Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network
With the development of agricultural and rural modernization, the informatization of rural roads has been an inevitable requirement for promoting rural revitalization. To date, however, the vast majority of road extraction methods mainly focus on urban areas and rely on very high-resolution satellit...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/17/4193 |
| _version_ | 1797581917496803328 |
|---|---|
| author | Yuanxin Jia Xining Zhang Ru Xiang Yong Ge |
| author_facet | Yuanxin Jia Xining Zhang Ru Xiang Yong Ge |
| author_sort | Yuanxin Jia |
| collection | DOAJ |
| description | With the development of agricultural and rural modernization, the informatization of rural roads has been an inevitable requirement for promoting rural revitalization. To date, however, the vast majority of road extraction methods mainly focus on urban areas and rely on very high-resolution satellite or aerial images, whose costs are not yet affordable for large-scale rural areas. Therefore, a deep learning (DL)-based super-resolution mapping (SRM) method has been considered to relieve this dilemma by using freely available Sentinel-2 imagery. However, few DL-based SRM methods are suitable due to these methods only relying on the spectral features derived from remote sensing images, which is insufficient for the complex rural road extraction task. To solve this problem, this paper proposes a spatial relationship-informed super-resolution mapping network (SRSNet) for extracting roads in rural areas which aims to generate 2.5 m fine-scale rural road maps from 10 m Sentinel-2 images. Based on the common sense that rural roads often lead to rural settlements, the method adopts a feature enhancement module to enhance the capture of road features by incorporating the relative position relation between roads and rural settlements into the model. Experimental results show that the SRSNet can effectively extract road information, with significantly better results for elongated rural roads. The intersection over union (IoU) of the mapping results is 68.9%, which is 4.7% higher than that of the method without fusing settlement features. The extracted roads show more details in the areas with strong spatial relationships between the settlements and roads. |
| first_indexed | 2024-03-10T23:14:27Z |
| format | Article |
| id | doaj.art-7e5991d1fc3f42d9ac6dd030a76f7d10 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:14:27Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7e5991d1fc3f42d9ac6dd030a76f7d102023-11-19T08:45:44ZengMDPI AGRemote Sensing2072-42922023-08-011517419310.3390/rs15174193Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed NetworkYuanxin Jia0Xining Zhang1Ru Xiang2Yong Ge3Academy of Forest Inventory and Planning, National Forestry and Grassland Administration, Beijing 100714, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaWith the development of agricultural and rural modernization, the informatization of rural roads has been an inevitable requirement for promoting rural revitalization. To date, however, the vast majority of road extraction methods mainly focus on urban areas and rely on very high-resolution satellite or aerial images, whose costs are not yet affordable for large-scale rural areas. Therefore, a deep learning (DL)-based super-resolution mapping (SRM) method has been considered to relieve this dilemma by using freely available Sentinel-2 imagery. However, few DL-based SRM methods are suitable due to these methods only relying on the spectral features derived from remote sensing images, which is insufficient for the complex rural road extraction task. To solve this problem, this paper proposes a spatial relationship-informed super-resolution mapping network (SRSNet) for extracting roads in rural areas which aims to generate 2.5 m fine-scale rural road maps from 10 m Sentinel-2 images. Based on the common sense that rural roads often lead to rural settlements, the method adopts a feature enhancement module to enhance the capture of road features by incorporating the relative position relation between roads and rural settlements into the model. Experimental results show that the SRSNet can effectively extract road information, with significantly better results for elongated rural roads. The intersection over union (IoU) of the mapping results is 68.9%, which is 4.7% higher than that of the method without fusing settlement features. The extracted roads show more details in the areas with strong spatial relationships between the settlements and roads.https://www.mdpi.com/2072-4292/15/17/4193spatial relationshipdeep learningsuper-resolution mappingrural road extractionfeature enhancement |
| spellingShingle | Yuanxin Jia Xining Zhang Ru Xiang Yong Ge Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network Remote Sensing spatial relationship deep learning super-resolution mapping rural road extraction feature enhancement |
| title | Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network |
| title_full | Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network |
| title_fullStr | Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network |
| title_full_unstemmed | Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network |
| title_short | Super-Resolution Rural Road Extraction from Sentinel-2 Imagery Using a Spatial Relationship-Informed Network |
| title_sort | super resolution rural road extraction from sentinel 2 imagery using a spatial relationship informed network |
| topic | spatial relationship deep learning super-resolution mapping rural road extraction feature enhancement |
| url | https://www.mdpi.com/2072-4292/15/17/4193 |
| work_keys_str_mv | AT yuanxinjia superresolutionruralroadextractionfromsentinel2imageryusingaspatialrelationshipinformednetwork AT xiningzhang superresolutionruralroadextractionfromsentinel2imageryusingaspatialrelationshipinformednetwork AT ruxiang superresolutionruralroadextractionfromsentinel2imageryusingaspatialrelationshipinformednetwork AT yongge superresolutionruralroadextractionfromsentinel2imageryusingaspatialrelationshipinformednetwork |