PSHNet: Hybrid Supervision and Feature Enhancement for Accurate Infrared Small-Target Detection
Applied Sciences · 08.07.2025 · 15 (14) · 7629
DOI: 10.3390/app15147629 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 08.07.2025. Verfasst von Weicong Chen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Detecting small targets in infrared imagery remains highly challenging due to sub-pixel target sizes, low signal-to-noise ratios, and complex background clutter. This paper proposes PSHNet, a hybrid deep-learning framework that combines dense spatial heatmap supervision with geometry-aware regression for accurate infrared small-target detection. The network generates position–scale heatmaps to guide coarse localization, which are further refined through sub-pixel offset and size regression. A Complete IoU (CIoU) loss is introduced as a geometric regularization term to improve alignment between predicted and ground-truth bounding boxes. To better preserve fine spatial details essential for identifying small thermal signatures, an Enhanced Low-level Feature Module (ELFM) is incorporated using multi-scale dilated convolutions and channel attention. Experiments on the NUDT-SIRST and IRSTD-1k datasets demonstrate that PSHNet outperforms existing methods in IoU, detection probability, and false alarm rate, achieving IoU improvement and robust performance under low-SNR conditions.
Zitieren
APA
Chen, W., Zhang, C., & Liu, Y. (2025). PSHNet: Hybrid Supervision and Feature Enhancement for Accurate Infrared Small-Target Detection. Applied Sciences, 15(14), 7629. https://doi.org/10.3390/app15147629
Vancouver
Chen W, Zhang C, Liu Y. PSHNet: Hybrid Supervision and Feature Enhancement for Accurate Infrared Small-Target Detection. Applied Sciences. 2025;15(14):7629. doi:10.3390/app15147629
BibTeX
@article{Chen2025,
author = {Chen, Weicong and Zhang, Chenghong and Liu, Yuan},
title = {PSHNet: Hybrid Supervision and Feature Enhancement for Accurate Infrared Small-Target Detection},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {14},
pages = {7629},
doi = {10.3390/app15147629}
}
EUVIMED