Comparative analysis of neural network models for detecting unmanned aerial vehicles
Computer Optics · 01.04.2026
DOI: 10.18287/coj1728 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Optics, online erschienen am 01.04.2026. Verfasst von S.V. Vychegzhanin und 2 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Vychegzhanin, S., Tatarinova, A., & Myshkin, R. (2026). Comparative analysis of neural network models for detecting unmanned aerial vehicles. Computer Optics. https://doi.org/10.18287/coj1728
Vancouver
Vychegzhanin S, Tatarinova A, Myshkin R. Comparative analysis of neural network models for detecting unmanned aerial vehicles. Computer Optics. 2026. doi:10.18287/coj1728
BibTeX
@article{Vychegzhanin2026,
author = {Vychegzhanin, S.V. and Tatarinova, A.G. and Myshkin, R.E.},
title = {Comparative analysis of neural network models for detecting unmanned aerial vehicles},
journal = {Computer Optics},
year = {2026},
doi = {10.18287/coj1728}
}
EUVIMED