Hyperspectral Remote Sensing Image Classification Based on Multi-scale Cross Graphic Convolution

TL;DR

This paper introduces MGRNet, a multi-scale feature-mining algorithm for hyperspectral image classification that combines PCA, multi-scale convolution, graph convolution, and residual networks to improve recognition accuracy.

Contribution

The paper proposes a novel multi-scale feature-mining learning algorithm (MGRNet) that effectively captures internal relationships between features for hyperspectral image classification.

Findings

MGRNet outperforms traditional methods in recognition accuracy on three datasets.

The model effectively retains semantic information through PCA-based dimensionality reduction.

Multi-scale graph convolution enhances internal feature relationships.

Abstract

The mining and utilization of features directly affect the classification performance of models used in the classification and recognition of hyperspectral remote sensing images. Traditional models usually conduct feature mining from a single perspective, with the features mined being limited and the internal relationships between them being ignored. Consequently, useful features are lost and classification results are unsatisfactory. To fully mine and utilize image features, a new multi-scale feature-mining learning algorithm (MGRNet) is proposed. The model uses principal component analysis to reduce the dimensionality of the original hyperspectral image (HSI) to retain 99.99% of its semantic information and extract dimensionality reduction features. Using a multi-scale convolution algorithm, the input dimensionality reduction features were mined to obtain shallow features, which then served as inputs into a multi-scale graph convolution algorithm to construct the internal relationships between eigenvalues at different scales. We then carried out cross fusion of multi-scale information obtained by graph convolution, before inputting the new information obtained into the residual network algorithm for deep feature mining. Finally, a flexible maximum transfer function classifier was used to predict the final features and complete the classification. Experiments on three common hyperspectral datasets showed the MGRNet algorithm proposed in this paper to be superior to traditional methods in recognition accuracy.