Building Extraction Network with Gated Mamba-CNN and Wavelet-Based Boundary Enhancement
Remote Sensing · 01.06.2026 · 18 (11) · 1773
DOI: 10.3390/rs18111773 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 01.06.2026. Verfasst von Dongjie Yang und 7 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Tianjin Key Laboratory of Rail Transit Navigation Positioning and Spatio-temporal Big Data Technology, Open Project of National Key Laboratory for Waterway Traffic Control, Tibet Autonomous Region Science and Technology Major Project.
Abstract (Originalsprache)
Building extraction from high-resolution remote sensing imagery remains challenging due to spectral heterogeneity, complex background interference, and incomplete boundary delineation. Thus, we propose GWNet, which integrates gated Mamba-CNN modeling with wavelet-based boundary enhancement. Specifically, a Gated Mamba-CNN Module (GMC) is embedded into the medium- and low-resolution branches to jointly capture local texture features and long-range dependencies. In addition, a channel-wise gating mechanism is introduced to adaptively balance global contextual information and local structural details, thereby alleviating fragmented predictions and internal holes within the same building caused by variations in roof materials, while reducing the misclassification between buildings and background objects such as roads and bare land. Furthermore, a Wavelet Boundary Optimization Module (WBO) is designed to exploit multi-directional high-frequency components extracted by fixed Haar wavelet filters, thereby enhancing the representation of building boundaries and corners. This design effectively mitigates boundary blurring, incomplete contours, and missed detections caused by the loss of high-frequency edge information during downsampling. Extensive experiments on four public datasets, namely WHU, Massachusetts, WHU Satellite I, and Potsdam, demonstrate the effectiveness and robustness of GWNet across diverse spatial resolutions and scene complexities. Specifically, GWNet achieves IoU/BIoU scores of 90.68%/66.88% on the WHU dataset, 73.02%/93.19% on the Massachusetts dataset, 63.86%/83.77% on the WHU Satellite I dataset, and 83.21%/58.96% on the Potsdam dataset, consistently outperforming several competitive methods. Qualitative results further confirm that GWNet produces more complete building regions and sharper, more continuous boundaries. These findings validate the effectiveness of the proposed global–local feature extraction mechanism and wavelet-based boundary enhancement strategy.
Förderung
- Tianjin Key Laboratory of Rail Transit Navigation Positioning and Spatio-temporal Big Data Technology
- Open Project of National Key Laboratory for Waterway Traffic Control
- Tibet Autonomous Region Science and Technology Major Project
- Hubei Provincial Department of Education
- China National Science and Technology Major Project
- National Engineering Laboratory for Digital Construction and Evaluation Technology of Urban Rail Transit
- Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake, Ministry of Natural Resources
- Tianjin Science and Technology Plan Project
Zitieren
APA
Yang, D., Yang, Y., Gao, X., Huang, R., Gao, X., Han, K., Guo, K., & Tao, Y. (2026). Building Extraction Network with Gated Mamba-CNN and Wavelet-Based Boundary Enhancement. Remote Sensing, 18(11), 1773. https://doi.org/10.3390/rs18111773
Vancouver
Yang D, Yang Y, Gao X, Huang R, Gao X, Han K, et al. Building Extraction Network with Gated Mamba-CNN and Wavelet-Based Boundary Enhancement. Remote Sensing. 2026;18(11):1773. doi:10.3390/rs18111773
BibTeX
@article{Yang2026,
author = {Yang, Dongjie and Yang, Yuanwei and Gao, Xianjun and Huang, Rujing and Gao, Xinlong and Han, Kuikui and Guo, Kangliang and Tao, Yuan},
title = {Building Extraction Network with Gated Mamba-CNN and Wavelet-Based Boundary Enhancement},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {11},
pages = {1773},
doi = {10.3390/rs18111773}
}
EUVIMED