Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing Images
The technology of road extraction serves as a crucial foundation for urban intelligent renewal and green sustainable development. Its outcomes can optimize transportation network planning, reduce resource waste, and enhance urban resilience. Deep learning-based approaches have demonstrated outstandi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/13/3915 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849703704768282624 |
|---|---|
| author | Yu Jiang Jiasen Zhao Wei Luo Bincheng Guo Zhulin An Yongjun Xu |
| author_facet | Yu Jiang Jiasen Zhao Wei Luo Bincheng Guo Zhulin An Yongjun Xu |
| author_sort | Yu Jiang |
| collection | DOAJ |
| description | The technology of road extraction serves as a crucial foundation for urban intelligent renewal and green sustainable development. Its outcomes can optimize transportation network planning, reduce resource waste, and enhance urban resilience. Deep learning-based approaches have demonstrated outstanding performance in road extraction, particularly excelling in complex scenarios. However, extracting roads from remote sensing data remains challenging due to several factors that limit accuracy: (1) Roads often share similar visual features with the background, such as rooftops and parking lots, leading to ambiguous inter-class distinctions; (2) Roads in complex environments, such as those occluded by shadows or trees, are difficult to detect. To address these issues, this paper proposes an improved model based on Graph Convolutional Networks (GCNs), named FR-SGCN (Hierarchical Depth-wise Separable Graph Convolutional Network Incorporating Graph Reasoning and Attention Mechanisms). The model is designed to enhance the precision and robustness of road extraction through intelligent techniques, thereby supporting precise planning of green infrastructure. First, high-dimensional features are extracted using ResNeXt, whose grouped convolution structure balances parameter efficiency and feature representation capability, significantly enhancing the expressiveness of the data. These high-dimensional features are then segmented, and enhanced channel and spatial features are obtained via attention mechanisms, effectively mitigating background interference and intra-class ambiguity. Subsequently, a hybrid adjacency matrix construction method is proposed, based on gradient operators and graph reasoning. This method integrates similarity and gradient information and employs graph convolution to capture the global contextual relationships among features. To validate the effectiveness of FR-SGCN, we conducted comparative experiments using 12 different methods on both a self-built dataset and a public dataset. The proposed model achieved the highest F1 score on both datasets. Visualization results from the experiments demonstrate that the model effectively extracts occluded roads and reduces the risk of redundant construction caused by data errors during urban renewal. This provides reliable technical support for smart cities and sustainable development. |
| format | Article |
| id | doaj-art-7945f47b89504bb1beb99aa02cc307bd |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-7945f47b89504bb1beb99aa02cc307bd2025-08-20T03:17:08ZengMDPI AGSensors1424-82202025-06-012513391510.3390/s25133915Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing ImagesYu Jiang0Jiasen Zhao1Wei Luo2Bincheng Guo3Zhulin An4Yongjun Xu5Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaInstitute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaThe technology of road extraction serves as a crucial foundation for urban intelligent renewal and green sustainable development. Its outcomes can optimize transportation network planning, reduce resource waste, and enhance urban resilience. Deep learning-based approaches have demonstrated outstanding performance in road extraction, particularly excelling in complex scenarios. However, extracting roads from remote sensing data remains challenging due to several factors that limit accuracy: (1) Roads often share similar visual features with the background, such as rooftops and parking lots, leading to ambiguous inter-class distinctions; (2) Roads in complex environments, such as those occluded by shadows or trees, are difficult to detect. To address these issues, this paper proposes an improved model based on Graph Convolutional Networks (GCNs), named FR-SGCN (Hierarchical Depth-wise Separable Graph Convolutional Network Incorporating Graph Reasoning and Attention Mechanisms). The model is designed to enhance the precision and robustness of road extraction through intelligent techniques, thereby supporting precise planning of green infrastructure. First, high-dimensional features are extracted using ResNeXt, whose grouped convolution structure balances parameter efficiency and feature representation capability, significantly enhancing the expressiveness of the data. These high-dimensional features are then segmented, and enhanced channel and spatial features are obtained via attention mechanisms, effectively mitigating background interference and intra-class ambiguity. Subsequently, a hybrid adjacency matrix construction method is proposed, based on gradient operators and graph reasoning. This method integrates similarity and gradient information and employs graph convolution to capture the global contextual relationships among features. To validate the effectiveness of FR-SGCN, we conducted comparative experiments using 12 different methods on both a self-built dataset and a public dataset. The proposed model achieved the highest F1 score on both datasets. Visualization results from the experiments demonstrate that the model effectively extracts occluded roads and reduces the risk of redundant construction caused by data errors during urban renewal. This provides reliable technical support for smart cities and sustainable development.https://www.mdpi.com/1424-8220/25/13/3915depthwise separable convolutiongraph convolutionroad extractionsmart citiesgradient operatorgraph reasoning |
| spellingShingle | Yu Jiang Jiasen Zhao Wei Luo Bincheng Guo Zhulin An Yongjun Xu Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing Images Sensors depthwise separable convolution graph convolution road extraction smart cities gradient operator graph reasoning |
| title | Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing Images |
| title_full | Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing Images |
| title_fullStr | Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing Images |
| title_full_unstemmed | Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing Images |
| title_short | Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing Images |
| title_sort | utilizing gcn based deep learning for road extraction from remote sensing images |
| topic | depthwise separable convolution graph convolution road extraction smart cities gradient operator graph reasoning |
| url | https://www.mdpi.com/1424-8220/25/13/3915 |
| work_keys_str_mv | AT yujiang utilizinggcnbaseddeeplearningforroadextractionfromremotesensingimages AT jiasenzhao utilizinggcnbaseddeeplearningforroadextractionfromremotesensingimages AT weiluo utilizinggcnbaseddeeplearningforroadextractionfromremotesensingimages AT binchengguo utilizinggcnbaseddeeplearningforroadextractionfromremotesensingimages AT zhulinan utilizinggcnbaseddeeplearningforroadextractionfromremotesensingimages AT yongjunxu utilizinggcnbaseddeeplearningforroadextractionfromremotesensingimages |