SAR Image Registration Based on ROEWA-Blocks and Multiscale Circle Descriptor
Given the imaging characteristics of synthetic aperture radar (SAR) images and the inherent speckle noise in them, scale-invariant feature transform based algorithms are unable to perform satisfactorily. To improve registration efficiency between SAR images, we propose a robust and efficient registr...
| 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/9573414/ |
| _version_ | 1819364477195255808 |
|---|---|
| author | Yameng Hong Chengcai Leng Xinyue Zhang Huaiping Yan Jinye Peng Licheng Jiao Irene Cheng Anup Basu |
| author_facet | Yameng Hong Chengcai Leng Xinyue Zhang Huaiping Yan Jinye Peng Licheng Jiao Irene Cheng Anup Basu |
| author_sort | Yameng Hong |
| collection | DOAJ |
| description | Given the imaging characteristics of synthetic aperture radar (SAR) images and the inherent speckle noise in them, scale-invariant feature transform based algorithms are unable to perform satisfactorily. To improve registration efficiency between SAR images, we propose a robust and efficient registration method with three main contributions. First, considering sudden dark patches appearing in SAR images, we propose the ratio of exponentially weighted average blocks to suppress the sudden dark patches and better adapt to different test images. This new operator called blocks of the ratio of exponentially weighted averages (ROEWA-B) divides the processing windows of ROEWA into blocks, which can not only reduce speckle noise but also retain more edge details compared to ROEWA when sudden dark patches appear. Second, for outlier removal, we present an approach using the minimum moment map to remove erroneous keypoints. Finally, based on the gradient location orientation histogram descriptor, we propose a novel multiscale circle descriptor, which combines scale change information to give weights to feature points at different scales. Experimental results for various thresholds and evaluations demonstrate the advantage and robustness of our method in registration. |
| first_indexed | 2024-12-24T22:59:34Z |
| format | Article |
| id | doaj.art-04e58f993290493e883987e006836768 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-24T22:59:34Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-04e58f993290493e883987e0068367682022-12-21T16:35:10ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-0114106141062710.1109/JSTARS.2021.31199239573414SAR Image Registration Based on ROEWA-Blocks and Multiscale Circle DescriptorYameng Hong0Chengcai Leng1https://orcid.org/0000-0003-4535-5430Xinyue Zhang2Huaiping Yan3Jinye Peng4Licheng Jiao5https://orcid.org/0000-0003-3354-9617Irene Cheng6https://orcid.org/0000-0001-9699-4895Anup Basu7https://orcid.org/0000-0002-7695-4148School of Mathematics, Northwest University, Xi'an, ChinaSchool of Mathematics, Northwest University, Xi'an, ChinaSchool of Mathematics, Northwest University, Xi'an, ChinaSchool of Information Science and Technology, Northwest University, Xi'an, ChinaSchool of Information Science and Technology, Northwest University, Xi'an, ChinaSchool of Artificial Intelligence, Key Laboratory of Intelligent Perception and Image Understanding of Education Ministry of China, Xidian University, Xi'an, ChinaDepartment of Computing Science, University of Alberta, Edmonton, AB, CanadaDepartment of Computing Science, University of Alberta, Edmonton, AB, CanadaGiven the imaging characteristics of synthetic aperture radar (SAR) images and the inherent speckle noise in them, scale-invariant feature transform based algorithms are unable to perform satisfactorily. To improve registration efficiency between SAR images, we propose a robust and efficient registration method with three main contributions. First, considering sudden dark patches appearing in SAR images, we propose the ratio of exponentially weighted average blocks to suppress the sudden dark patches and better adapt to different test images. This new operator called blocks of the ratio of exponentially weighted averages (ROEWA-B) divides the processing windows of ROEWA into blocks, which can not only reduce speckle noise but also retain more edge details compared to ROEWA when sudden dark patches appear. Second, for outlier removal, we present an approach using the minimum moment map to remove erroneous keypoints. Finally, based on the gradient location orientation histogram descriptor, we propose a novel multiscale circle descriptor, which combines scale change information to give weights to feature points at different scales. Experimental results for various thresholds and evaluations demonstrate the advantage and robustness of our method in registration.https://ieeexplore.ieee.org/document/9573414/Multiscale descriptormultiscale spaceratio of exponentially weighted averages (ROEWA)synthetic aperture radar (SAR) image |
| spellingShingle | Yameng Hong Chengcai Leng Xinyue Zhang Huaiping Yan Jinye Peng Licheng Jiao Irene Cheng Anup Basu SAR Image Registration Based on ROEWA-Blocks and Multiscale Circle Descriptor IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Multiscale descriptor multiscale space ratio of exponentially weighted averages (ROEWA) synthetic aperture radar (SAR) image |
| title | SAR Image Registration Based on ROEWA-Blocks and Multiscale Circle Descriptor |
| title_full | SAR Image Registration Based on ROEWA-Blocks and Multiscale Circle Descriptor |
| title_fullStr | SAR Image Registration Based on ROEWA-Blocks and Multiscale Circle Descriptor |
| title_full_unstemmed | SAR Image Registration Based on ROEWA-Blocks and Multiscale Circle Descriptor |
| title_short | SAR Image Registration Based on ROEWA-Blocks and Multiscale Circle Descriptor |
| title_sort | sar image registration based on roewa blocks and multiscale circle descriptor |
| topic | Multiscale descriptor multiscale space ratio of exponentially weighted averages (ROEWA) synthetic aperture radar (SAR) image |
| url | https://ieeexplore.ieee.org/document/9573414/ |
| work_keys_str_mv | AT yamenghong sarimageregistrationbasedonroewablocksandmultiscalecircledescriptor AT chengcaileng sarimageregistrationbasedonroewablocksandmultiscalecircledescriptor AT xinyuezhang sarimageregistrationbasedonroewablocksandmultiscalecircledescriptor AT huaipingyan sarimageregistrationbasedonroewablocksandmultiscalecircledescriptor AT jinyepeng sarimageregistrationbasedonroewablocksandmultiscalecircledescriptor AT lichengjiao sarimageregistrationbasedonroewablocksandmultiscalecircledescriptor AT irenecheng sarimageregistrationbasedonroewablocksandmultiscalecircledescriptor AT anupbasu sarimageregistrationbasedonroewablocksandmultiscalecircledescriptor |