ArticleOpen Access http://dx.doi.org/10.26855/aitcs.2025.06.003
Deep Learning-based FPV Drone Target Detection
Junfei Chen1,*, Bolin He2
1Immersion Academy, 4010 Barranca Parkway Suite 252, Irvine, California 92604, China.
2Wuhan Britain-China School, Wuhan Britain-China School (Qingyun Campus), No. 10 Gutian Ce Road, Qiaokou District, Wuhan 430034, China.
*Corresponding author: Junfei Chen
Published: October 13,2025
Abstract
With the rapid development of unmanned aerial vehicle (UAV) technology and its expanding applications, potential security risks have become increasingly prominent. Some malicious actors exploit UAVs for unlawful activities. These UAVs are typically small in size, fast, and highly maneuverable, making them difficult to detect with traditional surveillance methods. Therefore, the exploration of more precise and efficient UAV detection methods carries considerable practical significance. In this study, based on real-world scenarios, first-person view (FPV) and racing drones were employed to collect image and video datasets containing multiple UAVs. The datasets were then annotated for training. Subse-quently, the YOLOv11 object detection algorithm was applied for model training, enabling automatic detection and recognition of UAV positions within images. This approach provides a feasible technical pathway for UAV target detection and lays the groundwork for future studies on UAV monitoring in more complex environments.
Keywords
Object Detection; Aerial Targets; YOLOv11; FPV Drone Perspective
References
[1] YANG Y, JIANG W, GAO Z. Real-time target detection algorithm for low altitude UAVs. Acta Aeronautica et Astronautica Sinica [Internet]. [cited 2025 Aug 19];1-13. Available from: (Note: The journal's official citation style may differ; this follows Vancou-ver conventions for an online first article with a known citation date but no volume/issue/pagination).
[2] Lin F, Peng K, Dong X, Zhao S, Chen BM. Vision-based formation for UAVs. In: Proceedings of the IEEE International Conference on Control and Automation (ICCA). 2014. p. 1375-80.
[3] Gökçe F, Üçoluk G, Şahin E, Kalkan S. Vision-based detection and distance estimation of micro unmanned aerial vehicles. Sensors [Internet]. 2015 [cited 2025 Oct 11];15(9):23805-46. Available from: https://doi.org/10.3390/s150923805
[4] James J, Ford JJ, Molloy TL. Learning to detect aircraft for long-range vision-based sense-and-avoid systems. IEEE Robot Autom Lett. 2018 Oct;3(4):4383-90.
[5] Rozantsev A, Lepetit V, Fua P. Flying objects detection from a single moving camera. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2015. p. 4128-36.
[6] Chen Y, Aggarwal P, Choi J, Kuo CCJ. A deep learning approach to drone monitoring. In: Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 2017. p. 686-91.
[7] Peng X, Sun B, Ali K, Saenko K. Learning deep object detectors from 3D models. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2015. p. 1278-86.
[8] Walter V, Vrba M, Saska M. On training datasets for machine learning-based visual relative localization of micro-scale UAVs. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). 2020. p. 10674-80.
How to cite this paper
Deep Learning-based FPV Drone Target Detection
How to cite this paper: Junfei Chen, Bolin He. (2025) Deep Learning-based FPV Drone Target Detection. Advance in Information Technology and Computer Science, 2(1), 14-18.
DOI: http://dx.doi.org/10.26855/aitcs.2025.06.003