End member extract method of hyperspectral image

Abstract

The invention discloses an end member extract method of a hyperspectral image, comprising the following steps: projecting a dimensionality reduced hyperspectral image spectrum matrix onto a hyperplane to obtain a monomorphous; selecting the centre direction of an observation spectrum vector set as a projecting direction; projecting the monomorphous alongthe projecting direction; according a projecting result, obtaining a projecting extreme value and a pixel position corresponding thereto, setting up a pixel position index; obtaining a spectrum curve by the projecting extreme value and the position index; getting a next projecting direction with the position index, projecting on a new projecting direction and getting the projecting extreme value, the position index corresponding thereto and the spectrum curve of the end member until that the obtained end member reaches preset end member quantity. The method can reach better extracting precision and better stability.

Description

technical field [0001] The invention relates to the field of hyperspectral image analysis, in particular to an endmember extraction method of a hyperspectral image. Background technique [0002] Hyperspectral technology has achieved a leap in remote sensing technology in the 20th century, and is one of the focuses in the field of international remote sensing today. A hyperspectral image is a set of two-dimensional images obtained by multispectral imaging of a specific target, in which each spectral segment corresponds to a two-dimensional image, and one-dimensional spectral information is added to the two-dimensional image. It has the characteristic of combining graphs and spectra, can reflect the physical characteristics of the measured object, and is used for target detection in complex environments. Hyperspectral images are widely used in space remote sensing, military reconnaissance, agriculture and environmental detection, such as environmental imaging, geological rese...

AI Technical Summary

Problems solved by technology

In this case, a vertex is obtained, but in fact, it may not be the optimal choice for the subsequent iterative process (for example, it is not significant as a vertex, and the projection values ​​​​of surrounding points are slightly different from it), which will affect accuracy

[0015] In the process of extracting endmembers using the VCA method, the initial projection vector is generated by generating a zero-mean Gaussian random vector. Due to the randomness of the Gaussian vector selection, the final generated endmember set is unstable and the accuracy is not high, so it is not universal. sex

Images