Remote sensing hyperspectral image band selection method based on conditional mutual information

Abstract

The invention provides a remote sensing hyperspectral image band selection method based on conditional mutual information, which comprises the following steps of: A, opening a hyperspectral remote sensing image and labeling a sample to be classified by man-machine interaction; B, grouping: carrying out band grouping by utilizing the conditional mutual information among all adjacent bands under given class condition according to the sample to be classified obtained from the step A; and C, searching: carrying out search calculation on the grouped bands obtained from the step B by utilizing a search algorithm combining a support vector machine and a genetic algorithm so as to find out an optimal band combination; and on this basis, pruning by using a self-adaptation branch and bound algorithm. Through the combinational use of the band grouping based on the conditional mutual information and the pruning based on the self-adaptation branch and bound algorithm, redundancy and noise grouping which are caused by noise perturbation are avoided, the frequency of band grouping is reduced and the classification accuracy of the band combination is improved.

Description

Technical field [0001] The invention relates to the technical field of remote sensing hyperspectral image processing, in particular to a remote sensing hyperspectral image waveband selection method. Background technique [0002] With the development of remote sensing technology and imaging spectrometers, the application requirements for hyperspectral images are becoming more and more extensive. Because hyperspectral data can obtain almost continuous ground object spectra, it has the ability to identify ground characteristics unmatched by other remote sensing data. But also because of this, hyperspectral images are often composed of hundreds of continuous bands, giving hyperspectral images Image classification brings a huge amount of calculation and redundancy, which makes the problem extremely complicated. Therefore, it is very urgent and important to reduce the dimensionality of many bands of hyperspectral images. [0003] Commonly used dimensionality reduction methods can genera...

AI Technical Summary

Problems solved by technology

However, the distribution of bands selected by this method is not uniform, and sometimes they are concentrated in a certain area, and even some bands are not selected, which leads to the loss of a large amount of useful classification information and cannot make full use of the rich spectral information of hyperspectral images.

Images