SDSNet: Building Extraction in High-Resolution Remote Sensing Images Using a Deep Convolutional Network with Cross-Layer Feature Information Interaction Filtering
Building extraction refers to the automatic identification and separation of buildings from the background in remote sensing images. It plays a significant role in urban planning, land management, and disaster monitoring. Deep-learning methods have shown advantages in building extraction, but they s...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/1/169 |
| _version_ | 1797358218909843456 |
|---|---|
| author | Xudong Wang Mingliang Tian Zhijun Zhang Kang He Sheng Wang Yan Liu Yusen Dong |
| author_facet | Xudong Wang Mingliang Tian Zhijun Zhang Kang He Sheng Wang Yan Liu Yusen Dong |
| author_sort | Xudong Wang |
| collection | DOAJ |
| description | Building extraction refers to the automatic identification and separation of buildings from the background in remote sensing images. It plays a significant role in urban planning, land management, and disaster monitoring. Deep-learning methods have shown advantages in building extraction, but they still face challenges such as variations in building types, object occlusions, and complex backgrounds. To address these issues, SDSNet, a deep convolutional network that incorporates global multi-scale feature extraction and cross-level feature fusion, is proposed. SDSNet consists of three modules: semantic information extraction (SIE), multi-level merge (MLM), and semantic information fusion (SIF). The SIE module extracts contextual information and improves recognition of multi-scale buildings. The MLM module filters irrelevant details guided by high-level semantic information, aiding in the restoration of edge details for buildings. The SIF module combines filtered detail information with extracted semantic information for refined building extraction. A series of experiments conducted on two distinct public datasets for building extraction consistently demonstrate that SDSNet outperforms the state-of-the-art deep-learning models for building extraction tasks. On the WHU building dataset, the overall accuracy (OA) and intersection over union (IoU) achieved impressive scores of 98.86% and 90.17%, respectively. Meanwhile, on the Massachusetts dataset, SDSNet achieved OA and IoU scores of 94.05% and 71.6%, respectively. SDSNet exhibits a unique advantage in recovering fine details along building edges, enabling automated and intelligent building extraction. This capability effectively supports urban planning, resource management, and disaster monitoring. |
| first_indexed | 2024-03-08T14:58:42Z |
| format | Article |
| id | doaj.art-c334f059491d45ba8a7c34b5aa68d2ea |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T14:58:42Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c334f059491d45ba8a7c34b5aa68d2ea2024-01-10T15:07:46ZengMDPI AGRemote Sensing2072-42922023-12-0116116910.3390/rs16010169SDSNet: Building Extraction in High-Resolution Remote Sensing Images Using a Deep Convolutional Network with Cross-Layer Feature Information Interaction FilteringXudong Wang0Mingliang Tian1Zhijun Zhang2Kang He3Sheng Wang4Yan Liu5Yusen Dong6School of Computer Science, China University of Geosciences, Wuhan 430078, ChinaSchool of Computer Science, China University of Geosciences, Wuhan 430078, ChinaHubei Key Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan 430078, ChinaHubei Key Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan 430078, ChinaSchool of Computer Science, China University of Geosciences, Wuhan 430078, ChinaState Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, Wuhan 430078, ChinaSchool of Computer Science, China University of Geosciences, Wuhan 430078, ChinaBuilding extraction refers to the automatic identification and separation of buildings from the background in remote sensing images. It plays a significant role in urban planning, land management, and disaster monitoring. Deep-learning methods have shown advantages in building extraction, but they still face challenges such as variations in building types, object occlusions, and complex backgrounds. To address these issues, SDSNet, a deep convolutional network that incorporates global multi-scale feature extraction and cross-level feature fusion, is proposed. SDSNet consists of three modules: semantic information extraction (SIE), multi-level merge (MLM), and semantic information fusion (SIF). The SIE module extracts contextual information and improves recognition of multi-scale buildings. The MLM module filters irrelevant details guided by high-level semantic information, aiding in the restoration of edge details for buildings. The SIF module combines filtered detail information with extracted semantic information for refined building extraction. A series of experiments conducted on two distinct public datasets for building extraction consistently demonstrate that SDSNet outperforms the state-of-the-art deep-learning models for building extraction tasks. On the WHU building dataset, the overall accuracy (OA) and intersection over union (IoU) achieved impressive scores of 98.86% and 90.17%, respectively. Meanwhile, on the Massachusetts dataset, SDSNet achieved OA and IoU scores of 94.05% and 71.6%, respectively. SDSNet exhibits a unique advantage in recovering fine details along building edges, enabling automated and intelligent building extraction. This capability effectively supports urban planning, resource management, and disaster monitoring.https://www.mdpi.com/2072-4292/16/1/169high resolutionbuilding extractionremote sensing imagessemantic segmentationconvolutional network framework |
| spellingShingle | Xudong Wang Mingliang Tian Zhijun Zhang Kang He Sheng Wang Yan Liu Yusen Dong SDSNet: Building Extraction in High-Resolution Remote Sensing Images Using a Deep Convolutional Network with Cross-Layer Feature Information Interaction Filtering Remote Sensing high resolution building extraction remote sensing images semantic segmentation convolutional network framework |
| title | SDSNet: Building Extraction in High-Resolution Remote Sensing Images Using a Deep Convolutional Network with Cross-Layer Feature Information Interaction Filtering |
| title_full | SDSNet: Building Extraction in High-Resolution Remote Sensing Images Using a Deep Convolutional Network with Cross-Layer Feature Information Interaction Filtering |
| title_fullStr | SDSNet: Building Extraction in High-Resolution Remote Sensing Images Using a Deep Convolutional Network with Cross-Layer Feature Information Interaction Filtering |
| title_full_unstemmed | SDSNet: Building Extraction in High-Resolution Remote Sensing Images Using a Deep Convolutional Network with Cross-Layer Feature Information Interaction Filtering |
| title_short | SDSNet: Building Extraction in High-Resolution Remote Sensing Images Using a Deep Convolutional Network with Cross-Layer Feature Information Interaction Filtering |
| title_sort | sdsnet building extraction in high resolution remote sensing images using a deep convolutional network with cross layer feature information interaction filtering |
| topic | high resolution building extraction remote sensing images semantic segmentation convolutional network framework |
| url | https://www.mdpi.com/2072-4292/16/1/169 |
| work_keys_str_mv | AT xudongwang sdsnetbuildingextractioninhighresolutionremotesensingimagesusingadeepconvolutionalnetworkwithcrosslayerfeatureinformationinteractionfiltering AT mingliangtian sdsnetbuildingextractioninhighresolutionremotesensingimagesusingadeepconvolutionalnetworkwithcrosslayerfeatureinformationinteractionfiltering AT zhijunzhang sdsnetbuildingextractioninhighresolutionremotesensingimagesusingadeepconvolutionalnetworkwithcrosslayerfeatureinformationinteractionfiltering AT kanghe sdsnetbuildingextractioninhighresolutionremotesensingimagesusingadeepconvolutionalnetworkwithcrosslayerfeatureinformationinteractionfiltering AT shengwang sdsnetbuildingextractioninhighresolutionremotesensingimagesusingadeepconvolutionalnetworkwithcrosslayerfeatureinformationinteractionfiltering AT yanliu sdsnetbuildingextractioninhighresolutionremotesensingimagesusingadeepconvolutionalnetworkwithcrosslayerfeatureinformationinteractionfiltering AT yusendong sdsnetbuildingextractioninhighresolutionremotesensingimagesusingadeepconvolutionalnetworkwithcrosslayerfeatureinformationinteractionfiltering |