Hyperspectral waveband selection method based on normalization multidimensional mutual information and clonal selection

Abstract

The invention relates to a dimension reduction method for a hyperspectral image, and specifically relates to a hyperspectral waveband selection method based on normalization multidimensional mutual information and clonal selection. The method provided by the invention achieves the selection of clonal iteration times in the waveband selection of the hyperspectral image. The method comprises the steps: 1, reading the hyperspectral image, defining an antigen, randomly generating an initial set, and selecting optimal individuals according to the sizes of the adaptive values of individuals to form a set; 2, cloning the optimal individuals to form a temporary clonal set, carrying out the high-frequency mutation operation of the clonal set, and selecting the optimal individuals to form the set again; 3, judging the correlation degree of the new set and the former set through the normalization multidimensional mutual information, so as to judge whether the iteration is stopped or not. The method can achieve a purpose of reducing the dimensions of the hyperspectral image. In order to enable the value calculation to be more accurate, the method achieves the selection of the iteration times through the normalization multidimensional mutual information, reduces the unnecessary excessive iteration process in the selection process, and is suitable for the waveband selection application of the hyperspectral image.

Description

technical field [0001] The invention relates to a dimensionality reduction method for a hyperspectral image, in particular to a hyperspectral band selection method based on normalized multidimensional mutual information and clone selection. Background technique [0002] Hyperspectral imagery is a mass data source that combines imagery and spectrum. It contains both image information and spectral information. It can not only give spectral intensity data of each pixel on each spectral segment, but also has a high spectral resolution. This imaging technology can be applied in the field of target recognition, providing a good detection method for the detection and search of airborne hyperspectral imagers. However, hyperspectral images contain too much information and there is redundant information, so it is necessary to perform feature selection on hyperspectral data. [0003] The main task of feature selection is to select the features that can represent the original image inf...

AI Technical Summary

Problems solved by technology

It can solve the difficult problem of directly solving the multidimensional mutual information and the problem that the number of iterations needs to be determined manually

Images