Fusion of Dual Spatial Information for Hyperspectral Image Classification

TL;DR

This paper introduces a novel hyperspectral image classification framework that fuses dual spatial information through feature extraction and spatial optimization, significantly improving classification accuracy across diverse datasets.

Contribution

The work proposes a new hyperspectral classification method combining adaptive texture smoothing for feature extraction and extended random walker for spatial optimization, with a novel decision fusion approach.

Findings

Outperforms state-of-the-art classification methods on multiple datasets.

The structural profile (SP) enhances discrimination between land covers.

The proposed framework achieves higher accuracy in hyperspectral image classification.

Abstract

The inclusion of spatial information into spectral classifiers for fine-resolution hyperspectral imagery has led to significant improvements in terms of classification performance. The task of spectral-spatial hyperspectral image classification has remained challenging because of high intraclass spectrum variability and low interclass spectral variability. This fact has made the extraction of spatial information highly active. In this work, a novel hyperspectral image classification framework using the fusion of dual spatial information is proposed, in which the dual spatial information is built by both exploiting pre-processing feature extraction and post-processing spatial optimization. In the feature extraction stage, an adaptive texture smoothing method is proposed to construct the structural profile (SP), which makes it possible to precisely extract discriminative features from hyperspectral images. The SP extraction method is used here for the first time in the remote sensing community. Then, the extracted SP is fed into a spectral classifier. In the spatial optimization stage, a pixel-level classifier is used to obtain the class probability followed by an extended random walker-based spatial optimization technique. Finally, a decision fusion rule is utilized to fuse the class probabilities obtained by the two different stages. Experiments performed on three data sets from different scenes illustrate that the proposed method can outperform other state-of-the-art classification techniques. In addition, the proposed feature extraction method, i.e., SP, can effectively improve the discrimination between different land covers.