Global Random Graph Convolution Network for Hyperspectral Image Classification

Chaozi Zhang,Jianli Wang,Kainan Yao

doi:10.3390/rs13122285

Abstract

Machine learning and deep learning methods have been employed in the hyperspectral image (HSI) classification field. Of deep learning methods, convolution neural network (CNN) has been widely used and achieved promising results. However, CNN has its limitations in modeling sample relations. Graph convolution network (GCN) has been introduced to HSI classification due to its demonstrated ability in processing sample relations. Introducing GCN into HSI classification, the key issue is how to transform HSI, a typical euclidean data, into non-euclidean data. To address this problem, we propose a supervised framework called the Global Random Graph Convolution Network (GR-GCN). A novel method of constructing the graph is adopted for the network, where the graph is built by randomly sampling from the labeled data of each class. Using this technique, the size of the constructed graph is small, which can save computing resources, and we can obtain an enormous quantity of graphs, which also solves the problem of insufficient samples. Besides, the random combination of samples can make the generated graph more diverse and make the network more robust. We also use a neural network with trainable parameters, instead of artificial rules, to determine the adjacency matrix. An adjacency matrix obtained by a neural network is more flexible and stable, and it can better represent the relationship between nodes in a graph. We perform experiments on three benchmark datasets, and the results demonstrate that the GR-GCN performance is competitive with that of current state-of-the-art methods.

Highlights

Hyperspectral image (HSI) classification has received attention due to its applications in environmental monitoring, agriculture, and the military [1,2]
The methods based on the convolution neural network (CNN) (1D-CNN, 2D-CNN, and BASS) are superior to the machine learning methods (k-NN and support vector machine (SVM)) for all three datasets, the SVM test accuracy is close to that of the 1D-CNN and 2D-CNN for certain datasets
The experiment results demonstrate the superiority of CNN-based methods, which is why CNN has been widely used in HSI classification in recent years

Summary

Introduction

Hyperspectral image (HSI) classification has received attention due to its applications in environmental monitoring, agriculture, and the military [1,2]. Many methods have been applied in HSI classification, e.g., k-nearest neighbor (k-NN) [3], support vector machine (SVM) [4], random forest [5], extended morphological profile (EMP) [6], and extreme learning machine [7]. With the success of deep learning in the computer vision [8,9,10,11] and natural language processing [12,13,14] fields, many scholars have attempted to utilize advanced network structures in HSI classification. Chen et al first introduced the concept of deep learning into HSI classification by using stacked autoencoders [15]. Because recurrent neural networks are designed for sequential data, Mou et al applied them in HSI data analysis [17]

Methods

Results

Conclusion