Hyperspectral remote sensing image end member extraction method on basis of revised extended morphological operator

Abstract

The invention provides a hyperspectral remote sensing image end member extraction method on the basis of a revised extended morphological operator, which is characterized in that an original image is filtered by the opening-and-closing operation and the closing-and-opening operation which are defined by the revised extended morphological operator so as to fulfill the aim of combining spectral information with space information to carry out end member extraction. The method mainly aims to solve the problem of limitation in the extended morphological operator; the revise is carried out by leading in a reference vector; for the provided revised extended morphological operator, the alternately replacing phenomenon is eliminated; the correct replacing direction is ensured; and a separating effect of pure pixels and mixed pixels is reinforced. An experimental result shows that the condition that the method provided by the invention can optimize the end element extraction effect is proved onthe aspects of the spectral curve similarity and a corresponding ground feature distribution map and the like; and the method has a moderate calculated amount and lays a foundation for application ofsubsequent analysis and classification of hyperspectral remote sensing image mixed end members and the like.

Description

technical field [0001] The invention proposes a hyperspectral remote sensing image endmember extraction method based on modified and extended morphological operators, which combines the spatial and spectral information of the hyperspectral remote sensing image for endmember extraction, and belongs to the field of hyperspectral remote sensing digital image processing and pattern recognition . The invention uses the morphology concept for the automatic extraction of hyperspectral remote sensing image endmembers, and solves the wrong replacement phenomenon caused by traditional extended morphology operators during endmember extraction by modifying the sorting rules and replacement criteria. It is suitable for endmember extraction of hyperspectral remote sensing images, mixed pixel analysis, mapping of ground object distribution, etc. Background technique [0002] The emergence and development of hyperspectral remote sensing imaging technology is a revolution in earth observati...

AI Technical Summary

Problems solved by technology

[0005] The AMEE method is a model for the application of extended morphological operators to hyperspectral remote sensing image endmember extraction. Its original intention is to separate pure pixels and mixed pixels through morphological filtering. However, it is found through research that AMEE can , the set sorting rules and replacement criteria have certain limitations, which makes it limited in the ability to separate pure pixels and mixed pixels, and it is easy to cause the phenomenon of cross-replacement of pixels at the boundary of the two types of ground objects in the image, which in turn affects The accuracy of final terminal cell extraction and the effect of subsequent mixed cell unmixing

Images