Hyperspectral image processing method for extracting gypsum information

Abstract

The invention belongs to a hyperspectral image processing method and particularly relates to a hyperspectral image processing method for extracting gypsum information. The hyperspectral image processing method comprises the following steps: step 1, preprocessing, step 2, sampling images at the wave bands of 1,145 nm, 1,175 nm, 1,325 nm, 1,445 nm, 1,460 nm, 1,700 nm, 1,745 nm, 1,820 nm, 1,940 nm, 2,060 nm, 2,210 nm, 2,330 nm and 2,405 nm; step 3, judging; step 4, calculating. The method has the benefits that only 13 wave bands are used, and the quantity of data needing to be processed is reduced by 87% as compared with the 101 wave bands of an SASI full-waveband hyperspectral image; as extraction is automatically carried out by a computer in one step, the operation steps of principal component transformation, end member spectrum selection and the like are reduced, and the operation speed can be increased by more than seven times. As most of the wave bands irrelevant to information extraction are removed, the interference of other substances or noise in the spectrum is reduced, and the information extraction precision is improved. The hyperspectral image processing method has a great effect and meaning on the rapid extraction of the gypsum information in hyperspectral image data.

Description

technical field [0001] The invention belongs to a hyperspectral image processing method, in particular to a hyperspectral image processing method for gypsum information extraction. Background technique [0002] The current method of extracting gypsum information from hyperspectral remote sensing images is mainly spectral matching of full band or part of continuous band. However, these methods are easily affected by the spectrum or noise of other ground objects in the process of information extraction, and the accuracy of information extraction 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 objects or noise, manual operation steps, ...

AI Technical Summary

Problems solved by technology

[0002] The current method for extracting gypsum information from hyperspectral remote sensing images is mainly spectral matching of full bands or partial continuous bands. Specific algorithms include spectral angle, mixed demodulation filtering, etc. Since the material composition of the surface is rarely composed of a single mineral Yes, these methods are easily affected by the spectrum or noise of other ground objects in the process of information extraction, and the accuracy of information extraction 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.