A Robust Strategy for Large-Size Optical and SAR Image Registration
The traditional template matching strategy of optical and synthetic aperture radar (SAR) is sensitive to the nonlinear transformation between two images. In some cases, the optical and SAR image pairs do not conform to the affine transformation condition. To address this issue, this study presents a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/13/3012 |
| _version_ | 1797434033630609408 |
|---|---|
| author | Zeyi Li Haitao Zhang Yihang Huang Haifeng Li |
| author_facet | Zeyi Li Haitao Zhang Yihang Huang Haifeng Li |
| author_sort | Zeyi Li |
| collection | DOAJ |
| description | The traditional template matching strategy of optical and synthetic aperture radar (SAR) is sensitive to the nonlinear transformation between two images. In some cases, the optical and SAR image pairs do not conform to the affine transformation condition. To address this issue, this study presents a novel template matching strategy which uses the One-Class Support Vector Machine (SVM) to remove outliers. First, we propose a method to construct the similarity map dataset using the SEN1-2 dataset for training the One-Class SVM. Second, a four-step strategy for optical and SAR image registration is presented in this paper. In the first step, the optical image is divided into some grids. In the second step, the strongest Harris response point is selected as the feature point in each grid. In the third step, we use Gaussian pyramid features of oriented gradients (GPOG) descriptor to calculate the similarity map in the search region. The trained One-Class SVM is used to remove outliers through similarity maps in the fourth step. Furthermore, the number of improve matches (NIM) and the rate of improve matches (RIM) are designed to measure the effect of image registration. Finally, this paper designs two experiments to prove that the proposed strategy can correctly select the matching points through similarity maps. The experimental results of the One-Class SVM in dataset show that the One-Class SVM can select the correct points in different datasets. The image registration results obtained on the second experiment show that the proposed strategy is robust to the nonlinear transformation between optical and SAR images. |
| first_indexed | 2024-03-09T10:26:05Z |
| format | Article |
| id | doaj.art-ac24a95160ea425f8d0d2db251170d0e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T10:26:05Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ac24a95160ea425f8d0d2db251170d0e2023-12-01T21:40:15ZengMDPI AGRemote Sensing2072-42922022-06-011413301210.3390/rs14133012A Robust Strategy for Large-Size Optical and SAR Image RegistrationZeyi Li0Haitao Zhang1Yihang Huang2Haifeng Li3Department of Precision Instruments, Tsinghua University, Beijing 100083, ChinaDepartment of Precision Instruments, Tsinghua University, Beijing 100083, ChinaDepartment of Precision Instruments, Tsinghua University, Beijing 100083, ChinaDepartment of Geomatics, School of Geosciences and Info-Physic, Central South University, Changsha 410000, ChinaThe traditional template matching strategy of optical and synthetic aperture radar (SAR) is sensitive to the nonlinear transformation between two images. In some cases, the optical and SAR image pairs do not conform to the affine transformation condition. To address this issue, this study presents a novel template matching strategy which uses the One-Class Support Vector Machine (SVM) to remove outliers. First, we propose a method to construct the similarity map dataset using the SEN1-2 dataset for training the One-Class SVM. Second, a four-step strategy for optical and SAR image registration is presented in this paper. In the first step, the optical image is divided into some grids. In the second step, the strongest Harris response point is selected as the feature point in each grid. In the third step, we use Gaussian pyramid features of oriented gradients (GPOG) descriptor to calculate the similarity map in the search region. The trained One-Class SVM is used to remove outliers through similarity maps in the fourth step. Furthermore, the number of improve matches (NIM) and the rate of improve matches (RIM) are designed to measure the effect of image registration. Finally, this paper designs two experiments to prove that the proposed strategy can correctly select the matching points through similarity maps. The experimental results of the One-Class SVM in dataset show that the One-Class SVM can select the correct points in different datasets. The image registration results obtained on the second experiment show that the proposed strategy is robust to the nonlinear transformation between optical and SAR images.https://www.mdpi.com/2072-4292/14/13/3012image registrationnonlinear deformationsimilarity mapOne-Class SVMsynthetic aperture radar (SAR) |
| spellingShingle | Zeyi Li Haitao Zhang Yihang Huang Haifeng Li A Robust Strategy for Large-Size Optical and SAR Image Registration Remote Sensing image registration nonlinear deformation similarity map One-Class SVM synthetic aperture radar (SAR) |
| title | A Robust Strategy for Large-Size Optical and SAR Image Registration |
| title_full | A Robust Strategy for Large-Size Optical and SAR Image Registration |
| title_fullStr | A Robust Strategy for Large-Size Optical and SAR Image Registration |
| title_full_unstemmed | A Robust Strategy for Large-Size Optical and SAR Image Registration |
| title_short | A Robust Strategy for Large-Size Optical and SAR Image Registration |
| title_sort | robust strategy for large size optical and sar image registration |
| topic | image registration nonlinear deformation similarity map One-Class SVM synthetic aperture radar (SAR) |
| url | https://www.mdpi.com/2072-4292/14/13/3012 |
| work_keys_str_mv | AT zeyili arobuststrategyforlargesizeopticalandsarimageregistration AT haitaozhang arobuststrategyforlargesizeopticalandsarimageregistration AT yihanghuang arobuststrategyforlargesizeopticalandsarimageregistration AT haifengli arobuststrategyforlargesizeopticalandsarimageregistration AT zeyili robuststrategyforlargesizeopticalandsarimageregistration AT haitaozhang robuststrategyforlargesizeopticalandsarimageregistration AT yihanghuang robuststrategyforlargesizeopticalandsarimageregistration AT haifengli robuststrategyforlargesizeopticalandsarimageregistration |