SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network
To address key issues with traditional landform classification methods that impact the integrity and continuity of the analysis area, as well as neglecting neighboring features, We presents a novel approach called superpixel-based graph convolutional network (SGCN) for automatic classification of di...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-08-01
|
Series: | International Journal of Applied Earth Observations and Geoinformation |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223002650 |
_version_ | 1797737994100146176 |
---|---|
author | Honghao Fu Yilang Shen Yuxuan Liu Jingzhong Li Xiang Zhang |
author_facet | Honghao Fu Yilang Shen Yuxuan Liu Jingzhong Li Xiang Zhang |
author_sort | Honghao Fu |
collection | DOAJ |
description | To address key issues with traditional landform classification methods that impact the integrity and continuity of the analysis area, as well as neglecting neighboring features, We presents a novel approach called superpixel-based graph convolutional network (SGCN) for automatic classification of digital elevation model (DEM) landform. The SGCN uses superpixel segmentation and graph convolutional networks (GCNs). Specifically, we employ the Simple Linear Iterative Clustering (SLIC) algorithm to perform superpixel segmentation on the DEM image and convert the resulting distribution of superpixels in the 2D image into a graph structure, where nodes are labeled. We then analyze the geographic features and external neighborhood relationships within each DEM superpixel to obtain corresponding node information for the graph structure. Finally, the GCN model is trained according to the graph structure, node feature information, and node label, enabling automatic recognition of node landform types. Importantly, SGCN accounts for the multi-order neighborhood features of the basic analysis unit and expresses the DEM micro-features relatively macroscopically. Experimental results demonstrate that compared with pixel-level semantic segmentation methods like U-Net, FCN, and SegNet, the SGCN significantly improves DEM landform classification accuracy by 17.84%, 33.22%, and 30.60%, respectively. Moreover, SGCN better preserves the integrity and continuity of features inside and outside the analysis area, overcoming the limitation of traditional methods that use regular grids as the basic analysis unit, which can compromise landform edge continuity. |
first_indexed | 2024-03-12T13:37:30Z |
format | Article |
id | doaj.art-904b2ce16a2143f181704b848e979f39 |
institution | Directory Open Access Journal |
issn | 1569-8432 |
language | English |
last_indexed | 2024-03-12T13:37:30Z |
publishDate | 2023-08-01 |
publisher | Elsevier |
record_format | Article |
series | International Journal of Applied Earth Observations and Geoinformation |
spelling | doaj.art-904b2ce16a2143f181704b848e979f392023-08-24T04:34:20ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-08-01122103441SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional networkHonghao Fu0Yilang Shen1Yuxuan Liu2Jingzhong Li3Xiang Zhang4School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai 519082, China; School of Instrument Science and Engineering, Southeast University, Nanjing 211189, ChinaSchool of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai 519082, China; Corresponding author.School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Resource and Environment Sciences, Wuhan University, Wuhan 430079, ChinaSchool of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai 519082, ChinaTo address key issues with traditional landform classification methods that impact the integrity and continuity of the analysis area, as well as neglecting neighboring features, We presents a novel approach called superpixel-based graph convolutional network (SGCN) for automatic classification of digital elevation model (DEM) landform. The SGCN uses superpixel segmentation and graph convolutional networks (GCNs). Specifically, we employ the Simple Linear Iterative Clustering (SLIC) algorithm to perform superpixel segmentation on the DEM image and convert the resulting distribution of superpixels in the 2D image into a graph structure, where nodes are labeled. We then analyze the geographic features and external neighborhood relationships within each DEM superpixel to obtain corresponding node information for the graph structure. Finally, the GCN model is trained according to the graph structure, node feature information, and node label, enabling automatic recognition of node landform types. Importantly, SGCN accounts for the multi-order neighborhood features of the basic analysis unit and expresses the DEM micro-features relatively macroscopically. Experimental results demonstrate that compared with pixel-level semantic segmentation methods like U-Net, FCN, and SegNet, the SGCN significantly improves DEM landform classification accuracy by 17.84%, 33.22%, and 30.60%, respectively. Moreover, SGCN better preserves the integrity and continuity of features inside and outside the analysis area, overcoming the limitation of traditional methods that use regular grids as the basic analysis unit, which can compromise landform edge continuity.http://www.sciencedirect.com/science/article/pii/S1569843223002650Landform classificationDEMSuperpixelGCN |
spellingShingle | Honghao Fu Yilang Shen Yuxuan Liu Jingzhong Li Xiang Zhang SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network International Journal of Applied Earth Observations and Geoinformation Landform classification DEM Superpixel GCN |
title | SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network |
title_full | SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network |
title_fullStr | SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network |
title_full_unstemmed | SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network |
title_short | SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network |
title_sort | sgcn a multi order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network |
topic | Landform classification DEM Superpixel GCN |
url | http://www.sciencedirect.com/science/article/pii/S1569843223002650 |
work_keys_str_mv | AT honghaofu sgcnamultiorderneighborhoodfeaturefusionlandformclassificationmethodbasedonsuperpixelandgraphconvolutionalnetwork AT yilangshen sgcnamultiorderneighborhoodfeaturefusionlandformclassificationmethodbasedonsuperpixelandgraphconvolutionalnetwork AT yuxuanliu sgcnamultiorderneighborhoodfeaturefusionlandformclassificationmethodbasedonsuperpixelandgraphconvolutionalnetwork AT jingzhongli sgcnamultiorderneighborhoodfeaturefusionlandformclassificationmethodbasedonsuperpixelandgraphconvolutionalnetwork AT xiangzhang sgcnamultiorderneighborhoodfeaturefusionlandformclassificationmethodbasedonsuperpixelandgraphconvolutionalnetwork |