Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images
Water-body surveying and mapping is of great significance for water resources utilization, flood monitoring, and environmental protection. However, due to distribution diversities, shape and size variations, and complex scenarios of water-bodies, it is still challengeable to accurately and efficient...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-12-01
|
Series: | International Journal of Applied Earth Observations and Geoinformation |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S0303243421002063 |
_version_ | 1811317567217729536 |
---|---|
author | Jian Kang Haiyan Guan Daifeng Peng Ziyi Chen |
author_facet | Jian Kang Haiyan Guan Daifeng Peng Ziyi Chen |
author_sort | Jian Kang |
collection | DOAJ |
description | Water-body surveying and mapping is of great significance for water resources utilization, flood monitoring, and environmental protection. However, due to distribution diversities, shape and size variations, and complex scenarios of water-bodies, it is still challengeable to accurately and efficiently extract water-bodies from high-resolution remotely sensed images. In this paper, we propose a multi-scale context extractor network, termed as MSCENet, for delineating water-bodies from high-resolution optical remotely sensed images. The MSCENet mainly contains three key parts: a multi-scale feature encoder, a feature decoder, and a context feature extractor module. To address shape and size variations of water-bodies, the Res2Net is used in the feature encoder to extract rich multi-scale information of water-bodies. The context extractor module is composed of an assorted dilated convolution unit and a complex multi-kernel pooling unit, which further extracts multi-scale contextual information to generate high-level feature maps. The robustness and effectiveness of our MSCENet have been evaluated on two public datasets: LandCover.ai Data Set and DeepGlobe Data Set. Comparative experiments indicate the superiority and applicability of the MSCENet in water-body extraction. |
first_indexed | 2024-04-13T12:10:32Z |
format | Article |
id | doaj.art-52af17d305c04f65ad7c377db9d8b70a |
institution | Directory Open Access Journal |
issn | 1569-8432 |
language | English |
last_indexed | 2024-04-13T12:10:32Z |
publishDate | 2021-12-01 |
publisher | Elsevier |
record_format | Article |
series | International Journal of Applied Earth Observations and Geoinformation |
spelling | doaj.art-52af17d305c04f65ad7c377db9d8b70a2022-12-22T02:47:29ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322021-12-01103102499Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed imagesJian Kang0Haiyan Guan1Daifeng Peng2Ziyi Chen3School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China; Corresponding author.School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaDepartment of Computer Science and Technology, Fujian Key Laboratory of Big Data Intelligence and Security, Xiamen Key Laboratory of Computer Vision and Pattern Recognition, Huaqiao University, ChinaWater-body surveying and mapping is of great significance for water resources utilization, flood monitoring, and environmental protection. However, due to distribution diversities, shape and size variations, and complex scenarios of water-bodies, it is still challengeable to accurately and efficiently extract water-bodies from high-resolution remotely sensed images. In this paper, we propose a multi-scale context extractor network, termed as MSCENet, for delineating water-bodies from high-resolution optical remotely sensed images. The MSCENet mainly contains three key parts: a multi-scale feature encoder, a feature decoder, and a context feature extractor module. To address shape and size variations of water-bodies, the Res2Net is used in the feature encoder to extract rich multi-scale information of water-bodies. The context extractor module is composed of an assorted dilated convolution unit and a complex multi-kernel pooling unit, which further extracts multi-scale contextual information to generate high-level feature maps. The robustness and effectiveness of our MSCENet have been evaluated on two public datasets: LandCover.ai Data Set and DeepGlobe Data Set. Comparative experiments indicate the superiority and applicability of the MSCENet in water-body extraction.http://www.sciencedirect.com/science/article/pii/S0303243421002063Water-bodyMulti-scale featureContext extractorDilated convolutionMulti-kernel poolingRemote sensing imagery |
spellingShingle | Jian Kang Haiyan Guan Daifeng Peng Ziyi Chen Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images International Journal of Applied Earth Observations and Geoinformation Water-body Multi-scale feature Context extractor Dilated convolution Multi-kernel pooling Remote sensing imagery |
title | Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images |
title_full | Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images |
title_fullStr | Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images |
title_full_unstemmed | Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images |
title_short | Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images |
title_sort | multi scale context extractor network for water body extraction from high resolution optical remotely sensed images |
topic | Water-body Multi-scale feature Context extractor Dilated convolution Multi-kernel pooling Remote sensing imagery |
url | http://www.sciencedirect.com/science/article/pii/S0303243421002063 |
work_keys_str_mv | AT jiankang multiscalecontextextractornetworkforwaterbodyextractionfromhighresolutionopticalremotelysensedimages AT haiyanguan multiscalecontextextractornetworkforwaterbodyextractionfromhighresolutionopticalremotelysensedimages AT daifengpeng multiscalecontextextractornetworkforwaterbodyextractionfromhighresolutionopticalremotelysensedimages AT ziyichen multiscalecontextextractornetworkforwaterbodyextractionfromhighresolutionopticalremotelysensedimages |