EUVIMEDEUVIMED entdecken
Crossref

MNHU-Net: A Multiscale Feature Fusion and Nested Structure-Based High-Order U-Net for Infrared Small Target Detection

Xiaoyang Yuan, Chunling Yang, Yu Chen, Yan Zhang

IEEE Transactions on Aerospace and Electronic Systems · 2025-08 · 61 (4) · 10679-10693

DOI: 10.1109/taes.2025.3564932 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2025-08. Verfasst von Xiaoyang Yuan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared small target detection (IRSTD) methods have been extensively investigated within the infrared search and tracking applications. U-shaped networks and their improved versions have significantly enhanced IRSTD segmentation performance in recent years. However, existing methods overlook the feature dilution and insufficient representation of long-range dependencies in feature maps, hindering the accurate segmentation of small targets obscured by background clutter. To handle this problem, we designed a multiscale feature fusion and nested structure-based high-order UNet (MNHU). Our approach utilizes a high-order UNet paradigm that progressively calibrates infrared feature maps, and integrates hierarchical features to enhance both small target and background texture extraction performance. High-order U-Net selectively integrates feature maps from highly correlated adjacent nodes. Subsequently, these encoding or decoding feature maps are progressively merged into a high-order fusion feature map, ensuring sufficient feature extraction and precise feature representation. We evaluate the proposed high-order UNet-based methods (MNHU-E, MNHU-D, and MNHU) on three public datasets. The results underscore our method's superior performance in target enhancement and texture awareness, outperforming state-of-the-art techniques in intersection over union, Dice similarity coefficient, precision, and sensitivity. MNHU exhibits robust segmentation capabilities and generalization, effectively achieving a balance between model complexity and performance, which highlights its suitability for practical applications.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yuan, X., Yang, C., Chen, Y., & Zhang, Y. (2025). MNHU-Net: A Multiscale Feature Fusion and Nested Structure-Based High-Order U-Net for Infrared Small Target Detection. IEEE Transactions on Aerospace and Electronic Systems, 61(4), 10679-10693. https://doi.org/10.1109/taes.2025.3564932

Vancouver

Yuan X, Yang C, Chen Y, Zhang Y. MNHU-Net: A Multiscale Feature Fusion and Nested Structure-Based High-Order U-Net for Infrared Small Target Detection. IEEE Transactions on Aerospace and Electronic Systems. 2025;61(4):10679-10693. doi:10.1109/taes.2025.3564932

BibTeX
@article{Yuan2025,
  author = {Yuan, Xiaoyang and Yang, Chunling and Chen, Yu and Zhang, Yan},
  title = {MNHU-Net: A Multiscale Feature Fusion and Nested Structure-Based High-Order U-Net for Infrared Small Target Detection},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2025},
  volume = {61},
  number = {4},
  pages = {10679--10693},
  doi = {10.1109/taes.2025.3564932}
}
Kostenlos starten →