RDAU-Net: A U-Shaped Semantic Segmentation Network for Buildings near Rivers and Lakes Based on a Fusion Approach
The encroachment of buildings into the waters of rivers and lakes can lead to increased safety hazards, but current semantic segmentation algorithms have difficulty accurately segmenting buildings in such environments. The specular reflection of the water and boats with similar features to the build...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549033024258048 |
|---|---|
| author | Yipeng Wang Dongmei Wang Teng Xu Yifan Shi Wenguang Liang Yihong Wang George P. Petropoulos Yansong Bao |
| author_facet | Yipeng Wang Dongmei Wang Teng Xu Yifan Shi Wenguang Liang Yihong Wang George P. Petropoulos Yansong Bao |
| author_sort | Yipeng Wang |
| collection | DOAJ |
| description | The encroachment of buildings into the waters of rivers and lakes can lead to increased safety hazards, but current semantic segmentation algorithms have difficulty accurately segmenting buildings in such environments. The specular reflection of the water and boats with similar features to the buildings in the environment can greatly affect the performance of the algorithm. Effectively eliminating their influence on the model and further improving the segmentation accuracy of buildings near water will be of great help to the management of river and lake waters. To address the above issues, the present study proposes the design of a U-shaped segmentation network of buildings called RDAU-Net that works through extraction and fuses a convolutional neural network and a transformer to segment buildings. First, we designed a residual dynamic short-cut down-sampling (RDSC) module to minimize the interference of complex building shapes and building scale differences on the segmentation results; second, we reduced the semantic and resolution gaps between multi-scale features using a multi-channel cross fusion transformer module (MCCT); finally, a double-feature channel-wise fusion attention (DCF) was designed to improve the model’s ability to depict building edge details and to reduce the influence of similar features on the model. Additionally, an HRI Building dataset was constructed, comprising water-edge buildings situated in a riverine and lacustrine regulatory context. This dataset encompasses a plethora of water-edge building sample scenarios, offering a comprehensive representation of the subject matter. The experimental results indicated that the statistical metrics achieved by RDAU-Net using the HRI and WHU Building datasets are better than those of others, and that it can effectively solve the building segmentation problems in the management of river and lake waters. |
| format | Article |
| id | doaj-art-e9346c15381d4560b1cdd9e12c23b2b9 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-e9346c15381d4560b1cdd9e12c23b2b92025-01-10T13:19:55ZengMDPI AGRemote Sensing2072-42922024-12-01171210.3390/rs17010002RDAU-Net: A U-Shaped Semantic Segmentation Network for Buildings near Rivers and Lakes Based on a Fusion ApproachYipeng Wang0Dongmei Wang1Teng Xu2Yifan Shi3Wenguang Liang4Yihong Wang5George P. Petropoulos6Yansong Bao7College of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing 210098, ChinaJiangsu Hydraulic Research Institute, Nanjing 210017, ChinaCollege of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing 210098, ChinaJiangsu Hydraulic Research Institute, Nanjing 210017, ChinaJiangsu Hydraulic Research Institute, Nanjing 210017, ChinaJiangsu Hydraulic Research Institute, Nanjing 210017, ChinaDepartment of Geography, Harokopio University of Athens, EI. Venizelou 70, 17671 Athens, GreeceSchool of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaThe encroachment of buildings into the waters of rivers and lakes can lead to increased safety hazards, but current semantic segmentation algorithms have difficulty accurately segmenting buildings in such environments. The specular reflection of the water and boats with similar features to the buildings in the environment can greatly affect the performance of the algorithm. Effectively eliminating their influence on the model and further improving the segmentation accuracy of buildings near water will be of great help to the management of river and lake waters. To address the above issues, the present study proposes the design of a U-shaped segmentation network of buildings called RDAU-Net that works through extraction and fuses a convolutional neural network and a transformer to segment buildings. First, we designed a residual dynamic short-cut down-sampling (RDSC) module to minimize the interference of complex building shapes and building scale differences on the segmentation results; second, we reduced the semantic and resolution gaps between multi-scale features using a multi-channel cross fusion transformer module (MCCT); finally, a double-feature channel-wise fusion attention (DCF) was designed to improve the model’s ability to depict building edge details and to reduce the influence of similar features on the model. Additionally, an HRI Building dataset was constructed, comprising water-edge buildings situated in a riverine and lacustrine regulatory context. This dataset encompasses a plethora of water-edge building sample scenarios, offering a comprehensive representation of the subject matter. The experimental results indicated that the statistical metrics achieved by RDAU-Net using the HRI and WHU Building datasets are better than those of others, and that it can effectively solve the building segmentation problems in the management of river and lake waters.https://www.mdpi.com/2072-4292/17/1/2semantic segmentationremote sensingbuildings extractionconvolutional neural networktransformerRDAU-Net |
| spellingShingle | Yipeng Wang Dongmei Wang Teng Xu Yifan Shi Wenguang Liang Yihong Wang George P. Petropoulos Yansong Bao RDAU-Net: A U-Shaped Semantic Segmentation Network for Buildings near Rivers and Lakes Based on a Fusion Approach Remote Sensing semantic segmentation remote sensing buildings extraction convolutional neural network transformer RDAU-Net |
| title | RDAU-Net: A U-Shaped Semantic Segmentation Network for Buildings near Rivers and Lakes Based on a Fusion Approach |
| title_full | RDAU-Net: A U-Shaped Semantic Segmentation Network for Buildings near Rivers and Lakes Based on a Fusion Approach |
| title_fullStr | RDAU-Net: A U-Shaped Semantic Segmentation Network for Buildings near Rivers and Lakes Based on a Fusion Approach |
| title_full_unstemmed | RDAU-Net: A U-Shaped Semantic Segmentation Network for Buildings near Rivers and Lakes Based on a Fusion Approach |
| title_short | RDAU-Net: A U-Shaped Semantic Segmentation Network for Buildings near Rivers and Lakes Based on a Fusion Approach |
| title_sort | rdau net a u shaped semantic segmentation network for buildings near rivers and lakes based on a fusion approach |
| topic | semantic segmentation remote sensing buildings extraction convolutional neural network transformer RDAU-Net |
| url | https://www.mdpi.com/2072-4292/17/1/2 |
| work_keys_str_mv | AT yipengwang rdaunetaushapedsemanticsegmentationnetworkforbuildingsnearriversandlakesbasedonafusionapproach AT dongmeiwang rdaunetaushapedsemanticsegmentationnetworkforbuildingsnearriversandlakesbasedonafusionapproach AT tengxu rdaunetaushapedsemanticsegmentationnetworkforbuildingsnearriversandlakesbasedonafusionapproach AT yifanshi rdaunetaushapedsemanticsegmentationnetworkforbuildingsnearriversandlakesbasedonafusionapproach AT wenguangliang rdaunetaushapedsemanticsegmentationnetworkforbuildingsnearriversandlakesbasedonafusionapproach AT yihongwang rdaunetaushapedsemanticsegmentationnetworkforbuildingsnearriversandlakesbasedonafusionapproach AT georgeppetropoulos rdaunetaushapedsemanticsegmentationnetworkforbuildingsnearriversandlakesbasedonafusionapproach AT yansongbao rdaunetaushapedsemanticsegmentationnetworkforbuildingsnearriversandlakesbasedonafusionapproach |