EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Robust Method for Tiny-Target Detection in Deep-Space Images by Integrating Physical Laws with Deep Learning

Tuo Xu, Yuefan Du, Xi Yang, Lei Shi, Liying Yang, Zhaoyan Mou

Remote Sensing · 19.11.2026 · 18 (22) · 3983

DOI: 10.3390/rs18223983 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.11.2026. Verfasst von Tuo Xu und 5 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Shaanxi, Shaanxi Province Fundsfor Distinguished Young Youths.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a Noise-Decoupled Multi-scale Evidence-aware (NDME) algorithm to address the critical challenges of feature sparsity and noise interference in detecting tiny targets (occupying 2). Compared with state-of-the-art methods such as YOLOX series and ALCNet, NDME demonstrates significant advantages in small-target detection on the IST-S and IRDST datasets, exhibiting robust adaptability under complex noise environments. Experimental results show that NDME outperforms existing methods in recall, precision, and other key metrics, providing an effective solution for tiny-target detection under deep-space-like sparse-feature and noise conditions, while validation on real deep-space observations remains future work. It should be noted that the public benchmarks used in this work are deep-space-like infrared proxy datasets; they are used to evaluate the sparse-feature and noise-robustness aspects of the method rather than to claim direct deep-space validation.

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Program of Shaanxi
  • Shaanxi Province Fundsfor Distinguished Young Youths
  • Postdoctoral Fellowship Program (Grade C) of China Postdoctoral Science Foundation
  • Shaanxi Provincial Natural Science Basic Research Program
  • China Postdoctoral Science Foundation

Zitieren

APA

Xu, T., Du, Y., Yang, X., Shi, L., Yang, L., & Mou, Z. (2026). A Robust Method for Tiny-Target Detection in Deep-Space Images by Integrating Physical Laws with Deep Learning. Remote Sensing, 18(22), 3983. https://doi.org/10.3390/rs18223983

Vancouver

Xu T, Du Y, Yang X, Shi L, Yang L, Mou Z. A Robust Method for Tiny-Target Detection in Deep-Space Images by Integrating Physical Laws with Deep Learning. Remote Sensing. 2026;18(22):3983. doi:10.3390/rs18223983

BibTeX
@article{Xu2026,
  author = {Xu, Tuo and Du, Yuefan and Yang, Xi and Shi, Lei and Yang, Liying and Mou, Zhaoyan},
  title = {A Robust Method for Tiny-Target Detection in Deep-Space Images by Integrating Physical Laws with Deep Learning},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {22},
  pages = {3983},
  doi = {10.3390/rs18223983}
}
Kostenlos starten →