Deep-Separation Guided Progressive Reconstruction Network for Semantic Segmentation of Remote Sensing Images
The success of deep learning and the segmentation of remote sensing images (RSIs) has improved semantic segmentation in recent years. However, existing RSI segmentation methods have two inherent problems: (1) detecting objects of various scales in RSIs of complex scenes is challenging, and (2) featu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/21/5510 |
| _version_ | 1827645571757768704 |
|---|---|
| author | Jiabao Ma Wujie Zhou Xiaohong Qian Lu Yu |
| author_facet | Jiabao Ma Wujie Zhou Xiaohong Qian Lu Yu |
| author_sort | Jiabao Ma |
| collection | DOAJ |
| description | The success of deep learning and the segmentation of remote sensing images (RSIs) has improved semantic segmentation in recent years. However, existing RSI segmentation methods have two inherent problems: (1) detecting objects of various scales in RSIs of complex scenes is challenging, and (2) feature reconstruction for accurate segmentation is difficult. To solve these problems, we propose a deep-separation-guided progressive reconstruction network that achieves accurate RSI segmentation. First, we design a decoder comprising progressive reconstruction blocks capturing detailed features at various resolutions through multi-scale features obtained from various receptive fields to preserve accuracy during reconstruction. Subsequently, we propose a deep separation module that distinguishes various classes based on semantic features to use deep features to detect objects of different scales. Moreover, adjacent middle features are complemented during decoding to improve the segmentation performance. Extensive experimental results on two optical RSI datasets show that the proposed network outperforms 11 state-of-the-art methods. |
| first_indexed | 2024-03-09T18:42:01Z |
| format | Article |
| id | doaj.art-671a7150331d4bcd8739069b82ffc2da |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:42:01Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-671a7150331d4bcd8739069b82ffc2da2023-11-24T06:40:11ZengMDPI AGRemote Sensing2072-42922022-11-011421551010.3390/rs14215510Deep-Separation Guided Progressive Reconstruction Network for Semantic Segmentation of Remote Sensing ImagesJiabao Ma0Wujie Zhou1Xiaohong Qian2Lu Yu3School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaCollege of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, ChinaThe success of deep learning and the segmentation of remote sensing images (RSIs) has improved semantic segmentation in recent years. However, existing RSI segmentation methods have two inherent problems: (1) detecting objects of various scales in RSIs of complex scenes is challenging, and (2) feature reconstruction for accurate segmentation is difficult. To solve these problems, we propose a deep-separation-guided progressive reconstruction network that achieves accurate RSI segmentation. First, we design a decoder comprising progressive reconstruction blocks capturing detailed features at various resolutions through multi-scale features obtained from various receptive fields to preserve accuracy during reconstruction. Subsequently, we propose a deep separation module that distinguishes various classes based on semantic features to use deep features to detect objects of different scales. Moreover, adjacent middle features are complemented during decoding to improve the segmentation performance. Extensive experimental results on two optical RSI datasets show that the proposed network outperforms 11 state-of-the-art methods.https://www.mdpi.com/2072-4292/14/21/5510digital surface modelmultimodalmulti-scale supervisionfeature separationreconstruction refinement |
| spellingShingle | Jiabao Ma Wujie Zhou Xiaohong Qian Lu Yu Deep-Separation Guided Progressive Reconstruction Network for Semantic Segmentation of Remote Sensing Images Remote Sensing digital surface model multimodal multi-scale supervision feature separation reconstruction refinement |
| title | Deep-Separation Guided Progressive Reconstruction Network for Semantic Segmentation of Remote Sensing Images |
| title_full | Deep-Separation Guided Progressive Reconstruction Network for Semantic Segmentation of Remote Sensing Images |
| title_fullStr | Deep-Separation Guided Progressive Reconstruction Network for Semantic Segmentation of Remote Sensing Images |
| title_full_unstemmed | Deep-Separation Guided Progressive Reconstruction Network for Semantic Segmentation of Remote Sensing Images |
| title_short | Deep-Separation Guided Progressive Reconstruction Network for Semantic Segmentation of Remote Sensing Images |
| title_sort | deep separation guided progressive reconstruction network for semantic segmentation of remote sensing images |
| topic | digital surface model multimodal multi-scale supervision feature separation reconstruction refinement |
| url | https://www.mdpi.com/2072-4292/14/21/5510 |
| work_keys_str_mv | AT jiabaoma deepseparationguidedprogressivereconstructionnetworkforsemanticsegmentationofremotesensingimages AT wujiezhou deepseparationguidedprogressivereconstructionnetworkforsemanticsegmentationofremotesensingimages AT xiaohongqian deepseparationguidedprogressivereconstructionnetworkforsemanticsegmentationofremotesensingimages AT luyu deepseparationguidedprogressivereconstructionnetworkforsemanticsegmentationofremotesensingimages |