EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Resource-Efficient Framework for Degraded Underwater Image Object Detection

Yi Zhou, Jingchun Zhou, Zhiyu Su, Dehuan Zhang, Dezhen Zhang, Siyuan Liu

Journal of Marine Science and Engineering · 27.07.2026 · 14 (15) · 1375

DOI: 10.3390/jmse14151375 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 27.07.2026. Verfasst von Yi Zhou und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Open Project of the State Key Laboratory of Ocean Sensing, Liaoning Provincial Science and Technology Plan Joint Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater object detection is crucial for marine ecological monitoring and resource exploration. However, low underwater contrast causes severe aliasing between foreground and background in the spatial domain, and conventional methods struggle to effectively decouple their features. Transformer architectures incur high computational overhead. Conversely, over-compressing these models severely degrades their ability to detect heavily camouflaged or small marine organisms. High-quality underwater samples are limited, and existing time-consuming generative strategies are hard to implement efficiently on edge devices. To address these challenges, this paper proposes a resource-efficient framework for underwater object detection. First, we design a Wavelet-Enhanced Feature Pyramid Network that combines a saliency-focus mechanism and a discrete wavelet transform to overcome background noise in both spatial and frequency domains, extracting features of hidden small objects. Second, a data-dependent dynamic token pruning technique removes redundant tokens, effectively mitigating the computational bottleneck without sacrificing essential semantic capacity. Finally, for extreme sample scarcity, we introduce a Feature Correction Module and a two-stage fine-tuning and feature correction strategy, using a high-precision teacher model to guide a compressed student network in adaptively compensating for optical shifts with few samples. Experiments on URPC2020 and DUO demonstrate that our method improves small object detection accuracy while reducing parameter count and computational overhead, striking a good balance between accuracy and inference efficiency.

Förderung

  • National Natural Science Foundation of China
  • Open Project of the State Key Laboratory of Ocean Sensing
  • Liaoning Provincial Science and Technology Plan Joint Program
  • Fundamental Research Funds for the Central Universities
  • Fundamental Research Funds of the Liaoning Provincial Department of Education

Zitieren

APA

Zhou, Y., Zhou, J., Su, Z., Zhang, D., Zhang, D., & Liu, S. (2026). A Resource-Efficient Framework for Degraded Underwater Image Object Detection. Journal of Marine Science and Engineering, 14(15), 1375. https://doi.org/10.3390/jmse14151375

Vancouver

Zhou Y, Zhou J, Su Z, Zhang D, Zhang D, Liu S. A Resource-Efficient Framework for Degraded Underwater Image Object Detection. Journal of Marine Science and Engineering. 2026;14(15):1375. doi:10.3390/jmse14151375

BibTeX
@article{Zhou2026,
  author = {Zhou, Yi and Zhou, Jingchun and Su, Zhiyu and Zhang, Dehuan and Zhang, Dezhen and Liu, Siyuan},
  title = {A Resource-Efficient Framework for Degraded Underwater Image Object Detection},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {15},
  pages = {1375},
  doi = {10.3390/jmse14151375}
}
Kostenlos starten →