What question did this study set out to answer?

The aim is to improve remote sensing land cover classification by integrating multi-scale and depth features into a graph neural network.

February 9, 2026

Graph Neural Network-Based Land Cover-Classification of Remote Sensing Images Using Multi-Scale and Depth Features

Key Points

The aim is to improve remote sensing land cover classification by integrating multi-scale and depth features into a graph neural network.
Developed a multi-scale and depth-feature classification method using graph neural networks.
Embedded raster-depth features into node features of image objects.
Extracted global and local features from images to create multi-scale depth features.
Utilized a fractal network evolution algorithm to obtain and analyze image objects.
Predicted node categories using graph convolutional networks and SoftMax.
Achieved improved overall accuracy of 3.83% and 3.46% compared to traditional methods.
Increased kappa coefficient by 0.0681 and 0.0637, indicating enhanced classification performance.
Successfully captured multi-scale and depth features, significantly enriching image information.

Abstract

Remote sensing land-cover classification can provide valuable data support for natural resource management. Existing classification methods based on graph-neural networks rely mainly on the global features and non-Euclidean structural features of image objects without considering the local features that describe their internal structures and the raster-depth features in the form of Euclidean structures. To this end, this paper presents a multi-scale and deep-feature, remote sensing???image land cover???classification method that embeds raster-depth features into node features and captures multi-scale graph-embedding information from global graphs and subgraphs to fully express image information. The depth-feature map of the image is obtained through a visual geometry Group 16???layer network and integrated into the feature space. The fractal network evolution algorithm is adopted to obtain multi-scale image objects. Global-scale features such as spectral, texture, index, and raster-depth features of the image objects are extracted, and local-scale features (e.g., average degree, average path length, graph diameter, average clustering coefficient, small-world effect) of the subgraphs are extracted to construct multi-scale depth features. The composite global graph structure is constructed by adopting adaptive weights, the graph embeddings are extracted via the graph convolutional network, and the node categories are predicted via SoftMax. For the Gaofen Image Dataset (GID‐15, a public benchmark dataset for land cover classification) and the 2017 China Computer Federation Remote Sensing Image Classification Dataset (CCF 2017, released in the 2017 China Computer Federation Big Data and Computational Intelligence Contest), as compared with the traditional method that considers only the global scale and the single-graph structure, this method improves the overall accuracy by 3.83% and 3.46%, respectively, and increases the kappa coefficient by 0.0681 and 0.0637, respectively, which indicates its effectiveness.

Mark Helpful

Bookmark

Relay