.48550/arXiv.2207.02696.

Singh V, Kaewprapha P, Boonmee C. Ad-hoc Aerial-view Vehicle Detection and Tracking for Real-Time Traffic Monitoring Using YOLOv7. 2023 International Electrical Engineering Congress (iEECON). 2023 Mar;8:327–31.

Cyganek B. Object Detection and Recognition in Digital Images. 1st ed. Chichester: John Wiley & Sons; 2013.