ESPFNet: An Edge-Aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing Images
Shadows can hinder image interpretation in aerial remote sensing images. The existing shadow detection methods focus on all shadow regions and detect the shadow regions directly, but they ignore the fact that salient shadows have a more significant effect. In this work, a novel edge-aware spatial py...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9380896/ |
id |
doaj-6746f1ab0369444b86f672841f11a10d |
---|---|
record_format |
Article |
spelling |
doaj-6746f1ab0369444b86f672841f11a10d2021-06-03T23:08:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01144633464610.1109/JSTARS.2021.30667919380896ESPFNet: An Edge-Aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing ImagesShuang Luo0Huifang Li1https://orcid.org/0000-0003-4626-7416Ruzhao Zhu2Yuting Gong3Huanfeng Shen4https://orcid.org/0000-0002-4140-1869School of Resource and Environmental Sciences, Wuhan University, Wuhan, ChinaSchool of Resource and Environmental Sciences, Wuhan University, Wuhan, ChinaKylinSoft Company, Ltd., Changsha, ChinaSchool of Resource and Environmental Sciences, Wuhan University, Wuhan, ChinaSchool of Resource and Environmental Sciences and the Collaborative Innovation Center of Geospatial Technology, Wuhan University, Wuhan, ChinaShadows can hinder image interpretation in aerial remote sensing images. The existing shadow detection methods focus on all shadow regions and detect the shadow regions directly, but they ignore the fact that salient shadows have a more significant effect. In this work, a novel edge-aware spatial pyramid fusion network (ESPFNet) under a multitask learning framework is proposed for salient shadow detection in aerial remote sensing images. ESPFNet has three components: a parallel spatial pyramid (PSP) structure; an edge detection module (EDM); and an edge-aware multibranch integration (EMI). The PSP structure is constructed to extract multiscale features from the input image and fuse them gradually. The EDM then integrates the shallow features and deep features to detect the shadow edges. Finally, the EMI incorporates the edge features with multibranch features, and then concatenates them with the shallow features to generate the salient shadow detection result. The experimental analyses confirm the effectiveness of the ESPFNet method in both the qualitative and quantitative performance, compared to the existing methods, with the F-score reaching 92.04% in the salient shadow test set.https://ieeexplore.ieee.org/document/9380896/Aerial remote sensing imagesconvolutional neural networkmultitask learningsalient shadow detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shuang Luo Huifang Li Ruzhao Zhu Yuting Gong Huanfeng Shen |
spellingShingle |
Shuang Luo Huifang Li Ruzhao Zhu Yuting Gong Huanfeng Shen ESPFNet: An Edge-Aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Aerial remote sensing images convolutional neural network multitask learning salient shadow detection |
author_facet |
Shuang Luo Huifang Li Ruzhao Zhu Yuting Gong Huanfeng Shen |
author_sort |
Shuang Luo |
title |
ESPFNet: An Edge-Aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing Images |
title_short |
ESPFNet: An Edge-Aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing Images |
title_full |
ESPFNet: An Edge-Aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing Images |
title_fullStr |
ESPFNet: An Edge-Aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing Images |
title_full_unstemmed |
ESPFNet: An Edge-Aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing Images |
title_sort |
espfnet: an edge-aware spatial pyramid fusion network for salient shadow detection in aerial remote sensing images |
publisher |
IEEE |
series |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
issn |
2151-1535 |
publishDate |
2021-01-01 |
description |
Shadows can hinder image interpretation in aerial remote sensing images. The existing shadow detection methods focus on all shadow regions and detect the shadow regions directly, but they ignore the fact that salient shadows have a more significant effect. In this work, a novel edge-aware spatial pyramid fusion network (ESPFNet) under a multitask learning framework is proposed for salient shadow detection in aerial remote sensing images. ESPFNet has three components: a parallel spatial pyramid (PSP) structure; an edge detection module (EDM); and an edge-aware multibranch integration (EMI). The PSP structure is constructed to extract multiscale features from the input image and fuse them gradually. The EDM then integrates the shallow features and deep features to detect the shadow edges. Finally, the EMI incorporates the edge features with multibranch features, and then concatenates them with the shallow features to generate the salient shadow detection result. The experimental analyses confirm the effectiveness of the ESPFNet method in both the qualitative and quantitative performance, compared to the existing methods, with the F-score reaching 92.04% in the salient shadow test set. |
topic |
Aerial remote sensing images convolutional neural network multitask learning salient shadow detection |
url |
https://ieeexplore.ieee.org/document/9380896/ |
work_keys_str_mv |
AT shuangluo espfnetanedgeawarespatialpyramidfusionnetworkforsalientshadowdetectioninaerialremotesensingimages AT huifangli espfnetanedgeawarespatialpyramidfusionnetworkforsalientshadowdetectioninaerialremotesensingimages AT ruzhaozhu espfnetanedgeawarespatialpyramidfusionnetworkforsalientshadowdetectioninaerialremotesensingimages AT yutinggong espfnetanedgeawarespatialpyramidfusionnetworkforsalientshadowdetectioninaerialremotesensingimages AT huanfengshen espfnetanedgeawarespatialpyramidfusionnetworkforsalientshadowdetectioninaerialremotesensingimages |
_version_ |
1721398565432983552 |