RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer Learning
Maps can help governments in infrastructure development and emergency rescue operations around the world. Using adversarial learning to generate maps from remote sensing images is an emerging field. As we now know, the urban construction styles of different cities are diverse. The current translatio...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/4/919 |
| _version_ | 1797476857560432640 |
|---|---|
| author | Jieqiong Song Jun Li Hao Chen Jiangjiang Wu |
| author_facet | Jieqiong Song Jun Li Hao Chen Jiangjiang Wu |
| author_sort | Jieqiong Song |
| collection | DOAJ |
| description | Maps can help governments in infrastructure development and emergency rescue operations around the world. Using adversarial learning to generate maps from remote sensing images is an emerging field. As we now know, the urban construction styles of different cities are diverse. The current translation methods for remote sensing image-to-map tasks only work on the specific regions with similar styles and structures to the training set and perform poorly on previously unseen areas. We argue that this greatly limits their use. In this work, we intend to seek a remote sensing image-to-map translation model that approaches the challenge of generating maps for the remote sensing images of unseen areas. Our remote sensing image-to-map translation model (RSMT) achieves universal and general applicability to generate maps over multiple regions by combining adversarial deep transfer training schemes with novel attention-based network designs. Extracting the content and style latent features from remote sensing images and a series of maps, respectively, RSMT generalizes a pattern applied to the remote sensing images of new areas. Meanwhile, we introduce feature map loss and map consistency loss to reinforce generated maps’ precision and geometry similarity. We critically analyze qualitative and quantitative results using widely adopted evaluation metrics through extensive validation and comparisons with previous remote sensing image-to-map approaches. The results of experiment indicate that RSMT can translate remote sensing images to maps better than several state-of-the-art methods. |
| first_indexed | 2024-03-09T21:09:41Z |
| format | Article |
| id | doaj.art-fa25ac90ed6644f6adb315b714b6d8d0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:09:41Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-fa25ac90ed6644f6adb315b714b6d8d02023-11-23T21:54:06ZengMDPI AGRemote Sensing2072-42922022-02-0114491910.3390/rs14040919RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer LearningJieqiong Song0Jun Li1Hao Chen2Jiangjiang Wu3College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaMaps can help governments in infrastructure development and emergency rescue operations around the world. Using adversarial learning to generate maps from remote sensing images is an emerging field. As we now know, the urban construction styles of different cities are diverse. The current translation methods for remote sensing image-to-map tasks only work on the specific regions with similar styles and structures to the training set and perform poorly on previously unseen areas. We argue that this greatly limits their use. In this work, we intend to seek a remote sensing image-to-map translation model that approaches the challenge of generating maps for the remote sensing images of unseen areas. Our remote sensing image-to-map translation model (RSMT) achieves universal and general applicability to generate maps over multiple regions by combining adversarial deep transfer training schemes with novel attention-based network designs. Extracting the content and style latent features from remote sensing images and a series of maps, respectively, RSMT generalizes a pattern applied to the remote sensing images of new areas. Meanwhile, we introduce feature map loss and map consistency loss to reinforce generated maps’ precision and geometry similarity. We critically analyze qualitative and quantitative results using widely adopted evaluation metrics through extensive validation and comparisons with previous remote sensing image-to-map approaches. The results of experiment indicate that RSMT can translate remote sensing images to maps better than several state-of-the-art methods.https://www.mdpi.com/2072-4292/14/4/919map translationadversarial transfer learningremote sensing imageattention mechanism |
| spellingShingle | Jieqiong Song Jun Li Hao Chen Jiangjiang Wu RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer Learning Remote Sensing map translation adversarial transfer learning remote sensing image attention mechanism |
| title | RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer Learning |
| title_full | RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer Learning |
| title_fullStr | RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer Learning |
| title_full_unstemmed | RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer Learning |
| title_short | RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer Learning |
| title_sort | rsmt a remote sensing image to map translation model via adversarial deep transfer learning |
| topic | map translation adversarial transfer learning remote sensing image attention mechanism |
| url | https://www.mdpi.com/2072-4292/14/4/919 |
| work_keys_str_mv | AT jieqiongsong rsmtaremotesensingimagetomaptranslationmodelviaadversarialdeeptransferlearning AT junli rsmtaremotesensingimagetomaptranslationmodelviaadversarialdeeptransferlearning AT haochen rsmtaremotesensingimagetomaptranslationmodelviaadversarialdeeptransferlearning AT jiangjiangwu rsmtaremotesensingimagetomaptranslationmodelviaadversarialdeeptransferlearning |