Dual-Stream Difference Modeling with Deep-Guided Multiscale Fusion for Mangrove Change Detection
Sensors · 08.03.2026 · 26 (5) · 1701
DOI: 10.3390/s26051701 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 08.03.2026. Verfasst von Xin Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, China. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Major Science and Technology Project, Guangxi Science and Technology, Major Project.
Abstract (Originalsprache)
Accurate mangrove change detection is important for coastal ecosystem monitoring but remains challenging due to tidal disturbances, unstable land–water boundaries, and multi-scale distribution variability. Tidal fluctuations introduce spectral variations that obscure real changes. As a result, existing deep learning methods face difficulties in distinguishing tide-induced pseudo-changes while balancing semantic consistency and boundary accuracy. To address these issues, we propose DSDGMNet, which incorporates Dual-Stream Difference Modeling and Deep-Guided Multiscale Fusion. The dual-stream difference-driven strategy is designed to reduce tidal interference and improve sensitivity to true structural changes, and the deep-guided multiscale fusion module integrates global context with fine boundary details. Experiments on the GBCNR dataset show that DSDGMNet achieves an F1-score of 71.36% compared to 68.87% by SNUNet (Siamese Densely Connected UNet) and 66.39% by ChangeFormer. On the WHU-CD dataset, DSDGMNet yields an F1-score of 91.38%, in comparison with 89.85% for DDLNet and 88.82% for ChangeFormer. These results suggest the method’s effectiveness for mangrove change detection in complex intertidal environments.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, China.
- School of Computer Engineering, Guilin University of Electronic Technology, Beihai 536000, China.
- School of Electronic Information, Guilin University of Electronic Technology, Beihai 536000, China.
ORCID-Profile: Qin Qin, Shunqi Yuan
Förderung
- Guangxi Major Science and Technology Project
- Guangxi Science and Technology, Major Project
Zitieren
APA
Wang, X., Tang, S., Qin, Q., Yuan, S., & Liang, X. (2026). Dual-Stream Difference Modeling with Deep-Guided Multiscale Fusion for Mangrove Change Detection. Sensors, 26(5), 1701. https://doi.org/10.3390/s26051701
Vancouver
Wang X, Tang S, Qin Q, Yuan S, Liang X. Dual-Stream Difference Modeling with Deep-Guided Multiscale Fusion for Mangrove Change Detection. Sensors. 2026;26(5):1701. doi:10.3390/s26051701
BibTeX
@article{Wang2026,
author = {Wang, Xin and Tang, Shuai and Qin, Qin and Yuan, Shunqi and Liang, Xiansheng},
title = {Dual-Stream Difference Modeling with Deep-Guided Multiscale Fusion for Mangrove Change Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {5},
pages = {1701},
doi = {10.3390/s26051701}
}
EUVIMED