High-spectral image processing method for gibbsite information extraction

Abstract

The invention belongs to a high-spectral image processing method, and especially relates to a high-spectral image processing method for gibbsite information extraction. The method comprises the steps: 1, preprocessing; 2, sampling: carrying out the sampling of images with bands being at 1355nm, 1455nm, 1490nm, 1520nm, 1550nm, 1625nm, 1775nm, 1940nm, 2150nm, and 2255nm; 3, judgment; 4, calculation. The effects of the invention lie in that the method just employs ten bands; compared with a method employing a high-spectral image SASI full-wave band (101 bands), the method reduces the size of to-be-processed data by 90%, reduces the steps of principal component transformation and end member wave spectrum selection with the help of automatic one-step extraction through a computer, and can improve the operation speed by ten times or more. Because most of bands which are hardly correlated with the information extraction, the method reduces the interference with the spectrum from other materials or noises, and improves the precision of information extraction. The method is has greater effect and significance for the quick extraction of the gibbsite information in high-spectral image data.

Description

technical field [0001] The invention belongs to a hyperspectral image processing method, in particular to a hyperspectral image processing method for extracting gibbsite information. Background technique [0002] The current methods for extracting gibbsite information from hyperspectral remote sensing images are mainly spectral matching of full bands or partial continuous bands. In the process of information extraction, these methods are easily affected by the spectrum or noise of other ground features, and the accuracy of extracted information is relatively low. Secondly, the existing spectrum extraction method has many manual steps, which increases the error of human judgment. The third is that hyperspectral data has many bands and a large amount of data. The existing methods take a long time to process, which reduces the speed of data processing and the scale of application. Therefore, how to reduce the influence of other ground features or noise, manual operation steps...

AI Technical Summary

Problems solved by technology

[0002] The current methods for extracting gibbsite information from hyperspectral remote sensing images are mainly spectral matching of full bands or partial continuous bands. Mineral composition, these methods are easily affected by the spectrum or noise of other ground objects in the process of information extraction, and the accuracy of extracted information is relatively low

Secondly, the existing spectrum extraction method has many manual steps, which increases the error of human judgment.

The third is that the hyperspectral data has many bands and a large amount of data. The existing methods take a long time to process, which reduces the speed of data processing and the scale of application.