Attentional Dense Convolutional Neural Network for Water Body Extraction From Sentinel-2 Images

被引:16
作者
Parajuli, Janak [1 ]
Fernandez-Beltran, Ruben [2 ]
Kang, Jian [3 ]
Pla, Filiberto [1 ]
机构
[1] Univ Jaume 1, Inst New Imaging Technol, Dept Comp Languages & Syst, E-12071 Castellon De La Plana, Spain
[2] Univ Murcia, Dept Comp Sci & Syst, Murcia 30100, Spain
[3] Soochow Univ, Sch Elect & Informat Engn, Dept Elect Sci & Technol, Suzhou 215006, Peoples R China
基金
中国国家自然科学基金;
关键词
Feature extraction; Water resources; Remote sensing; Earth; Indexes; Data mining; Water conservation; Convolutional neural networks (CNNs); dense networks; residual attention networks; Sentinel-2; water bodies; INDEX; NDWI;
D O I
10.1109/JSTARS.2022.3198497
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Monitoring water bodies from remote sensing data is certainly an essential task to supervise the actual conditions of the available water resources for environment conservation, sustainable development, and many other applications. Being Sentinel-2 images some of the most attractive data, existing traditional index-based and deep learning-based water extraction methods still have important limitations in effectively dealing with large heterogeneous areas since many types of water bodies with different spatial-spectral complexities are logically expected. Note that, in this scenario, optimal feature abstraction and neighborhood information may certainly vary from water to water pixel, however existing methods are generally constrained by a fix abstraction level and amount of land cover context. To address these issues, this article presents a new attentional dense convolutional neural network (AD-CNN) especially designed for water body extraction from Sentinel-2 imagery. On the one hand, the AD-CNN exploits dense connections to allow uncovering deeper features while simultaneously characterizing multiple data complexities. On the other hand, the proposed model also implements a new residual attention module to dynamically put the focus on the most relevant spatial-spectral features for classifying water pixels. To test the performance of the AD-CNN, a new water database of Nepal (WaterPAL) is also built. The conducted experiments reveal the competitive performance of the proposed architecture with respect to several traditional index-based and state-of-the-art deep learning-based water extraction models.
引用
收藏
页码:6804 / 6816
页数:13
相关论文
共 55 条
[1]   Application of Water Indices in Surface Water Change Detection Using Landsat Imagery in Nepal [J].
Acharya, Tri Dev ;
Subedi, Anoj ;
Huang, He ;
Lee, Dong Ha .
SENSORS AND MATERIALS, 2019, 31 (05) :1429-1447
[2]   Evaluation of Water Indices for Surface Water Extraction in a Landsat 8 Scene of Nepal [J].
Acharya, Tri Dev ;
Subedi, Anoj ;
Lee, Dong Ha .
SENSORS, 2018, 18 (08)
[3]   NDVI as an indicator for changes in water availability to woody vegetation [J].
Aguilar, Cristina ;
Zinnert, Julie C. ;
Jose Polo, Maria ;
Young, Donald R. .
ECOLOGICAL INDICATORS, 2012, 23 :290-300
[4]   A Review of In-Situ and Remote Sensing Technologies to Monitor Water and Sanitation Interventions [J].
Andres, Luis ;
Boateng, Kwasi ;
Borja-Vega, Christian ;
Thomas, Evan .
WATER, 2018, 10 (06)
[5]  
[Anonymous], 2010, DHS PROGRAM
[6]  
[Anonymous], 2007, NEPAL BIODIVERSITY R
[7]   Who launched what, when and why; trends in global land-cover observation capacity from civilian earth observation satellites [J].
Belward, Alan S. ;
Skoien, Jon O. .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2015, 103 :115-128
[8]   Extraction of Urban Water Bodies from High-Resolution Remote-Sensing Imagery Using Deep Learning [J].
Chen, Yang ;
Fan, Rongshuang ;
Yang, Xiucheng ;
Wang, Jingxue ;
Latif, Aamir .
WATER, 2018, 10 (05)
[9]   Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services [J].
Drusch, M. ;
Del Bello, U. ;
Carlier, S. ;
Colin, O. ;
Fernandez, V. ;
Gascon, F. ;
Hoersch, B. ;
Isola, C. ;
Laberinti, P. ;
Martimort, P. ;
Meygret, A. ;
Spoto, F. ;
Sy, O. ;
Marchese, F. ;
Bargellini, P. .
REMOTE SENSING OF ENVIRONMENT, 2012, 120 :25-36
[10]   Water Bodies' Mapping from Sentinel-2 Imagery with Modified Normalized Difference Water Index at 10-m Spatial Resolution Produced by Sharpening the SWIR Band [J].
Du, Yun ;
Zhang, Yihang ;
Ling, Feng ;
Wang, Qunming ;
Li, Wenbo ;
Li, Xiaodong .
REMOTE SENSING, 2016, 8 (04)