Depth-guided selective cross-modal fusion network for deep-sea polymetallic nodule segmentation
Measurement Science and Technology · 13.11.2026 · 37 (45) · 455403
DOI: 10.1088/1361-6501/aebaad ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 10.11.2026. Verfasst von Heqing Qin und 4 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Accurate segmentation of deep-sea polymetallic nodules is essential for deep-sea mineral resource measurement and assessment. However, existing methods predominantly rely on RGB images, and their performance is often compromised by complex seabed backgrounds, substantial scale variations, and blurred boundaries. To address these challenges, we propose a depth-guided selective cross-modal fusion network (DSCFNet), which uses monocularly estimated depth as a structural prior to complement RGB appearance information. First, a Frequency-Enhanced Modality Interaction module is developed to enhance cross-modal feature representation and suppress redundant responses in complex backgrounds. Second, a Semantic-Boundary Gated Injection module is designed to selectively incorporate reliable complementary cues while reducing interference from depth noise. Finally, a Multi-Scale Depth Feature Refinement module is constructed to strengthen the representation of nodules with substantial scale variations. Experimental results on a self-constructed multimodal deep-sea polymetallic nodule dataset demonstrate that the proposed DSCFNet outperforms representative semantic segmentation methods, achieving an mean intersection over union of 92.73% and an F 1-score of 94.49%. The proposed method improves segmentation accuracy in complex seabed environments, providing a reliable solution for image-based measurement and assessment of deep-sea polymetallic nodule resources.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Qin, H., Liang, J., Cui, X., Si, J., & Shu, Y. (2026). Depth-guided selective cross-modal fusion network for deep-sea polymetallic nodule segmentation. Measurement Science and Technology, 37(45), 455403. https://doi.org/10.1088/1361-6501/aebaad
Vancouver
Qin H, Liang J, Cui X, Si J, Shu Y. Depth-guided selective cross-modal fusion network for deep-sea polymetallic nodule segmentation. Measurement Science and Technology. 2026;37(45):455403. doi:10.1088/1361-6501/aebaad
BibTeX
@article{Qin2026,
author = {Qin, Heqing and Liang, Jianfeng and Cui, Xuerong and Si, Jia and Shu, Yuting},
title = {Depth-guided selective cross-modal fusion network for deep-sea polymetallic nodule segmentation},
journal = {Measurement Science and Technology},
year = {2026},
volume = {37},
number = {45},
pages = {455403},
doi = {10.1088/1361-6501/aebaad}
}
EUVIMED