Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images
The segmentation algorithm for buildings and waters is extremely important for the efficient planning and utilization of land resources. The temporal and space range of remote sensing pictures is growing. Due to the generic convolutional neural network’s (CNN) insensitivity to the spatial position i...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/6/1536 |
_version_ | 1797609234152554496 |
---|---|
author | Jing Chen Min Xia Dehao Wang Haifeng Lin |
author_facet | Jing Chen Min Xia Dehao Wang Haifeng Lin |
author_sort | Jing Chen |
collection | DOAJ |
description | The segmentation algorithm for buildings and waters is extremely important for the efficient planning and utilization of land resources. The temporal and space range of remote sensing pictures is growing. Due to the generic convolutional neural network’s (CNN) insensitivity to the spatial position information in remote sensing images, certain location and edge details can be lost, leading to a low level of segmentation accuracy. This research suggests a double-branch parallel interactive network to address these issues, fully using the interactivity of global information in a Swin Transformer network, and integrating CNN to capture deeper information. Then, by building a cross-scale multi-level fusion module, the model can combine features gathered using convolutional neural networks with features derived using Swin Transformer, successfully extracting the semantic information of spatial information and context. Then, an up-sampling module for multi-scale fusion is suggested. It employs the output high-level feature information to direct the low-level feature information and recover the high-resolution pixel-level features. According to experimental results, the proposed networks maximizes the benefits of the two models and increases the precision of semantic segmentation of buildings and waters. |
first_indexed | 2024-03-11T05:58:39Z |
format | Article |
id | doaj.art-d13780164b94438d84f26b7c675a37f5 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-11T05:58:39Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-d13780164b94438d84f26b7c675a37f52023-11-17T13:38:29ZengMDPI AGRemote Sensing2072-42922023-03-01156153610.3390/rs15061536Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing ImagesJing Chen0Min Xia1Dehao Wang2Haifeng Lin3Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, B-DAT, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollaborative Innovation Center on Atmospheric Environment and Equipment Technology, B-DAT, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollaborative Innovation Center on Atmospheric Environment and Equipment Technology, B-DAT, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollege of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaThe segmentation algorithm for buildings and waters is extremely important for the efficient planning and utilization of land resources. The temporal and space range of remote sensing pictures is growing. Due to the generic convolutional neural network’s (CNN) insensitivity to the spatial position information in remote sensing images, certain location and edge details can be lost, leading to a low level of segmentation accuracy. This research suggests a double-branch parallel interactive network to address these issues, fully using the interactivity of global information in a Swin Transformer network, and integrating CNN to capture deeper information. Then, by building a cross-scale multi-level fusion module, the model can combine features gathered using convolutional neural networks with features derived using Swin Transformer, successfully extracting the semantic information of spatial information and context. Then, an up-sampling module for multi-scale fusion is suggested. It employs the output high-level feature information to direct the low-level feature information and recover the high-resolution pixel-level features. According to experimental results, the proposed networks maximizes the benefits of the two models and increases the precision of semantic segmentation of buildings and waters.https://www.mdpi.com/2072-4292/15/6/1536double branchCNNsemantic segmentationbuildings and watersdeep learning |
spellingShingle | Jing Chen Min Xia Dehao Wang Haifeng Lin Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images Remote Sensing double branch CNN semantic segmentation buildings and waters deep learning |
title | Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images |
title_full | Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images |
title_fullStr | Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images |
title_full_unstemmed | Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images |
title_short | Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images |
title_sort | double branch parallel network for segmentation of buildings and waters in remote sensing images |
topic | double branch CNN semantic segmentation buildings and waters deep learning |
url | https://www.mdpi.com/2072-4292/15/6/1536 |
work_keys_str_mv | AT jingchen doublebranchparallelnetworkforsegmentationofbuildingsandwatersinremotesensingimages AT minxia doublebranchparallelnetworkforsegmentationofbuildingsandwatersinremotesensingimages AT dehaowang doublebranchparallelnetworkforsegmentationofbuildingsandwatersinremotesensingimages AT haifenglin doublebranchparallelnetworkforsegmentationofbuildingsandwatersinremotesensingimages |