elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

A Lightweight Deep Learning-based Cloud Detection Method for Sentinel-2A Imagery Fusing Multiscale Spectral and Spatial Features

Li, Jun and Wu, Zhaocong and Hu, Zhongwen and Jian, Canliang and Luo, Shaojie and Zhu, Xiao Xiang and Mou, LiChao and Molinier, Matthieu (2022) A Lightweight Deep Learning-based Cloud Detection Method for Sentinel-2A Imagery Fusing Multiscale Spectral and Spatial Features. IEEE Transactions on Geoscience and Remote Sensing, 60, p. 5401219. IEEE - Institute of Electrical and Electronics Engineers. doi: 10.1109/TGRS.2021.3069641. ISSN 0196-2892.

Full text not available from this repository.

Official URL: https://ieeexplore.ieee.org/document/9397390

Abstract

Clouds are a very important factor in the availability of optical remote sensing images. Recently, deep learning (DL)-based cloud detection methods have surpassed classical methods based on rules and physical models of clouds. However, most of these deep models are very large, which limits their applicability and explainability, while other models do not make use of the full spectral information in multispectral images, such as Sentinel-2. In this article, we propose a lightweight network for cloud detection, fusing multiscale spectral and spatial features (CD-FM3SFs) and tailored for processing all spectral bands in Sentinel-2A images. The proposed method consists of an encoder and a decoder. In the encoder, three input branches are designed to handle spectral bands at their native resolution and extract multiscale spectral features. Three novel components are designed: a mixed depthwise separable convolution (MDSC) and a shared and dilated residual block (SDRB) to extract multiscale spatial features, and a concatenation and sum (CS) operation to fuse multiscale spectral and spatial features with little calculation and no additional parameters. The decoder of CD-FM3SF outputs three cloud masks at the same resolution as input bands to enhance the supervision information of small, middle, and large clouds. To validate the performance of the proposed method, we manually labeled 36 Sentinel-2A scenes evenly distributed over mainland China. The experiment results demonstrate that CD-FM3SF outperforms traditional cloud detection methods and state-of-the-art DL-based methods in both accuracy and speed.

Item URL in elib:https://elib.dlr.de/141573/
Document Type:Article
Title:A Lightweight Deep Learning-based Cloud Detection Method for Sentinel-2A Imagery Fusing Multiscale Spectral and Spatial Features
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Li, Junjun__li (at) whu.edu.cnUNSPECIFIED
Wu, Zhaocongzcwoo (at) whu.edu.cnUNSPECIFIED
Hu, Zhongwenzwhoo (at) szu.edu.cnUNSPECIFIED
Jian, Canliangjiancanliang (at) 163.netUNSPECIFIED
Luo, Shaojieshaojieluo (at) sina.comUNSPECIFIED
Zhu, Xiao Xiangxiao.zhu (at) dlr.deUNSPECIFIED
Mou, LiChaoLiChao.Mou (at) dlr.deUNSPECIFIED
Molinier, Matthieumatthieu.molinier (at) vtt.fiUNSPECIFIED
Date:2022
Journal or Publication Title:IEEE Transactions on Geoscience and Remote Sensing
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:60
DOI :10.1109/TGRS.2021.3069641
Page Range:p. 5401219
Publisher:IEEE - Institute of Electrical and Electronics Engineers
ISSN:0196-2892
Status:Published
Keywords:deep learning, cloud detection, Sentinel 2, multi-scale fusion
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Artificial Intelligence, R - Optical remote sensing
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Bratasanu, Ion-Dragos
Deposited On:26 Mar 2021 17:59
Last Modified:20 Dec 2021 17:39

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.