A Dimensionality Reduction Method for Hyperspectral Data Based on Pairwise Constrained Discriminant Analysis-Nonnegative Sparse Divergence

Abstract

The invention discloses a method for reducing dimensions of hyper-spectral data on the basis of pairwise constraint discriminate analysis and non-negative sparse divergence, and belongs to methods for processing hyper-spectral remote sensing images. The method aims to solve the problem of deterioration of the classification performance of most advanced algorithms for classifying hyper-spectral data on the basis of machine learning when source hyper-spectral data and target hyper-spectral data are distributed differently. The method includes firstly, performing pairwise constraint discriminate analysis according to pairwise constraint samples; secondly, designing a non-negative sparse divergence criterion to create a bridge among source-field hyper-spectral data and target-field hyper-spectral data which are distributed differently; thirdly, combining the pairwise constraint discriminate analysis with the bridge to transfer knowledge from the source hyper-spectral data to the target hyper-spectral data. The pairwise constraint samples containing discriminate information can be automatically acquired. The method has the advantages that the knowledge can be transferred among the hyper-spectral data acquired at different moments, in different areas or by different sensors; the information of the source-field hyper-spectral data can be effectively utilized to analyze the target-field hyper-spectral data, and high integral classification precision and a high Kappa coefficient can be acquired.

Description

technical field [0001] The invention relates to a hyperspectral remote sensing image processing method, in particular to a hyperspectral data dimensionality reduction method based on pairwise constraint discriminant analysis-nonnegative sparse divergence. Background technique [0002] With the development of hyperspectral sensors, a large number of dense and continuous spectral bands can be obtained and widely used to observe the earth's surface. The complexity of the hyperspectral data classification process usually depends on the number of bands obtained, and the high correlation between dense and continuous spectral bands will increase the band redundancy and produce the Hughes phenomenon. Therefore, in order to retain as much useful information as possible while reducing the complexity of hyperspectral data classification, it is necessary to transform high-dimensional data into low-dimensional subspaces, so that hyperspectral data can be classified more efficiently. [...

AI Technical Summary

Problems solved by technology

TSSL-MMD needs to obtain the kernel matrix of samples in the source domain and the target domain. When it is used to process data with a very large sample size such as hyperspectral data, the computational overhead of TSSL-MMD is relatively large; in addition, according to the MMD criterion The resulting kernel matrix does not have discriminative information, which leads to reduced transfer efficiency

The discriminative manifold embedding part of STME takes all the background samples and target samples into account, so it is impossible to avoid redundant and noisy samples that affect the efficiency of the algorithm.

Images