R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images
In the detection of building changes in high spatial-resolution remote sensing images, both the distribution position and surface characteristics of the same objects are probably different under different imaging phases, which potentially causes high false positives. In order to improve the detectio...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10366788/ |
_version_ | 1797357970441371648 |
---|---|
author | Zhong Chen Tong Zheng Junsong Leng Jiahao Zhang He Deng Xiaofei Mi Jian Yang |
author_facet | Zhong Chen Tong Zheng Junsong Leng Jiahao Zhang He Deng Xiaofei Mi Jian Yang |
author_sort | Zhong Chen |
collection | DOAJ |
description | In the detection of building changes in high spatial-resolution remote sensing images, both the distribution position and surface characteristics of the same objects are probably different under different imaging phases, which potentially causes high false positives. In order to improve the detection accuracy of building changes, an integration network, named R&D net is proposed in this article, which comprises a registration network (R-net) followed by a change detection network (D-net). In R-net, two different phase images are accepted as inputs, corner points and their descriptors are generated to spatially align those images. After that, the spatially aligned images are fed into the D-net, and building images are detected accordingly. In this article, a multiview automatic labeling method is proposed to obtain labeling corner points. A new dataset containing 5104 image pairs is established. Experimental results demonstrate that the R-net can extract robust invariant features, and then improve registration accuracy under circumstances with obvious changes of surface feature, which is a base of D-net. Uniting pyramid pooling structure with a focal loss function in D-net, both leaky and wrong segmentations can be dramatically improved under complex scenes with many interferences. When compared with baseline methods on different high-resolution remote sensing scenes, the proposed method achieves better performance and more accurate detection results of building changes. |
first_indexed | 2024-03-08T14:53:19Z |
format | Article |
id | doaj.art-5e7aacf80cc0411380c1f8cb461dd629 |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-03-08T14:53:19Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-5e7aacf80cc0411380c1f8cb461dd6292024-01-11T00:01:33ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01172629263910.1109/JSTARS.2023.334493910366788R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing ImagesZhong Chen0https://orcid.org/0000-0001-8256-0156Tong Zheng1https://orcid.org/0009-0004-4653-5147Junsong Leng2https://orcid.org/0000-0001-6443-1190Jiahao Zhang3https://orcid.org/0009-0007-7586-2448He Deng4https://orcid.org/0000-0002-4402-4923Xiaofei Mi5https://orcid.org/0009-0006-2543-1853Jian Yang6https://orcid.org/0000-0001-9732-2409School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, ChinaHuawei Technologies Company Ltd., Chengdu, ChinaSchool of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, ChinaHikvision Digital Technology Company Ltd., Hangzhou, ChinaWuhan University of Science and Technology, Wuhan, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaIn the detection of building changes in high spatial-resolution remote sensing images, both the distribution position and surface characteristics of the same objects are probably different under different imaging phases, which potentially causes high false positives. In order to improve the detection accuracy of building changes, an integration network, named R&D net is proposed in this article, which comprises a registration network (R-net) followed by a change detection network (D-net). In R-net, two different phase images are accepted as inputs, corner points and their descriptors are generated to spatially align those images. After that, the spatially aligned images are fed into the D-net, and building images are detected accordingly. In this article, a multiview automatic labeling method is proposed to obtain labeling corner points. A new dataset containing 5104 image pairs is established. Experimental results demonstrate that the R-net can extract robust invariant features, and then improve registration accuracy under circumstances with obvious changes of surface feature, which is a base of D-net. Uniting pyramid pooling structure with a focal loss function in D-net, both leaky and wrong segmentations can be dramatically improved under complex scenes with many interferences. When compared with baseline methods on different high-resolution remote sensing scenes, the proposed method achieves better performance and more accurate detection results of building changes.https://ieeexplore.ieee.org/document/10366788/Building changesdetection network (D-net)registrationregistration network (R-net)segmentation |
spellingShingle | Zhong Chen Tong Zheng Junsong Leng Jiahao Zhang He Deng Xiaofei Mi Jian Yang R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Building changes detection network (D-net) registration registration network (R-net) segmentation |
title | R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images |
title_full | R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images |
title_fullStr | R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images |
title_full_unstemmed | R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images |
title_short | R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images |
title_sort | r amp d net integration of registration net and detection net for identifying building changes in high spatial resolution remote sensing images |
topic | Building changes detection network (D-net) registration registration network (R-net) segmentation |
url | https://ieeexplore.ieee.org/document/10366788/ |
work_keys_str_mv | AT zhongchen rampdnetintegrationofregistrationnetanddetectionnetforidentifyingbuildingchangesinhighspatialresolutionremotesensingimages AT tongzheng rampdnetintegrationofregistrationnetanddetectionnetforidentifyingbuildingchangesinhighspatialresolutionremotesensingimages AT junsongleng rampdnetintegrationofregistrationnetanddetectionnetforidentifyingbuildingchangesinhighspatialresolutionremotesensingimages AT jiahaozhang rampdnetintegrationofregistrationnetanddetectionnetforidentifyingbuildingchangesinhighspatialresolutionremotesensingimages AT hedeng rampdnetintegrationofregistrationnetanddetectionnetforidentifyingbuildingchangesinhighspatialresolutionremotesensingimages AT xiaofeimi rampdnetintegrationofregistrationnetanddetectionnetforidentifyingbuildingchangesinhighspatialresolutionremotesensingimages AT jianyang rampdnetintegrationofregistrationnetanddetectionnetforidentifyingbuildingchangesinhighspatialresolutionremotesensingimages |