Hyperspectral image sparse unmixing method based on random projection

Abstract

A hyperspectral image sparse unmixing method based on random projection includes the following four main steps: (1) data are read by a computer under the environment of MATLAB R2008b; (2) the hyperspectral image data and the hyperspectral library data are randomly projected by the computer; (3) a target function for sparse unmixing is constructed, and the split Bregman algorithm is used for optimizing the target function and working out an extremum until reaching convergence and stopping conditions; (4) an appropriate threshold value is set to process a abundance fraction matrix, so that a final abundance fraction graph and end members can be obtained. The hyperspectral image sparse unmixing method based on random projection utilizes a hyperspectral database to choose the end members, and overcomes the defect that the end members worked out by the conventional algorithm cannot strictly correspond to the spectra of pure materials in the standard hyperspectral database; and moreover, the hyperspectral image sparse unmixing method based on random projection uses the random projection technology to carry out dimensionality reduction on raw data, thus achieving the effects of saving memories and reducing the calculation load. The hyperspectral image sparse unmixing method based on random projection realizes rapid quantitative analysis on hyperspectral images, and has practical value and a broad application prospect in the field of hyperspectral remote sensing image analysis.

Description

(1) Technical field: [0001] The invention relates to a hyperspectral image sparse unmixing method based on random projection, and belongs to the technical field of hyperspectral remote sensing image analysis. (two) background technology: [0002] In the past three decades, with the continuous development of imaging spectroscopy technology, remote sensing images (remote sensing images) collected by imaging spectrometers mounted on aircraft or satellite platforms contain more and more abundant spatial , radiation and spectral information, thus providing a powerful means for information extraction and target detection of surface materials. As an important indicator of the development of remote sensing technology, spectral resolution has been developed from multi-spectral to hyperspectral, and is developing towards ultra-hyperspectral. [0003] Generally speaking, in the same environment, the material spectra detected by the same spectral sensor have the characteristics of diff...

AI Technical Summary

Problems solved by technology

[0006] The common problem faced by the three hyperspectral image unmixing technologies is that the massive hyperspectral data causes insufficient computer memory and long calculation time during the unmixing process.

Images