EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unsupervised Progressive Domain Adaptation for Underwater Hyperspectral Target Detection Across Increasing Turbidity Levels

Yaru Zhu, Feng Yang, Kang Yue, Junli Nie, Wenxing Shi, Xiaomeng Li, Kaixuan Chang

Remote Sensing · 26.10.2026 · 18 (21) · 3676

DOI: 10.3390/rs18213676 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 26.10.2026. Verfasst von Yaru Zhu und 6 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting submerged objects becomes difficult when suspended particles alter spectral signatures and reduce target–background contrast. A detector trained in clear water can consequently lose discrimination and produce extensive background responses as turbidity increases. Here, we present a target-specific framework that couples progressive domain adaptation with object-level response calibration. A nonlinear unmixing autoencoder first learns the target representation from labeled clear-water observations. Cross-turbidity progressive domain adaptation (CTP-DA) then transfers model states, target prototypes, and prediction memory through ordered unlabeled domains. Risk-gated object-level background suppression (RG-OBS) subsequently limits background activation while protecting supported target regions. Across the L1–L5 target domains of the controlled brick-and-stone benchmark, the framework achieved an average precision of 0.9282. This exceeded the strongest external comparator evaluated here by 7.10 percentage points. Ablation experiments linked the ranking improvement to progressive adaptation and the reduction in background response to subsequent spatial calibration. Together, these findings support combining intermediate unlabeled domains with spatial target evidence to sustain underwater detection across controlled turbidity changes.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhu, Y., Yang, F., Yue, K., Nie, J., Shi, W., Li, X., & Chang, K. (2026). Unsupervised Progressive Domain Adaptation for Underwater Hyperspectral Target Detection Across Increasing Turbidity Levels. Remote Sensing, 18(21), 3676. https://doi.org/10.3390/rs18213676

Vancouver

Zhu Y, Yang F, Yue K, Nie J, Shi W, Li X, et al. Unsupervised Progressive Domain Adaptation for Underwater Hyperspectral Target Detection Across Increasing Turbidity Levels. Remote Sensing. 2026;18(21):3676. doi:10.3390/rs18213676

BibTeX
@article{Zhu2026,
  author = {Zhu, Yaru and Yang, Feng and Yue, Kang and Nie, Junli and Shi, Wenxing and Li, Xiaomeng and Chang, Kaixuan},
  title = {Unsupervised Progressive Domain Adaptation for Underwater Hyperspectral Target Detection Across Increasing Turbidity Levels},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {21},
  pages = {3676},
  doi = {10.3390/rs18213676}
}
Kostenlos starten →