EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Robustness of YOLO models for object detection in remote sensing images

Touati Adli, Dimitrije M. Bujaković, Boban P. Bondžulić, Mohammed Zouaoui Laidouni, Milenko S. Andrić

Journal of Electrical Engineering · 01.10.2025 · 76 (5) · 429-442

DOI: 10.2478/jee-2025-0045 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Electrical Engineering, online erschienen am 16.10.2025. Verfasst von Touati Adli und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing imagery enables object detection systems to localize and classify targets for critical applications like surveillance and autonomous driving. However, distortions introduced during image acquisition, transmission, or compression degrade the detection performance, posing challenges for real-world applications. This study conducts a comprehensive robustness evaluation of seven state-of-the-art YOLO models, including YOLOv5, YOLOv7, YOLOv8, YOLOv9, YOLOv10, YOLOv11, and the modified YOLOv5 against four common distortions: Additive White Gaussian Noise (AWGN), JPEG and JPEG2000 compressions, and Gaussian blurring. Using the DOTA-v1.0 dataset, we generated 40 distortion test sets (10 levels per distortion type). The obtained results demonstrate that all distortions degrade performance across all evaluated models. YOLOv9 outperforms others YOLO models in terms of mean average precision under different distortions. YOLOv7 and YOLOv10 exhibit the weakest robustness, whereas YOLOv11 shows low resistance to AWGN distortion.

Zitieren

APA

Adli, T., Bujaković, D. M., Bondžulić, B. P., Laidouni, M. Z., & Andrić, M. S. (2025). Robustness of YOLO models for object detection in remote sensing images. Journal of Electrical Engineering, 76(5), 429-442. https://doi.org/10.2478/jee-2025-0045

Vancouver

Adli T, Bujaković DM, Bondžulić BP, Laidouni MZ, Andrić MS. Robustness of YOLO models for object detection in remote sensing images. Journal of Electrical Engineering. 2025;76(5):429-442. doi:10.2478/jee-2025-0045

BibTeX
@article{Adli2025,
  author = {Adli, Touati and Bujaković, Dimitrije M. and Bondžulić, Boban P. and Laidouni, Mohammed Zouaoui and Andrić, Milenko S.},
  title = {Robustness of YOLO models for object detection in remote sensing images},
  journal = {Journal of Electrical Engineering},
  year = {2025},
  volume = {76},
  number = {5},
  pages = {429--442},
  doi = {10.2478/jee-2025-0045}
}
Kostenlos starten →