A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHING
Matching synthetic aperture radar (SAR) and optical remote sensing imagery is a key first step towards exploiting the complementary nature of these data in data fusion frameworks. While numerous signal-based approaches to matching have been proposed, they often fail to perform well in multi-sensor s...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2019-09-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2-W7/71/2019/isprs-annals-IV-2-W7-71-2019.pdf |
| _version_ | 1818952498643206144 |
|---|---|
| author | L. H. Hughes M. Schmitt |
| author_facet | L. H. Hughes M. Schmitt |
| author_sort | L. H. Hughes |
| collection | DOAJ |
| description | Matching synthetic aperture radar (SAR) and optical remote sensing imagery is a key first step towards exploiting the complementary nature of these data in data fusion frameworks. While numerous signal-based approaches to matching have been proposed, they often fail to perform well in multi-sensor situations. In recent years deep learning has become the go-to approach for solving image matching in computer vision applications, and has also been adapted to the case of SAR-optical image matching. However, the hitherto proposed techniques still fail to match SAR and optical imagery in a generalizable manner. These limitations are largely due to the complexities in creating large-scale datasets of corresponding SAR and optical image patches. In this paper we frame the matching problem within semi-supervised learning, and use this as a proxy for investigating the effects of data scarcity on matching. In doing so we make an initial contribution towards the use of semi-supervised learning for matching SAR and optical imagery. We further gain insight into the non-complementary nature of commonly used supervised and unsupervised loss functions, as well as dataset size requirements for semi-supervised matching. |
| first_indexed | 2024-12-20T09:51:20Z |
| format | Article |
| id | doaj.art-ba060c6d90ab4c28a15a9c474f6773b7 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-12-20T09:51:20Z |
| publishDate | 2019-09-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-ba060c6d90ab4c28a15a9c474f6773b72022-12-21T19:44:35ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502019-09-01IV-2-W7717810.5194/isprs-annals-IV-2-W7-71-2019A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHINGL. H. Hughes0M. Schmitt1Signal Processing in Earth Observation, Technical University of Munich, Munich, GermanySignal Processing in Earth Observation, Technical University of Munich, Munich, GermanyMatching synthetic aperture radar (SAR) and optical remote sensing imagery is a key first step towards exploiting the complementary nature of these data in data fusion frameworks. While numerous signal-based approaches to matching have been proposed, they often fail to perform well in multi-sensor situations. In recent years deep learning has become the go-to approach for solving image matching in computer vision applications, and has also been adapted to the case of SAR-optical image matching. However, the hitherto proposed techniques still fail to match SAR and optical imagery in a generalizable manner. These limitations are largely due to the complexities in creating large-scale datasets of corresponding SAR and optical image patches. In this paper we frame the matching problem within semi-supervised learning, and use this as a proxy for investigating the effects of data scarcity on matching. In doing so we make an initial contribution towards the use of semi-supervised learning for matching SAR and optical imagery. We further gain insight into the non-complementary nature of commonly used supervised and unsupervised loss functions, as well as dataset size requirements for semi-supervised matching.https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2-W7/71/2019/isprs-annals-IV-2-W7-71-2019.pdf |
| spellingShingle | L. H. Hughes M. Schmitt A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHING ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHING |
| title_full | A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHING |
| title_fullStr | A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHING |
| title_full_unstemmed | A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHING |
| title_short | A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHING |
| title_sort | semi supervised approach to sar optical image matching |
| url | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2-W7/71/2019/isprs-annals-IV-2-W7-71-2019.pdf |
| work_keys_str_mv | AT lhhughes asemisupervisedapproachtosaropticalimagematching AT mschmitt asemisupervisedapproachtosaropticalimagematching AT lhhughes semisupervisedapproachtosaropticalimagematching AT mschmitt semisupervisedapproachtosaropticalimagematching |