S<sup>2</sup>-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image Registration
In this paper, the super-resolution structural point cloud matching (S<sup>2</sup>-PCM) framework is proposed for video synthetic aperture radar (SAR) inter-frame registration, which consists of a feature recurrence super-resolution network (FRSR-Net), structural point cloud extraction n...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/17/4302 |
| _version_ | 1827665058806628352 |
|---|---|
| author | Zhikun Xie Jun Shi Yihang Zhou Xiaqing Yang Wenxuan Guo Xiaoling Zhang |
| author_facet | Zhikun Xie Jun Shi Yihang Zhou Xiaqing Yang Wenxuan Guo Xiaoling Zhang |
| author_sort | Zhikun Xie |
| collection | DOAJ |
| description | In this paper, the super-resolution structural point cloud matching (S<sup>2</sup>-PCM) framework is proposed for video synthetic aperture radar (SAR) inter-frame registration, which consists of a feature recurrence super-resolution network (FRSR-Net), structural point cloud extraction network (SPCE-Net) and robust point matching network (RPM-Net). FRSR-Net is implemented by integrating the feature recurrence structure and residual dense block (RDB) for super-resolution enhancement, SPCE-Net is implemented by training a U-Net with data augmentation, and RPM-Net is applied for robust point cloud matching. Experimental results show that compared with the classical SIFT-like algorithms, S<sup>2</sup>-PCM achieves higher registration accuracy for video-SAR images under diverse evaluation metrics, such as mutual information (MI), normalized mutual information (NMI), entropy correlation coefficient (ECC), structural similarity (SSIM), etc. The proposed FRSR-Net can significantly improve the quality of video-SAR images and point cloud extraction accuracy. Combining FRSR-Net with S<sup>2</sup>-PCM, we can obtain higher inter-frame registration accuracy, which is crucial for moving target detection and shadow tracking. |
| first_indexed | 2024-03-10T01:18:14Z |
| format | Article |
| id | doaj.art-90426e447e0c46c791990a8d9ab7edca |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T01:18:14Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-90426e447e0c46c791990a8d9ab7edca2023-11-23T14:04:20ZengMDPI AGRemote Sensing2072-42922022-09-011417430210.3390/rs14174302S<sup>2</sup>-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image RegistrationZhikun Xie0Jun Shi1Yihang Zhou2Xiaqing Yang3Wenxuan Guo4Xiaoling Zhang5School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaIn this paper, the super-resolution structural point cloud matching (S<sup>2</sup>-PCM) framework is proposed for video synthetic aperture radar (SAR) inter-frame registration, which consists of a feature recurrence super-resolution network (FRSR-Net), structural point cloud extraction network (SPCE-Net) and robust point matching network (RPM-Net). FRSR-Net is implemented by integrating the feature recurrence structure and residual dense block (RDB) for super-resolution enhancement, SPCE-Net is implemented by training a U-Net with data augmentation, and RPM-Net is applied for robust point cloud matching. Experimental results show that compared with the classical SIFT-like algorithms, S<sup>2</sup>-PCM achieves higher registration accuracy for video-SAR images under diverse evaluation metrics, such as mutual information (MI), normalized mutual information (NMI), entropy correlation coefficient (ECC), structural similarity (SSIM), etc. The proposed FRSR-Net can significantly improve the quality of video-SAR images and point cloud extraction accuracy. Combining FRSR-Net with S<sup>2</sup>-PCM, we can obtain higher inter-frame registration accuracy, which is crucial for moving target detection and shadow tracking.https://www.mdpi.com/2072-4292/14/17/4302SAR image registrationRPMsuper-resolution networkvideo-SAR |
| spellingShingle | Zhikun Xie Jun Shi Yihang Zhou Xiaqing Yang Wenxuan Guo Xiaoling Zhang S<sup>2</sup>-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image Registration Remote Sensing SAR image registration RPM super-resolution network video-SAR |
| title | S<sup>2</sup>-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image Registration |
| title_full | S<sup>2</sup>-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image Registration |
| title_fullStr | S<sup>2</sup>-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image Registration |
| title_full_unstemmed | S<sup>2</sup>-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image Registration |
| title_short | S<sup>2</sup>-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image Registration |
| title_sort | s sup 2 sup pcm super resolution structural point cloud matching for high accuracy video sar image registration |
| topic | SAR image registration RPM super-resolution network video-SAR |
| url | https://www.mdpi.com/2072-4292/14/17/4302 |
| work_keys_str_mv | AT zhikunxie ssup2suppcmsuperresolutionstructuralpointcloudmatchingforhighaccuracyvideosarimageregistration AT junshi ssup2suppcmsuperresolutionstructuralpointcloudmatchingforhighaccuracyvideosarimageregistration AT yihangzhou ssup2suppcmsuperresolutionstructuralpointcloudmatchingforhighaccuracyvideosarimageregistration AT xiaqingyang ssup2suppcmsuperresolutionstructuralpointcloudmatchingforhighaccuracyvideosarimageregistration AT wenxuanguo ssup2suppcmsuperresolutionstructuralpointcloudmatchingforhighaccuracyvideosarimageregistration AT xiaolingzhang ssup2suppcmsuperresolutionstructuralpointcloudmatchingforhighaccuracyvideosarimageregistration |