A 3-stage Spectral-spatial Method for Hyperspectral Image Classification

TL;DR

This paper introduces a three-stage spectral-spatial framework for hyperspectral image classification that enhances accuracy, especially with limited training data, by combining data reconstruction, spectral analysis, and spatial smoothing.

Contribution

The proposed method uniquely integrates nested sliding window reconstruction, PCA, SVM probability estimation, and total variation smoothing for improved hyperspectral classification.

Findings

Outperforms three state-of-the-art algorithms on six benchmark datasets.

Achieves higher accuracy with fewer training labels.

More effective in small training set scenarios.

Abstract

Hyperspectral images often have hundreds of spectral bands of different wavelengths captured by aircraft or satellites that record land coverage. Identifying detailed classes of pixels becomes feasible due to the enhancement in spectral and spatial resolution of hyperspectral images. In this work, we propose a novel framework that utilizes both spatial and spectral information for classifying pixels in hyperspectral images. The method consists of three stages. In the first stage, the pre-processing stage, Nested Sliding Window algorithm is used to reconstruct the original data by {enhancing the consistency of neighboring pixels} and then Principal Component Analysis is used to reduce the dimension of data. In the second stage, Support Vector Machines are trained to estimate the pixel-wise probability map of each class using the spectral information from the images. Finally, a smoothed total variation model is applied to smooth the class probability vectors by {ensuring spatial connectivity} in the images. We demonstrate the superiority of our method against three state-of-the-art algorithms on six benchmark hyperspectral data sets with 10 to 50 training labels for each class. The results show that our method gives the overall best performance in accuracy. Especially, our gain in accuracy increases when the number of labeled pixels decreases and therefore our method is more advantageous to be applied to problems with small training set. Hence it is of great practical significance since expert annotations are often expensive and difficult to collect.