Extracting Buildings from Remote Sensing Images Using a Multitask Encoder-Decoder Network with Boundary Refinement
Extracting buildings from high-resolution remote sensing images is essential for many geospatial applications, such as building change detection, urban planning, and disaster emergency assessment. Due to the diversity of geometric shapes and the blurring of boundaries among buildings, it is still a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/3/564 |
| _version_ | 1797485059511418880 |
|---|---|
| author | Hao Xu Panpan Zhu Xiaobo Luo Tianshou Xie Liqiang Zhang |
| author_facet | Hao Xu Panpan Zhu Xiaobo Luo Tianshou Xie Liqiang Zhang |
| author_sort | Hao Xu |
| collection | DOAJ |
| description | Extracting buildings from high-resolution remote sensing images is essential for many geospatial applications, such as building change detection, urban planning, and disaster emergency assessment. Due to the diversity of geometric shapes and the blurring of boundaries among buildings, it is still a challenging task to accurately generate building footprints from the complex scenes of remote sensing images. The rapid development of convolutional neural networks is presenting both new opportunities and challenges with respect to the extraction of buildings from high-resolution remote sensing images. To capture multilevel contextual information, most deep learning methods extract buildings by integrating multilevel features. However, the differential responses between such multilevel features are often ignored, leading to blurred contours in the extraction results. In this study, we propose an end-to-end multitask building extraction method to address these issues; this approach utilizes the rich contextual features of remote sensing images to assist with building segmentation while ensuring that the shape of the extraction results is preserved. By combining boundary classification and boundary distance regression, clear contour and distance transformation maps are generated to further improve the accuracy of building extraction. Subsequently, multiple refinement modules are used to refine each part of the network to minimize the loss of image feature information. Experimental comparisons conducted on the SpaceNet and Massachusetts building datasets show that the proposed method outperforms other deep learning methods in terms of building extraction results. |
| first_indexed | 2024-03-09T23:13:25Z |
| format | Article |
| id | doaj.art-20271b09ca86451a9ef65099b132dbe0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T23:13:25Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-20271b09ca86451a9ef65099b132dbe02023-11-23T17:39:46ZengMDPI AGRemote Sensing2072-42922022-01-0114356410.3390/rs14030564Extracting Buildings from Remote Sensing Images Using a Multitask Encoder-Decoder Network with Boundary RefinementHao Xu0Panpan Zhu1Xiaobo Luo2Tianshou Xie3Liqiang Zhang4College of Computer Sciences and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Computer Sciences and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Computer Sciences and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Computer Sciences and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaExtracting buildings from high-resolution remote sensing images is essential for many geospatial applications, such as building change detection, urban planning, and disaster emergency assessment. Due to the diversity of geometric shapes and the blurring of boundaries among buildings, it is still a challenging task to accurately generate building footprints from the complex scenes of remote sensing images. The rapid development of convolutional neural networks is presenting both new opportunities and challenges with respect to the extraction of buildings from high-resolution remote sensing images. To capture multilevel contextual information, most deep learning methods extract buildings by integrating multilevel features. However, the differential responses between such multilevel features are often ignored, leading to blurred contours in the extraction results. In this study, we propose an end-to-end multitask building extraction method to address these issues; this approach utilizes the rich contextual features of remote sensing images to assist with building segmentation while ensuring that the shape of the extraction results is preserved. By combining boundary classification and boundary distance regression, clear contour and distance transformation maps are generated to further improve the accuracy of building extraction. Subsequently, multiple refinement modules are used to refine each part of the network to minimize the loss of image feature information. Experimental comparisons conducted on the SpaceNet and Massachusetts building datasets show that the proposed method outperforms other deep learning methods in terms of building extraction results.https://www.mdpi.com/2072-4292/14/3/564building extractionremote sensingdeep learningmultitask methodboundary information |
| spellingShingle | Hao Xu Panpan Zhu Xiaobo Luo Tianshou Xie Liqiang Zhang Extracting Buildings from Remote Sensing Images Using a Multitask Encoder-Decoder Network with Boundary Refinement Remote Sensing building extraction remote sensing deep learning multitask method boundary information |
| title | Extracting Buildings from Remote Sensing Images Using a Multitask Encoder-Decoder Network with Boundary Refinement |
| title_full | Extracting Buildings from Remote Sensing Images Using a Multitask Encoder-Decoder Network with Boundary Refinement |
| title_fullStr | Extracting Buildings from Remote Sensing Images Using a Multitask Encoder-Decoder Network with Boundary Refinement |
| title_full_unstemmed | Extracting Buildings from Remote Sensing Images Using a Multitask Encoder-Decoder Network with Boundary Refinement |
| title_short | Extracting Buildings from Remote Sensing Images Using a Multitask Encoder-Decoder Network with Boundary Refinement |
| title_sort | extracting buildings from remote sensing images using a multitask encoder decoder network with boundary refinement |
| topic | building extraction remote sensing deep learning multitask method boundary information |
| url | https://www.mdpi.com/2072-4292/14/3/564 |
| work_keys_str_mv | AT haoxu extractingbuildingsfromremotesensingimagesusingamultitaskencoderdecodernetworkwithboundaryrefinement AT panpanzhu extractingbuildingsfromremotesensingimagesusingamultitaskencoderdecodernetworkwithboundaryrefinement AT xiaoboluo extractingbuildingsfromremotesensingimagesusingamultitaskencoderdecodernetworkwithboundaryrefinement AT tianshouxie extractingbuildingsfromremotesensingimagesusingamultitaskencoderdecodernetworkwithboundaryrefinement AT liqiangzhang extractingbuildingsfromremotesensingimagesusingamultitaskencoderdecodernetworkwithboundaryrefinement |