A method and device for nonlinear hyperspectral image mixed pixel decomposition

Abstract

The invention provides a nonlinear hyperspectral image mixed pixel decomposition method and device. The mixed pixel decomposition precision can be improved. The method comprises the following steps: taking end-member spectral information in a mixed pixel as a non-perturbation item, taking interaction among different spectrums as a perturbation item, carrying out nonlinear mathematical descriptionon the mixed pixel, and constructing a nonlinear spectral correlation mixing model meeting self-consistency; By taking the spectral cluster as an impurity, mapping the nonlinear spectral correlation mixing model to an impurity model, and constructing a superlattice local Green function of the impurity model for solving to obtain an end member component and an end member abundance estimation result; And according to the obtained end member components and the end member abundance estimation result, clustering the estimation end members by using a density peak clustering method, and merging the same kind of estimation end members. The invention relates to the technical field of remote sensing image processing.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a nonlinear hyperspectral image mixed pixel decomposition method and device. Background technique [0002] As one of the important loads of the satellite remote sensing system, the hyperspectral remote sensing camera has the advantages of rich spectral information and high spectral resolution. It has broad application prospects in civilian fields such as planting surveys and in military fields such as military target reconnaissance, camouflage and anti-camouflage, and strike effect evaluation. However, the low spatial resolution and the complex diversity of ground objects lead to the existence of mixed pixels, which makes the rapid and accurate detection and classification of sub-pixel-level targets very difficult, which greatly limits the development of quantitative applications of hyperspectral data. Therefore, how to reduce the influence of mixed pixel...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a nonlinear hyperspectral image mixed pixel decomposition method and device to solve the problem of unclear physical meaning of the hyperspectral pixel mixed model in the prior art, resulting in poor decomposition accuracy of the mixed pixel The problem

Images