(50-2) 15 * << * >> * Russian * English * Contents * All issues

Comparative analysis of neural network models for detecting unmanned aerial vehicles
S.V. Vychegzhanin1, A.G. Tatarinova1, R.E. Myshkin2

1Vyatka State University, Ul. Moskovskaya 36, Kirov, 610000, Russia;
2JSC "SRI of Computer Engineering", Ul. Melnichnaya 31, Kirov, 610025, Russia

  Full text (PDF)

DOI: 10.18287/COJ1728

Article ID: 1728

Abstract:
The paper presents a comparative analysis of YOLO models and their fine-tuning options for the task of real-time unmanned aerial vehicles detection. The quality and computational performance of different model families from YOLOv3 to YOLO12 and versions ranging from nano to extra-large are estimated. Their advantages and disadvantages are analyzed based on a wide range of measures, including precision, recall, F1-measure, average precision, inference time, and model size. Fine-tuning options for pre-trained models trained on the Common Objects in Context dataset are investigated for different input image resolutions and learning rates. We analyze detection errors of small unmanned aerial vehicles in complex environments using specialized datasets. The study showed that the YOLO11 family is the optimal in terms of the set of evaluated parameters, providing a balance between quality and computational performance. The highest quality scores for unmanned aerial vehicles detection on the test dataset were obtained using the fine-tuned yolo11m model with increased input image resolution and achieved values of F1 = 0.970, AP50 = 0.981, AP50-95 = 0.765.

Keywords:
image processing, object detection, neural network algorithms, deep learning, transfer learning.

Citation:
Vychegzhanin SV, Tatarinova AG, Myshkin RE. Comparative analysis of neural network models for detecting unmanned aerial vehicles. Computer Optics 2026; 50(2): 1728. DOI: 10.18287/COJ1728.

References:

  1. Benarbia T, Kyamakya K. A literature review of drone-based package delivery logistics systems and their implementation feasibility. Sustainability 2022; 14(1): 360. DOI: 10.3390/su14010360.
  2. Alsalam BHY, Morton K, Campbell D, Gonzalez F. Autonomous UAV with vision based on-board decision making for remote sensing and precision agriculture. 2017 IEEE Aerospace Conference, Big Sky, MT, USA, 4-11 March 2017: 1-12. DOI: 10.1109/AERO.2017.7943593.
  3. Reedha R, Dericquebourg E, Canals R, Hafiane A. Transformer neural network for weed and crop classification of high resolution UAV images. Remote Sens 2022; 14(3): 592. DOI: 10.3390/rs14030592.
  4. Chamola V, Kotesh P, Agarwal A, Gupta N, Guizani M. A comprehensive review of unmanned aerial vehicle attacks and neutralization techniques. Ad Hoc Netw 2021; 111: 102324. DOI: 10.1016/j.adhoc.2020.102324.
  5. Coveney S, Roberts K. Lightweight UAV digital elevation models and orthoimagery for environmental applications: Data accuracy evaluation and potential for river flood risk modelling. Int J Remote Sens 2017; 38(8-10): 3159-3180. DOI: 10.1080/01431161.2017.1292074.
  6. Agyemang IO, Zhang X, Adjei-Mensah I, Acheampong D, Fiasam LD, Sey C, Yussif SB, Effah D. Automated vision-based structural health inspection and assessment for post-construction civil infrastructure. Autom Constr 2023; 156(2): 105153. DOI: 10.1016/j.autcon.2023.105153.
  7. Turkmen Z, Kuloglu M. A new era for drug trafficking: Drones. Forensic Sci Addict Res 2018; 2(1): 114-118. DOI: 10.31031/FSAR.2018.02.000539.
  8. Mahdavi F, Rajabi R. Drone detection using convolutional neural networks. 2020 6th Iranian Conf on Signal Processing and Intelligent Systems (ICSPIS) 2020: 1-5. DOI: 10.1109/ICSPIS51611.2020.9349620.
  9. Kassab M, Zitar RA, Barbaresco F, Seghrouchni AEF. Drone detection with improved precision in traditional machine learning and less complexity in single shot detectors. IEEE Trans Aerosp Electron Syst 2024; 60(4): 3847-3859. DOI: 10.1109/TAES.2024.3368991.
  10. Cheng F, Liang Z, Peng G, Liu S, Li S, Ji M. An anti-UAV long-term tracking method with hybrid attention mechanism and hierarchical discriminator. Sensors 2022; 22(10): 3701. DOI: 10.3390/s22103701.
  11. Huang B, Li J, Chen J, Wang G, Zhao J, Xu T. Anti-UAV410: A thermal infrared benchmark and customized scheme for tracking drones in the wild. IEEE Trans Pattern Anal Mach Intell 2023; 46(5): 2852-2865. DOI: 10.1109/TPAMI.2023.3335338.
  12. Xie X, Xi J, Yang X, Lu R, Xia W. STFTrack: Spatio-temporal-focused siamese network for infrared UAV tracking. Drones 2023; 7(5): 296. DOI: 10.3390/drones7050296.
  13. Yu Q, Ma Y, He J, Yang D, Zhang T. A unified transformer-based tracker for anti-UAV tracking. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023: 3036-3046. DOI: 10.1109/CVPRW59228.2023.00305.
  14. Tong X, Zuo Z, Su S, Wei J, Sun X, Wu P, Zhao Z. ST-Trans: Spatial-temporal transformer for infrared small target detection in sequential images. IEEE Trans Geosci Remote Sens 2024; 62: 5001819. DOI: 10.1109/TGRS.2024.3355947.
  15. Yang Z, Lan X, Wang H. Comparative analysis of YOLO series algorithms for UAV-based highway distress inspection: performance and application insights. Sensors 2025; 25(5): 1475. DOI: 10.3390/s25051475.
  16. Elesawy A, Mohammed Abdelkader E, Osman H. A detailed comparative analysis of you only look once-based architectures for the detection of personal protective equipment on construction sites. Eng 2024; 5(1): 347-366. DOI: 10.3390/eng5010019.
  17. Suewongsuwan K, Angsuseranee N, Wongkamchang P, Phasinam K. Comparative analysis of UAV detection and tracking performance: Evaluating YOLOv5, YOLOv8, and YOLOv8 DeepSORT for enhancing anti-UAV systems. Edelweiss Appl Sci Tech 2024; 8(5): 708-726. DOI: 10.55214/25768484.v8i5.1737.
  18. Hakani R, Rawat A. Edge computing-driven real-time drone detection using YOLOv9 and NVIDIA Jetson Nano. Drones 2024; 8(11): 680. DOI: 10.3390/drones8110680.
  19. Dewangan V, Saxena A, Thakur R, Tripathi S. Application of image processing techniques for UAV detection using deep learning and distance-wise analysis. Drones 2023; 7(3): 174. DOI: 10.3390/drones7030174.
  20. Zhao J, Zhang J, Li D, Wang D. Vision-based anti-UAV detection and tracking. IEEE Trans Intell Transp Syst 2022; 23(12): 25323-25334. DOI: 10.1109/TITS.2022.3177627.
  21. Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL. Microsoft COCO: Common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T, eds. Computer Vision - ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V. Cham: Springer International Publishing Switzerland; 2014: 740-755. DOI: 10.1007/978-3-319-10602-1_48.
  22. Zoph B, Ghiasi G, Lin T-Y, Cui Y, Liu H, Cubuk ED, Le QV. Rethinking pre-training and self-training. NIPS'20: Proceedings of the 34th International Conference on Neural Information Processing Systems 2020: 3833-3845.
  23. Li Y, Zhang H, Zhang Y. Rethinking training from scratch for object detection. arXiv Preprint. 2021. Source: https://arxiv.org/abs/2106.03112. DOI: 10.48550/arXiv.2106.03112.
  24. Ultralytics. 2025. Source: https://github.com/ultralytics.

151, Molodogvardeyskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20