Multi-Scale Fused SAR Image Registration Based on Deep Forest
SAR image registration is a crucial problem in SAR image processing since the registration results with high precision are conducive to improving the quality of other problems, such as change detection of SAR images. Recently, for most DL-based SAR image registration methods, the problem of SAR imag...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/11/2227 |
| _version_ | 1827690397565976576 |
|---|---|
| author | Shasha Mao Jinyuan Yang Shuiping Gou Licheng Jiao Tao Xiong Lin Xiong |
| author_facet | Shasha Mao Jinyuan Yang Shuiping Gou Licheng Jiao Tao Xiong Lin Xiong |
| author_sort | Shasha Mao |
| collection | DOAJ |
| description | SAR image registration is a crucial problem in SAR image processing since the registration results with high precision are conducive to improving the quality of other problems, such as change detection of SAR images. Recently, for most DL-based SAR image registration methods, the problem of SAR image registration has been regarded as a binary classification problem with matching and non-matching categories to construct the training model, where a fixed scale is generally set to capture pair image blocks corresponding to key points to generate the training set, whereas it is known that image blocks with different scales contain different information, which affects the performance of registration. Moreover, the number of key points is not enough to generate a mass of class-balance training samples. Hence, we proposed a new method of SAR image registration that meanwhile utilizes the information of multiple scales to construct the matching models. Specifically, considering that the number of training samples is small, deep forest was employed to train multiple matching models. Moreover, a multi-scale fusion strategy is proposed to integrate the multiple predictions and obtain the best pair matching points between the reference image and the sensed image. Finally, experimental results on four datasets illustrate that the proposed method is better than the compared state-of-the-art methods, and the analyses for different scales also indicate that the fusion of multiple scales is more effective and more robust for SAR image registration than one single fixed scale. |
| first_indexed | 2024-03-10T10:38:39Z |
| format | Article |
| id | doaj.art-036460327235494fbe349140b5e2e121 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T10:38:39Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-036460327235494fbe349140b5e2e1212023-11-21T23:06:07ZengMDPI AGRemote Sensing2072-42922021-06-011311222710.3390/rs13112227Multi-Scale Fused SAR Image Registration Based on Deep ForestShasha Mao0Jinyuan Yang1Shuiping Gou2Licheng Jiao3Tao Xiong4Lin Xiong5Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaJD Finance America Corporation, 675 E Middlefield Rd, Mountain View, CA 94043, USASAR image registration is a crucial problem in SAR image processing since the registration results with high precision are conducive to improving the quality of other problems, such as change detection of SAR images. Recently, for most DL-based SAR image registration methods, the problem of SAR image registration has been regarded as a binary classification problem with matching and non-matching categories to construct the training model, where a fixed scale is generally set to capture pair image blocks corresponding to key points to generate the training set, whereas it is known that image blocks with different scales contain different information, which affects the performance of registration. Moreover, the number of key points is not enough to generate a mass of class-balance training samples. Hence, we proposed a new method of SAR image registration that meanwhile utilizes the information of multiple scales to construct the matching models. Specifically, considering that the number of training samples is small, deep forest was employed to train multiple matching models. Moreover, a multi-scale fusion strategy is proposed to integrate the multiple predictions and obtain the best pair matching points between the reference image and the sensed image. Finally, experimental results on four datasets illustrate that the proposed method is better than the compared state-of-the-art methods, and the analyses for different scales also indicate that the fusion of multiple scales is more effective and more robust for SAR image registration than one single fixed scale.https://www.mdpi.com/2072-4292/13/11/2227SAR image registrationsynthetic aperture radardeep forestmulti-scale fusion |
| spellingShingle | Shasha Mao Jinyuan Yang Shuiping Gou Licheng Jiao Tao Xiong Lin Xiong Multi-Scale Fused SAR Image Registration Based on Deep Forest Remote Sensing SAR image registration synthetic aperture radar deep forest multi-scale fusion |
| title | Multi-Scale Fused SAR Image Registration Based on Deep Forest |
| title_full | Multi-Scale Fused SAR Image Registration Based on Deep Forest |
| title_fullStr | Multi-Scale Fused SAR Image Registration Based on Deep Forest |
| title_full_unstemmed | Multi-Scale Fused SAR Image Registration Based on Deep Forest |
| title_short | Multi-Scale Fused SAR Image Registration Based on Deep Forest |
| title_sort | multi scale fused sar image registration based on deep forest |
| topic | SAR image registration synthetic aperture radar deep forest multi-scale fusion |
| url | https://www.mdpi.com/2072-4292/13/11/2227 |
| work_keys_str_mv | AT shashamao multiscalefusedsarimageregistrationbasedondeepforest AT jinyuanyang multiscalefusedsarimageregistrationbasedondeepforest AT shuipinggou multiscalefusedsarimageregistrationbasedondeepforest AT lichengjiao multiscalefusedsarimageregistrationbasedondeepforest AT taoxiong multiscalefusedsarimageregistrationbasedondeepforest AT linxiong multiscalefusedsarimageregistrationbasedondeepforest |