Boundary-Aware Dual-Stream Network for VHR Remote Sensing Images Semantic Segmentation
Semantic segmentation for very-high-resolution remote sensing images has been a research hotspot in the field of remote sensing image analysis. However, most existing methods still suffer from a challenge that object boundaries cannot be finely recovered. To tackle the problem, we develop a dual-str...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9416898/ |
| _version_ | 1828144734517854208 |
|---|---|
| author | Zhixian Nong Xin Su Yi Liu Zongqian Zhan Qiangqiang Yuan |
| author_facet | Zhixian Nong Xin Su Yi Liu Zongqian Zhan Qiangqiang Yuan |
| author_sort | Zhixian Nong |
| collection | DOAJ |
| description | Semantic segmentation for very-high-resolution remote sensing images has been a research hotspot in the field of remote sensing image analysis. However, most existing methods still suffer from a challenge that object boundaries cannot be finely recovered. To tackle the problem, we develop a dual-stream network based on the U-Net architecture, Instead of the traditional skip connections, a boundary attention module is proposed to introduce the boundary information from the EDN module to the SSN module. Experiments on ISPRS Potsdam and Vaihingen datasets show the effectiveness of the proposed network, especially in man-made objects with distinct boundaries. |
| first_indexed | 2024-04-11T20:21:12Z |
| format | Article |
| id | doaj.art-3be78066b0f94789b2d183c8f3bf7afa |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-11T20:21:12Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-3be78066b0f94789b2d183c8f3bf7afa2022-12-22T04:04:48ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01145260526810.1109/JSTARS.2021.30760359416898Boundary-Aware Dual-Stream Network for VHR Remote Sensing Images Semantic SegmentationZhixian Nong0Xin Su1https://orcid.org/0000-0003-0957-4628Yi Liu2Zongqian Zhan3Qiangqiang Yuan4School of Geodesy and Geomatics, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan, ChinaSemantic segmentation for very-high-resolution remote sensing images has been a research hotspot in the field of remote sensing image analysis. However, most existing methods still suffer from a challenge that object boundaries cannot be finely recovered. To tackle the problem, we develop a dual-stream network based on the U-Net architecture, Instead of the traditional skip connections, a boundary attention module is proposed to introduce the boundary information from the EDN module to the SSN module. Experiments on ISPRS Potsdam and Vaihingen datasets show the effectiveness of the proposed network, especially in man-made objects with distinct boundaries.https://ieeexplore.ieee.org/document/9416898/Attention moduleedge detection subnetworksemantic segmentationvery high spatial resolution |
| spellingShingle | Zhixian Nong Xin Su Yi Liu Zongqian Zhan Qiangqiang Yuan Boundary-Aware Dual-Stream Network for VHR Remote Sensing Images Semantic Segmentation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention module edge detection subnetwork semantic segmentation very high spatial resolution |
| title | Boundary-Aware Dual-Stream Network for VHR Remote Sensing Images Semantic Segmentation |
| title_full | Boundary-Aware Dual-Stream Network for VHR Remote Sensing Images Semantic Segmentation |
| title_fullStr | Boundary-Aware Dual-Stream Network for VHR Remote Sensing Images Semantic Segmentation |
| title_full_unstemmed | Boundary-Aware Dual-Stream Network for VHR Remote Sensing Images Semantic Segmentation |
| title_short | Boundary-Aware Dual-Stream Network for VHR Remote Sensing Images Semantic Segmentation |
| title_sort | boundary aware dual stream network for vhr remote sensing images semantic segmentation |
| topic | Attention module edge detection subnetwork semantic segmentation very high spatial resolution |
| url | https://ieeexplore.ieee.org/document/9416898/ |
| work_keys_str_mv | AT zhixiannong boundaryawaredualstreamnetworkforvhrremotesensingimagessemanticsegmentation AT xinsu boundaryawaredualstreamnetworkforvhrremotesensingimagessemanticsegmentation AT yiliu boundaryawaredualstreamnetworkforvhrremotesensingimagessemanticsegmentation AT zongqianzhan boundaryawaredualstreamnetworkforvhrremotesensingimagessemanticsegmentation AT qiangqiangyuan boundaryawaredualstreamnetworkforvhrremotesensingimagessemanticsegmentation |