Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion Strategy
Change detection in multitemporal synthetic aperture radar (SAR) images has been an important research content in the field of remote sensing for a long time. In this article, based on the slow feature analysis (SFA) theory and the nonsubsampled contourlet transform (NSCT) algorithm, we propose a no...
| 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/9755046/ |
| _version_ | 1829137159164002304 |
|---|---|
| author | Weisong Li Xiayang Xiao Penghao Xiao Haipeng Wang Feng Xu |
| author_facet | Weisong Li Xiayang Xiao Penghao Xiao Haipeng Wang Feng Xu |
| author_sort | Weisong Li |
| collection | DOAJ |
| description | Change detection in multitemporal synthetic aperture radar (SAR) images has been an important research content in the field of remote sensing for a long time. In this article, based on the slow feature analysis (SFA) theory and the nonsubsampled contourlet transform (NSCT) algorithm, we propose a novel unsupervised change detection method called NSCT nonlocal means (NSCT-NLM). The powerful extraction to the changed information of SFA and the superior information fusion of NSCT are jointly adopted in this method. The main framework consists of the following parts. First, SFA and the log-ratio operator are used to generate difference images (DIs) independently. Then, the NSCT is used to fuse two DIs into a new higher quality DI. The newly fused DI combines the complementary information of the two kinds of original DI. Therefore, the contrast of the changed regions and unchanged regions is greatly enhanced, as well as the changed details are preserved more completely. Furthermore, an NLM filtering algorithm is employed to suppress the strong speckles in the fused DI. We use the fuzzy C-means algorithm to generate the final binary change map. The experiments are carried out on two public datasets and three real-world SAR datasets from different scenarios. The results demonstrate that the proposed method has higher detection accuracy by comparing with the reference methods. |
| first_indexed | 2024-12-14T18:53:50Z |
| format | Article |
| id | doaj.art-a85196e98ced48669e160e8e831a017a |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-14T18:53:50Z |
| 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-a85196e98ced48669e160e8e831a017a2022-12-21T22:51:09ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01153008302310.1109/JSTARS.2022.31662349755046Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion StrategyWeisong Li0https://orcid.org/0000-0003-1486-4363Xiayang Xiao1Penghao Xiao2Haipeng Wang3https://orcid.org/0000-0003-1912-7143Feng Xu4https://orcid.org/0000-0002-7015-1467Key Laboratory of Information Science of Electromagnetic Waves, Fudan University, Shanghai, ChinaKey Laboratory of Information Science of Electromagnetic Waves, Fudan University, Shanghai, ChinaKey Laboratory of Information Science of Electromagnetic Waves, Fudan University, Shanghai, ChinaKey Laboratory of Information Science of Electromagnetic Waves, Fudan University, Shanghai, ChinaKey Laboratory of Information Science of Electromagnetic Waves, Fudan University, Shanghai, ChinaChange detection in multitemporal synthetic aperture radar (SAR) images has been an important research content in the field of remote sensing for a long time. In this article, based on the slow feature analysis (SFA) theory and the nonsubsampled contourlet transform (NSCT) algorithm, we propose a novel unsupervised change detection method called NSCT nonlocal means (NSCT-NLM). The powerful extraction to the changed information of SFA and the superior information fusion of NSCT are jointly adopted in this method. The main framework consists of the following parts. First, SFA and the log-ratio operator are used to generate difference images (DIs) independently. Then, the NSCT is used to fuse two DIs into a new higher quality DI. The newly fused DI combines the complementary information of the two kinds of original DI. Therefore, the contrast of the changed regions and unchanged regions is greatly enhanced, as well as the changed details are preserved more completely. Furthermore, an NLM filtering algorithm is employed to suppress the strong speckles in the fused DI. We use the fuzzy C-means algorithm to generate the final binary change map. The experiments are carried out on two public datasets and three real-world SAR datasets from different scenarios. The results demonstrate that the proposed method has higher detection accuracy by comparing with the reference methods.https://ieeexplore.ieee.org/document/9755046/Nonsubsampled contourlet transform (NSCT)slow feature analysis (SFA)synthetic aperture radar (SAR) imagesunsupervised change detection |
| spellingShingle | Weisong Li Xiayang Xiao Penghao Xiao Haipeng Wang Feng Xu Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion Strategy IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Nonsubsampled contourlet transform (NSCT) slow feature analysis (SFA) synthetic aperture radar (SAR) images unsupervised change detection |
| title | Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion Strategy |
| title_full | Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion Strategy |
| title_fullStr | Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion Strategy |
| title_full_unstemmed | Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion Strategy |
| title_short | Change Detection in Multitemporal SAR Images Based on Slow Feature Analysis Combined With Improving Image Fusion Strategy |
| title_sort | change detection in multitemporal sar images based on slow feature analysis combined with improving image fusion strategy |
| topic | Nonsubsampled contourlet transform (NSCT) slow feature analysis (SFA) synthetic aperture radar (SAR) images unsupervised change detection |
| url | https://ieeexplore.ieee.org/document/9755046/ |
| work_keys_str_mv | AT weisongli changedetectioninmultitemporalsarimagesbasedonslowfeatureanalysiscombinedwithimprovingimagefusionstrategy AT xiayangxiao changedetectioninmultitemporalsarimagesbasedonslowfeatureanalysiscombinedwithimprovingimagefusionstrategy AT penghaoxiao changedetectioninmultitemporalsarimagesbasedonslowfeatureanalysiscombinedwithimprovingimagefusionstrategy AT haipengwang changedetectioninmultitemporalsarimagesbasedonslowfeatureanalysiscombinedwithimprovingimagefusionstrategy AT fengxu changedetectioninmultitemporalsarimagesbasedonslowfeatureanalysiscombinedwithimprovingimagefusionstrategy |