Polarimetric SAR Image Affine Registration Based on Neighborhood Consensus
As the base of Synthetic Aperture Radar (SAR) image processing, the registration of polarimetric SAR images requires high accuracy and a fast speed. Most methods used to register polarimetric SAR images based on deep learning are combined with patch matching and iterative estimation, e.g. the random...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
China Science Publishing & Media Ltd. (CSPM)
2021-02-01
|
| Series: | Leida xuebao |
| Subjects: | |
| Online Access: | https://radars.ac.cn/cn/article/doi/10.12000/JR20120 |
| _version_ | 1797421596826140672 |
|---|---|
| author | Qingtao ZHU Junjun YIN Liang ZENG Jian YANG |
| author_facet | Qingtao ZHU Junjun YIN Liang ZENG Jian YANG |
| author_sort | Qingtao ZHU |
| collection | DOAJ |
| description | As the base of Synthetic Aperture Radar (SAR) image processing, the registration of polarimetric SAR images requires high accuracy and a fast speed. Most methods used to register polarimetric SAR images based on deep learning are combined with patch matching and iterative estimation, e.g. the random sample consensus algorithm. However, end-to-end deep convolutional neural networks have not been used in the non-iterative affine registration of polarimetric SAR images. This paper proposes a framework for end-to-end polarimetric SAR image registration that is based on weakly-supervised learning and uses no image patch processing or iterative parameter estimation. First, feature extraction is performed on input image pairs to obtain dense feature maps with the most relevant k matches kept for each feature point. To filter the matched feature pairs, the 4D sparse feature matching maps are then fed into a 4D sparse convolutional network based on neighborhood consensus. Lastly, the affine parameters are solved by the weighted least square method according to the degree of confidence of the matches, which enables the affine registration of the input image pair. As test image pairs, we use farmland data from Wallerfing, Germany obtained by the RADARSAT-2 satellite and Zhoushan port data from China obtained by the PAZ satellite. Comprehensive experiments were conducted on polarimetric SAR image pairs using different orbit directions, imaging modes, polarization types and resolutions. Compared with four existing methods, the proposed method was found to have high accuracy and a fast speed. |
| first_indexed | 2024-03-09T07:19:48Z |
| format | Article |
| id | doaj.art-47fb7d50983e4351883dd3390984b60e |
| institution | Directory Open Access Journal |
| issn | 2095-283X |
| language | English |
| last_indexed | 2024-03-09T07:19:48Z |
| publishDate | 2021-02-01 |
| publisher | China Science Publishing & Media Ltd. (CSPM) |
| record_format | Article |
| series | Leida xuebao |
| spelling | doaj.art-47fb7d50983e4351883dd3390984b60e2023-12-03T07:49:56ZengChina Science Publishing & Media Ltd. (CSPM)Leida xuebao2095-283X2021-02-01101496010.12000/JR20120R20120Polarimetric SAR Image Affine Registration Based on Neighborhood ConsensusQingtao ZHU0Junjun YIN1Liang ZENG2Jian YANG3Department of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaSchool of Computer and Communication Engineering, University of Science and Technology, Beijing 100083, ChinaDepartment of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaAs the base of Synthetic Aperture Radar (SAR) image processing, the registration of polarimetric SAR images requires high accuracy and a fast speed. Most methods used to register polarimetric SAR images based on deep learning are combined with patch matching and iterative estimation, e.g. the random sample consensus algorithm. However, end-to-end deep convolutional neural networks have not been used in the non-iterative affine registration of polarimetric SAR images. This paper proposes a framework for end-to-end polarimetric SAR image registration that is based on weakly-supervised learning and uses no image patch processing or iterative parameter estimation. First, feature extraction is performed on input image pairs to obtain dense feature maps with the most relevant k matches kept for each feature point. To filter the matched feature pairs, the 4D sparse feature matching maps are then fed into a 4D sparse convolutional network based on neighborhood consensus. Lastly, the affine parameters are solved by the weighted least square method according to the degree of confidence of the matches, which enables the affine registration of the input image pair. As test image pairs, we use farmland data from Wallerfing, Germany obtained by the RADARSAT-2 satellite and Zhoushan port data from China obtained by the PAZ satellite. Comprehensive experiments were conducted on polarimetric SAR image pairs using different orbit directions, imaging modes, polarization types and resolutions. Compared with four existing methods, the proposed method was found to have high accuracy and a fast speed.https://radars.ac.cn/cn/article/doi/10.12000/JR20120neighborhood consensusaffine transformationpolarimetric sarimage registrationsparse convolutional neural network |
| spellingShingle | Qingtao ZHU Junjun YIN Liang ZENG Jian YANG Polarimetric SAR Image Affine Registration Based on Neighborhood Consensus Leida xuebao neighborhood consensus affine transformation polarimetric sar image registration sparse convolutional neural network |
| title | Polarimetric SAR Image Affine Registration Based on Neighborhood Consensus |
| title_full | Polarimetric SAR Image Affine Registration Based on Neighborhood Consensus |
| title_fullStr | Polarimetric SAR Image Affine Registration Based on Neighborhood Consensus |
| title_full_unstemmed | Polarimetric SAR Image Affine Registration Based on Neighborhood Consensus |
| title_short | Polarimetric SAR Image Affine Registration Based on Neighborhood Consensus |
| title_sort | polarimetric sar image affine registration based on neighborhood consensus |
| topic | neighborhood consensus affine transformation polarimetric sar image registration sparse convolutional neural network |
| url | https://radars.ac.cn/cn/article/doi/10.12000/JR20120 |
| work_keys_str_mv | AT qingtaozhu polarimetricsarimageaffineregistrationbasedonneighborhoodconsensus AT junjunyin polarimetricsarimageaffineregistrationbasedonneighborhoodconsensus AT liangzeng polarimetricsarimageaffineregistrationbasedonneighborhoodconsensus AT jianyang polarimetricsarimageaffineregistrationbasedonneighborhoodconsensus |