RFA-LinkNet: a novel deep learning network for water body extraction from high-resolution remote sensing images

The Convolutional Neural Network (CNN) has unsatisfactory performance in water body extinction from high-resolution optical remote sensing images with complex background, which is low in accuracy, unable to capture multi-scale features, and complex in model structure. Here, we propose an RFA-Link Ne...

Full description

Saved in:
Bibliographic Details
Published inNanjing Xinxi Gongcheng Daxue Xuebao Vol. 15; no. 2; pp. 160 - 168
Main Authors Kang, Jian, Guan, Haiyan, Yu, Yongao, Jing, Zhuangwei, Liu, Chao, Gao, Junyong
Format Journal Article
LanguageChinese
Published Nanjing Nanjing University of Information Science & Technology 01.04.2023
Subjects
Artificial neural networks
Feature maps
High resolution
Image resolution
Machine learning
Neural networks
Remote sensing
Semantics
Water bodies
Online AccessGet full text

Cover

More Information
Summary:The Convolutional Neural Network (CNN) has unsatisfactory performance in water body extinction from high-resolution optical remote sensing images with complex background, which is low in accuracy, unable to capture multi-scale features, and complex in model structure. Here, we propose an RFA-Link Net (Receptive Field Attention Link Net) approach combining Receptive Field Block (RFB) and Channel Attention Block (CAB), from which the high-level water body semantic information and multi-scale feature map can be obtained by RFB, then the CAB is used to realize the weighed fusion of encoding and decoding features, to suppress background features as well as enhance water body semantics. Compared with state-of-the-art CNN models, the proposed RFA-Link Net can extract water body information from high-resolution optical remote sensing images more efficiently and robustly with high precision.
ISSN:1674-7070
DOI:10.13878/j.cnki.jnuist.2023.02.004