Optical material classification and recognition method based on hyperspectral data information maximization

Abstract

The invention discloses an optimal material classification and recognition method based on hyperspectral data information maximization. The optimal material classification and recognition method comprises the following steps: (1) selecting training data from acquired hyperspectral data; (2) successively carrying out zero-mean, energy-keeping dimensionality reduction and unit normalizing pretreatment on the training data; (3) estimating a dimension matrix of line dimensionality reduction according to pretreatment data; (4) carrying out information maximizing row dimensionality reduction characteristic matrix calculation according to line-by-line dimensionality reduction dimension arrays; (5) carrying out classifier training according to a row-by-row dimensionality reduction characteristic matrix; (6) selecting an optimal characteristic matrix and an optimal classifier according to a training result; and (7) carrying out material classification and recognition on to-be-classified hyperspectral data according to the optimal characteristic matrix and the optimal classifier. The method provided by the invention has the advantages that the reduction of the hyperspectral data can be performed from a high-order statistics angle, and thus the high classification efficiency is achieved; a new classifier is easy to expand and add, so that the classifier with the excellent property is convenient to generate, and the material classification and recognition are well performed.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral data processing, and relates to a method for information maximization and optimal classification and utilization of hyperspectral data, whereby different substances can be optimally classified. Background technique [0002] Hyperspectral remote sensing technology (also known as imaging spectroscopy technology) is a new remote sensing technology developed in the past two decades. Hyperspectral remote sensing is the frontier of today's remote sensing technology. Hyperspectral technology was first applied in the identification of geological minerals, and then widely used in atmospheric science, ecology, geology, hydrology and marine science. Compared with traditional multispectral data, hyperspectral remote sensing data has richer spectral information, and its successful application shows that hyperspectral remote sensing has high application potential. my country is one of the few countries w...

AI Technical Summary

Problems solved by technology

Commonly used hyperspectral data classification methods are mainly based on classification methods represented by maximum likelihood method, spectral angle mapping, principal component analysis, wavelet transform, artificial neural network, etc., and do not take into account the categories in the training data when extracting features Information and high-order statistical features are not used for feature selection and dimensionality reduction based on classification capabilities, and generally can only be used to classify substances with a small number of substances

Images