Fang_Deep-Learning-Based_Multispectral_Satellite_Image_Segmentation_for_Water_Body_Detection.pdf (7.7 MB)
Deep learning-based multi-spectral satellite image segmentation for water body detection
journal contribution
posted on 2021-09-24, 12:53 authored by Kunhao Yuan, Xu Zhuang, Gerald SchaeferGerald Schaefer, Jianxin Feng, Lin GuanLin Guan, Hui FangHui FangAutomated water body detection from satellite imagery is a fundamental stage for urban hydrological studies.
In recent years, various deep convolutional neural network
(DCNN)-based methods have been proposed to segment remote
sensing data collected by conventional RGB or multi-spectral
imagery for such studies. However, how to effectively explore
the wider spectrum bands of multi-spectral sensors to achieve
significantly better performance compared to the use of only RGB
bands has been left underexplored. In this paper, we propose a
novel deep convolutional neural network model – Multi-Channel
Water Body Detection Network (MC-WBDN) – that incorporates
three innovative components, a multi-channel fusion module,
an Enhanced Atrous Spatial Pyramid Pooling (EASPP) module,
and Space-to-Depth (S2D)/Depth-to-Space (D2S) operations, to
outperform state-of-the-art DCNN-based water body detection
methods. Experimental results convincingly show that our MCWBDN model achieves remarkable water body detection performance, is more robust to light and weather variations and can
better distinguish tiny water bodies compared to other DCNN
models.
Funding
Government of Chengdu City
History
School
- Science
Department
- Computer Science
Published in
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingVolume
14Pages
7422-7434Publisher
Institute of Electrical and Electronics EngineersVersion
- VoR (Version of Record)
Publisher statement
This is an Open Access Article. It is published by IEEE under the Creative Commons Attribution 4.0 Unported Licence (CC BY). Full details of this licence are available at: http://creativecommons.org/licenses/by/4.0/Acceptance date
2021-07-17Publication date
2021-07-21Copyright date
2021ISSN
1939-1404eISSN
2151-1535Publisher version
Language
- en