Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images

• Published in: International journal of applied earth observation and geoinformation Vol. 103; p. 102499
• Main Authors: Kang, Jian, Guan, Haiyan, Peng, Daifeng, Chen, Ziyi
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2021; Elsevier
• Subjects: Context extractor; data collection; Dilated convolution; environmental protection; Multi-kernel pooling; Multi-scale feature; remote sensing; Remote sensing imagery; spatial data; Water-body; Dilated convolution; Water-body; Context extractor; Multi-kernel pooling; Remote sensing imagery; Multi-scale feature

•A state-of-the-art MSCENet was applied to extract water-body.•The Res2Net was used to extract rich multi-scale water-body features.•A novel CEM was designed to preserve multi-scale contextual information.•The sufficient ablation study and comparative experiments were implemented.•The robustness and...