Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building Footprints
For most cities, municipal governments have constructed basic building footprint datasets that need to be updated regularly for the management and monitoring of urban development and ecology. Cities are capable of changing in a short period of time, and the area of change is variable; hence, automat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/22/5851 |
| _version_ | 1797464013614874624 |
|---|---|
| author | Zehui Wang Yu Meng Jingbo Chen Junxian Ma Anzhi Yue Jiansheng Chen |
| author_facet | Zehui Wang Yu Meng Jingbo Chen Junxian Ma Anzhi Yue Jiansheng Chen |
| author_sort | Zehui Wang |
| collection | DOAJ |
| description | For most cities, municipal governments have constructed basic building footprint datasets that need to be updated regularly for the management and monitoring of urban development and ecology. Cities are capable of changing in a short period of time, and the area of change is variable; hence, automated methods for generating up-to-date building footprints are urgently needed. However, the labels of current buildings or changed areas are usually lacking, and the conditions for acquiring images from different periods are not perfectly consistent, which can severely limit deep learning methods when attempting to learn deep information about buildings. In addition, common update methods can ignore the strictly accurate historical labels of unchanged areas. To solve the above problem, we propose a new update algorithm to update the existing building database to the current state without manual relabeling. First, the difference between the data distributions of different time-phase images is reduced using the image color translation method. Then, a semantic segmentation model predicts the segmentation results of the images from the latest period, and, finally, a post-processing update strategy is applied to strictly retain the existing labels of unchanged regions to attain the updated results. We apply the proposed algorithm on the Wuhan University change detection dataset and the Beijing Huairou district land survey dataset to evaluate the effectiveness of the method in building surface and complex labeling scenarios in urban and suburban areas. The F1 scores of the updated results obtained for both datasets reach more than 96%, which proves the applicability of our proposed algorithm and its ability to efficiently and accurately extract building footprints in real-world scenarios. |
| first_indexed | 2024-03-09T18:01:56Z |
| format | Article |
| id | doaj.art-5445e694bbe44005a418ff6a3e3f281a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:01:56Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5445e694bbe44005a418ff6a3e3f281a2023-11-24T09:51:27ZengMDPI AGRemote Sensing2072-42922022-11-011422585110.3390/rs14225851Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building FootprintsZehui Wang0Yu Meng1Jingbo Chen2Junxian Ma3Anzhi Yue4Jiansheng Chen5Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaFor most cities, municipal governments have constructed basic building footprint datasets that need to be updated regularly for the management and monitoring of urban development and ecology. Cities are capable of changing in a short period of time, and the area of change is variable; hence, automated methods for generating up-to-date building footprints are urgently needed. However, the labels of current buildings or changed areas are usually lacking, and the conditions for acquiring images from different periods are not perfectly consistent, which can severely limit deep learning methods when attempting to learn deep information about buildings. In addition, common update methods can ignore the strictly accurate historical labels of unchanged areas. To solve the above problem, we propose a new update algorithm to update the existing building database to the current state without manual relabeling. First, the difference between the data distributions of different time-phase images is reduced using the image color translation method. Then, a semantic segmentation model predicts the segmentation results of the images from the latest period, and, finally, a post-processing update strategy is applied to strictly retain the existing labels of unchanged regions to attain the updated results. We apply the proposed algorithm on the Wuhan University change detection dataset and the Beijing Huairou district land survey dataset to evaluate the effectiveness of the method in building surface and complex labeling scenarios in urban and suburban areas. The F1 scores of the updated results obtained for both datasets reach more than 96%, which proves the applicability of our proposed algorithm and its ability to efficiently and accurately extract building footprints in real-world scenarios.https://www.mdpi.com/2072-4292/14/22/5851building updateimage color translationsemantic segmentation |
| spellingShingle | Zehui Wang Yu Meng Jingbo Chen Junxian Ma Anzhi Yue Jiansheng Chen Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building Footprints Remote Sensing building update image color translation semantic segmentation |
| title | Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building Footprints |
| title_full | Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building Footprints |
| title_fullStr | Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building Footprints |
| title_full_unstemmed | Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building Footprints |
| title_short | Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building Footprints |
| title_sort | learning color distributions from bitemporal remote sensing images to update existing building footprints |
| topic | building update image color translation semantic segmentation |
| url | https://www.mdpi.com/2072-4292/14/22/5851 |
| work_keys_str_mv | AT zehuiwang learningcolordistributionsfrombitemporalremotesensingimagestoupdateexistingbuildingfootprints AT yumeng learningcolordistributionsfrombitemporalremotesensingimagestoupdateexistingbuildingfootprints AT jingbochen learningcolordistributionsfrombitemporalremotesensingimagestoupdateexistingbuildingfootprints AT junxianma learningcolordistributionsfrombitemporalremotesensingimagestoupdateexistingbuildingfootprints AT anzhiyue learningcolordistributionsfrombitemporalremotesensingimagestoupdateexistingbuildingfootprints AT jianshengchen learningcolordistributionsfrombitemporalremotesensingimagestoupdateexistingbuildingfootprints |