A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing Images
Remote sensing image change detection (RSICD) is a technique that explores the change of surface coverage in a certain time series by studying the difference between multiple remote sensing images (RSIs) collected over the same area. Traditional RSICD algorithms exhibit poor performance on complex c...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9733219/ |
| _version_ | 1818773238536208384 |
|---|---|
| author | Tao Chen Zhiyuan Lu Yue Yang Yuxiang Zhang Bo Du Antonio Plaza |
| author_facet | Tao Chen Zhiyuan Lu Yue Yang Yuxiang Zhang Bo Du Antonio Plaza |
| author_sort | Tao Chen |
| collection | DOAJ |
| description | Remote sensing image change detection (RSICD) is a technique that explores the change of surface coverage in a certain time series by studying the difference between multiple remote sensing images (RSIs) collected over the same area. Traditional RSICD algorithms exhibit poor performance on complex change detection (CD) tasks. In recent years, deep learning (DL) techniques have achieved outstanding results in the fields of RSI segmentation and target recognition. In CD research, most of the methods treat multitemporal remote sensing data as one input and directly apply DL-based image segmentation theory on it while ignoring the spatio-temporal information in these images. In this article, a new siamese neural network is designed by combing an attention mechanism (Siamese_AUNet) with UNet to solve the problems of RSICD algorithms. SiameseNet encodes the feature extraction of RSIs by two branches in the siamese network, respectively. The weights are shared between these two branches in siamese networks. Subsequently, an attention mechanism is added to the model in order to improve its detection ability for changed objects. The models are then compared with conventional neural networks using three benchmark datasets. The results show that the Siamese_AUNet newly proposed in this article exhibits better performance than other standard methods when solving problems related to weak CD and noise suppression. |
| first_indexed | 2024-12-18T10:22:04Z |
| format | Article |
| id | doaj.art-883f4404c3df4f8abdbe577101660870 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-18T10:22:04Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-883f4404c3df4f8abdbe5771016608702022-12-21T21:11:05ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01152357236910.1109/JSTARS.2022.31576489733219A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing ImagesTao Chen0https://orcid.org/0000-0001-6965-1256Zhiyuan Lu1https://orcid.org/0000-0001-7329-5477Yue Yang2Yuxiang Zhang3https://orcid.org/0000-0002-2913-3515Bo Du4https://orcid.org/0000-0002-0059-8458Antonio Plaza5https://orcid.org/0000-0002-9613-1659Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan, ChinaInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan, ChinaInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan, ChinaInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan, ChinaSchool of Computer Science, Wuhan University, Wuhan, ChinaHyperspectral Computing Laboratory, Department of Technology of Computers and Communications, Escuela Politécnica, University of Extremadura, Cáceres, SpainRemote sensing image change detection (RSICD) is a technique that explores the change of surface coverage in a certain time series by studying the difference between multiple remote sensing images (RSIs) collected over the same area. Traditional RSICD algorithms exhibit poor performance on complex change detection (CD) tasks. In recent years, deep learning (DL) techniques have achieved outstanding results in the fields of RSI segmentation and target recognition. In CD research, most of the methods treat multitemporal remote sensing data as one input and directly apply DL-based image segmentation theory on it while ignoring the spatio-temporal information in these images. In this article, a new siamese neural network is designed by combing an attention mechanism (Siamese_AUNet) with UNet to solve the problems of RSICD algorithms. SiameseNet encodes the feature extraction of RSIs by two branches in the siamese network, respectively. The weights are shared between these two branches in siamese networks. Subsequently, an attention mechanism is added to the model in order to improve its detection ability for changed objects. The models are then compared with conventional neural networks using three benchmark datasets. The results show that the Siamese_AUNet newly proposed in this article exhibits better performance than other standard methods when solving problems related to weak CD and noise suppression.https://ieeexplore.ieee.org/document/9733219/Attention blockschange detection (CD)remote sensingsiamese networks |
| spellingShingle | Tao Chen Zhiyuan Lu Yue Yang Yuxiang Zhang Bo Du Antonio Plaza A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention blocks change detection (CD) remote sensing siamese networks |
| title | A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing Images |
| title_full | A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing Images |
| title_fullStr | A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing Images |
| title_full_unstemmed | A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing Images |
| title_short | A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing Images |
| title_sort | siamese network based u net for change detection in high resolution remote sensing images |
| topic | Attention blocks change detection (CD) remote sensing siamese networks |
| url | https://ieeexplore.ieee.org/document/9733219/ |
| work_keys_str_mv | AT taochen asiamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT zhiyuanlu asiamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT yueyang asiamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT yuxiangzhang asiamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT bodu asiamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT antonioplaza asiamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT taochen siamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT zhiyuanlu siamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT yueyang siamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT yuxiangzhang siamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT bodu siamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages AT antonioplaza siamesenetworkbasedunetforchangedetectioninhighresolutionremotesensingimages |