Feature-Enhanced Deep Learning Network for Digital Elevation Model Super-Resolution
The high-resolution digital elevation model (HR DEM) plays an important role in hydrological analysis, cartographic generalization, and national security. As the main high-precision DEM data supplementary method, DEM super-resolution (DEM SR) based on deep learning has been widely studied. However,...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10158772/ |
| _version_ | 1797330419231752192 |
|---|---|
| author | Xiaochuan Ma Houpu Li Zhanlong Chen |
| author_facet | Xiaochuan Ma Houpu Li Zhanlong Chen |
| author_sort | Xiaochuan Ma |
| collection | DOAJ |
| description | The high-resolution digital elevation model (HR DEM) plays an important role in hydrological analysis, cartographic generalization, and national security. As the main high-precision DEM data supplementary method, DEM super-resolution (DEM SR) based on deep learning has been widely studied. However, its accuracy has fallen into a bottleneck at present, which is more prominent in complex regions. The reason for this issue is that the existing methods are difficult to capture enough local features from the low-resolution input data, and a part of the global information (contour information of long-distance features, such as rivers and ridges) will also be lost in the network transmission process. To resolve this issue, a novel feature-enhanced deep learning network (FEN) is designed in this article. The proposed FEN includes a global feature SR (GFSR) module and a local feature SR (LFSR) module. The former provides global information by using an interpolation method (Kriging), including geographical laws (spatial autocorrelation). The latter fully captures the features in the input data by integrating powerful feature extraction modules and then provides sufficient local features for DEM SR tasks. Thus, DEM SR tasks for complex regions can be realized by integrating the results of GFSR and LFSR modules. Extensive experiments show that FEN achieves state-of-the-art performance in DEM SR tasks facing complex regions. Specifically, compared with the existing DEM SR method (TfaSR, SRResNet, Bicubic, SRCNN, and Kriging), the result by FEN is closer to HR DEM and can retain more local DEM features. Meanwhile, the FEN is more than 20% ahead of other DEM SR methods based on deep learning in elevation accuracy. |
| first_indexed | 2024-03-08T07:19:35Z |
| format | Article |
| id | doaj.art-a5b2776e3718440ea67de26d8023ec22 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-08T07:19:35Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-a5b2776e3718440ea67de26d8023ec222024-02-03T00:01:01ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01165670568510.1109/JSTARS.2023.328829610158772Feature-Enhanced Deep Learning Network for Digital Elevation Model Super-ResolutionXiaochuan Ma0Houpu Li1https://orcid.org/0000-0002-0560-6656Zhanlong Chen2https://orcid.org/0000-0001-6373-3162School of Geography and Information Engineering, China University of Geosciences, Wuhan, ChinaControl Engineering Laboratory, Naval University of Engineering, Wuhan, ChinaSchool of Computer Science, China University of Geosciences, Wuhan, ChinaThe high-resolution digital elevation model (HR DEM) plays an important role in hydrological analysis, cartographic generalization, and national security. As the main high-precision DEM data supplementary method, DEM super-resolution (DEM SR) based on deep learning has been widely studied. However, its accuracy has fallen into a bottleneck at present, which is more prominent in complex regions. The reason for this issue is that the existing methods are difficult to capture enough local features from the low-resolution input data, and a part of the global information (contour information of long-distance features, such as rivers and ridges) will also be lost in the network transmission process. To resolve this issue, a novel feature-enhanced deep learning network (FEN) is designed in this article. The proposed FEN includes a global feature SR (GFSR) module and a local feature SR (LFSR) module. The former provides global information by using an interpolation method (Kriging), including geographical laws (spatial autocorrelation). The latter fully captures the features in the input data by integrating powerful feature extraction modules and then provides sufficient local features for DEM SR tasks. Thus, DEM SR tasks for complex regions can be realized by integrating the results of GFSR and LFSR modules. Extensive experiments show that FEN achieves state-of-the-art performance in DEM SR tasks facing complex regions. Specifically, compared with the existing DEM SR method (TfaSR, SRResNet, Bicubic, SRCNN, and Kriging), the result by FEN is closer to HR DEM and can retain more local DEM features. Meanwhile, the FEN is more than 20% ahead of other DEM SR methods based on deep learning in elevation accuracy.https://ieeexplore.ieee.org/document/10158772/Deformable convolution (Dconv)digital elevation model (DEM) super-resolution (DEM SR)KrigingResNet |
| spellingShingle | Xiaochuan Ma Houpu Li Zhanlong Chen Feature-Enhanced Deep Learning Network for Digital Elevation Model Super-Resolution IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deformable convolution (Dconv) digital elevation model (DEM) super-resolution (DEM SR) Kriging ResNet |
| title | Feature-Enhanced Deep Learning Network for Digital Elevation Model Super-Resolution |
| title_full | Feature-Enhanced Deep Learning Network for Digital Elevation Model Super-Resolution |
| title_fullStr | Feature-Enhanced Deep Learning Network for Digital Elevation Model Super-Resolution |
| title_full_unstemmed | Feature-Enhanced Deep Learning Network for Digital Elevation Model Super-Resolution |
| title_short | Feature-Enhanced Deep Learning Network for Digital Elevation Model Super-Resolution |
| title_sort | feature enhanced deep learning network for digital elevation model super resolution |
| topic | Deformable convolution (Dconv) digital elevation model (DEM) super-resolution (DEM SR) Kriging ResNet |
| url | https://ieeexplore.ieee.org/document/10158772/ |
| work_keys_str_mv | AT xiaochuanma featureenhanceddeeplearningnetworkfordigitalelevationmodelsuperresolution AT houpuli featureenhanceddeeplearningnetworkfordigitalelevationmodelsuperresolution AT zhanlongchen featureenhanceddeeplearningnetworkfordigitalelevationmodelsuperresolution |