CDWMamba: Cloud Detection with Wavelet-Enhanced Mamba for Optical Satellite Imagery
Remote Sensing · 28.05.2025 · 17 (11) · 1874
DOI: 10.3390/rs17111874 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 28.05.2025. Verfasst von Shiyao Meng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Youth Project from the Hubei Research Center for Basic Disciplines of Earth Sciences, Key Laboratory of Smart Earth.
Abstract (Originalsprache)
Accurate cloud detection is a critical preprocessing step in remote sensing applications, as cloud and cloud shadow contamination can significantly degrade the quality of optical satellite imagery. In this paper, we propose CDWMamba, a novel dual-domain neural network that integrates the Mamba-based state space model with discrete wavelet transform (DWT) for effective cloud detection. CDWMamba adopts a four-direction Mamba module to capture long-range dependencies, while the wavelet decomposition enables multi-scale global context modeling in the frequency domain. To further enhance fine-grained spatial features, we incorporate a multi-scale depth-wise separable convolution (MDC) module for spatial detail refinement. Additionally, a spectral–spatial bottleneck (SSN) with channel-wise attention is introduced to promote inter-band information interaction across multi-spectral inputs. We evaluate our method on two benchmark datasets, L8 Biome and S2_CMC, covering diverse land cover types and environmental conditions. Experimental results demonstrate that CDWMamba achieves state-of-the-art performance across multiple metrics, significantly outperforming deep-learning-based baselines in terms of overall accuracy, mIoU, precision, and recall. Moreover, the model exhibits satisfactory performance under challenging conditions such as snow/ice and shrubland surfaces. These results verify the effectiveness of combining a state space model, frequency-domain representation, and spectral–spatial attention for cloud detection in multi-spectral remote sensing imagery.
Förderung
- National Natural Science Foundation of China
- Youth Project from the Hubei Research Center for Basic Disciplines of Earth Sciences
- Key Laboratory of Smart Earth
Zitieren
APA
Meng, S., Gong, W., Li, S., Song, G., Yang, J., & Ding, Y. (2025). CDWMamba: Cloud Detection with Wavelet-Enhanced Mamba for Optical Satellite Imagery. Remote Sensing, 17(11), 1874. https://doi.org/10.3390/rs17111874
Vancouver
Meng S, Gong W, Li S, Song G, Yang J, Ding Y. CDWMamba: Cloud Detection with Wavelet-Enhanced Mamba for Optical Satellite Imagery. Remote Sensing. 2025;17(11):1874. doi:10.3390/rs17111874
BibTeX
@article{Meng2025,
author = {Meng, Shiyao and Gong, Wei and Li, Siwei and Song, Ge and Yang, Jie and Ding, Yu},
title = {CDWMamba: Cloud Detection with Wavelet-Enhanced Mamba for Optical Satellite Imagery},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {11},
pages = {1874},
doi = {10.3390/rs17111874}
}
EUVIMED