Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor
Image matching between the optical and synthetic aperture radar (SAR) is one of the most fundamental problems for earth observation. In recent years, many researchers have used hand-made descriptors with their expertise to find matches between optical and SAR images. However, due to the large nonlin...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9647956/ |
| _version_ | 1797947284590166016 |
|---|---|
| author | Yun Liao Yide Di Hao Zhou Anran Li Junhui Liu Mingyu Lu Qing Duan |
| author_facet | Yun Liao Yide Di Hao Zhou Anran Li Junhui Liu Mingyu Lu Qing Duan |
| author_sort | Yun Liao |
| collection | DOAJ |
| description | Image matching between the optical and synthetic aperture radar (SAR) is one of the most fundamental problems for earth observation. In recent years, many researchers have used hand-made descriptors with their expertise to find matches between optical and SAR images. However, due to the large nonlinear radiation difference between optical images and SAR images, the image matching becomes very difficult. To deal with the problems, the article proposes an efficient feature matching and position matching algorithm (MatchosNet) based on local deep feature descriptor. First, A new dataset is presented by collecting a large number of corresponding SAR images and optical images. Then a deep convolutional network with dense blocks and cross stage partial networks is designed to generate deep feature descriptors. Next, the hard L2 loss function and ARCpatch loss function are designed to improve matching effect. In addition, on the basis of feature matching, the two-dimensional (2-D) Gaussian function voting algorithm is designed to further match the position of optical images and SAR images of different sizes. Finally, a large number of quantitative experiments show that MatchosNet has a excellent matching effect in feature matching and position matching. The code will be released at: <uri>https://github.com/LiaoYun0x0/Feature-Matching-and-Position-Matching-between-Optical-and-SAR</uri>. |
| first_indexed | 2024-04-10T21:25:23Z |
| format | Article |
| id | doaj.art-be2e759f80444ebc9b51e38e35f84ad4 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-10T21:25:23Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-be2e759f80444ebc9b51e38e35f84ad42023-01-20T00:00:13ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-011544846210.1109/JSTARS.2021.31346769647956Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature DescriptorYun Liao0Yide Di1https://orcid.org/0000-0003-3802-6620Hao Zhou2Anran Li3Junhui Liu4Mingyu Lu5Qing Duan6National Pilot School of Software, Yunnan University, Kunming, Yunnan, ChinaSchool of Information Science and Technology, Dalian Maritime University, Dalian, ChinaYunnan Lanyi Network Technology Co, Kunming, ChinaYunnan Lanyi Network Technology Co, Kunming, ChinaNational Pilot School of Software, Yunnan University, Kunming, Yunnan, ChinaSchool of Information Science and Technology, Dalian Maritime University, Dalian, ChinaNational Pilot School of Software, Yunnan University, Kunming, Yunnan, ChinaImage matching between the optical and synthetic aperture radar (SAR) is one of the most fundamental problems for earth observation. In recent years, many researchers have used hand-made descriptors with their expertise to find matches between optical and SAR images. However, due to the large nonlinear radiation difference between optical images and SAR images, the image matching becomes very difficult. To deal with the problems, the article proposes an efficient feature matching and position matching algorithm (MatchosNet) based on local deep feature descriptor. First, A new dataset is presented by collecting a large number of corresponding SAR images and optical images. Then a deep convolutional network with dense blocks and cross stage partial networks is designed to generate deep feature descriptors. Next, the hard L2 loss function and ARCpatch loss function are designed to improve matching effect. In addition, on the basis of feature matching, the two-dimensional (2-D) Gaussian function voting algorithm is designed to further match the position of optical images and SAR images of different sizes. Finally, a large number of quantitative experiments show that MatchosNet has a excellent matching effect in feature matching and position matching. The code will be released at: <uri>https://github.com/LiaoYun0x0/Feature-Matching-and-Position-Matching-between-Optical-and-SAR</uri>.https://ieeexplore.ieee.org/document/9647956/Deep learningfeature descriptorfeature matchingimage matchingoptical imagesposition matching |
| spellingShingle | Yun Liao Yide Di Hao Zhou Anran Li Junhui Liu Mingyu Lu Qing Duan Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning feature descriptor feature matching image matching optical images position matching |
| title | Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor |
| title_full | Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor |
| title_fullStr | Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor |
| title_full_unstemmed | Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor |
| title_short | Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor |
| title_sort | feature matching and position matching between optical and sar with local deep feature descriptor |
| topic | Deep learning feature descriptor feature matching image matching optical images position matching |
| url | https://ieeexplore.ieee.org/document/9647956/ |
| work_keys_str_mv | AT yunliao featurematchingandpositionmatchingbetweenopticalandsarwithlocaldeepfeaturedescriptor AT yidedi featurematchingandpositionmatchingbetweenopticalandsarwithlocaldeepfeaturedescriptor AT haozhou featurematchingandpositionmatchingbetweenopticalandsarwithlocaldeepfeaturedescriptor AT anranli featurematchingandpositionmatchingbetweenopticalandsarwithlocaldeepfeaturedescriptor AT junhuiliu featurematchingandpositionmatchingbetweenopticalandsarwithlocaldeepfeaturedescriptor AT mingyulu featurematchingandpositionmatchingbetweenopticalandsarwithlocaldeepfeaturedescriptor AT qingduan featurematchingandpositionmatchingbetweenopticalandsarwithlocaldeepfeaturedescriptor |