Expansion morphology and orthogonal subspace projection combined end member automatic extraction method

Abstract

The invention relates to a method for automatically extracting end members by combination of expanding morphology and orthogonal subspace projection, which comprises the following steps: (1) reading high-spectrum data; (2) determining the dimension, the initial iteration and the maximum iteration of a structural element; (3) calculating pixels with minimum mixing degree and maximum mixing degree in neighboring areas of the structural element through expansion and corrosion operations; (4) calculating and obtaining the morphological eccentricity index value through the result obtained in the step (3); (5) repeating the step (3) and the step (4) along with the increase of the iteration, and utilizing the result of expansion operation in the step (3) to update image data until the maximum iteration is reached; (6) performing binaryzation on MEI images and obtaining an end member data set; (7) calculating and obtaining a first end member by a spectral corner matching method, and updating the end member data set by the projection in an orthogonal subspace of the obtained end member; and (8) repeating the step (7) until the error requirement is met. The invention is a method for automatically extracting the high-spectrum end members with strong stability, high reliability and high precision.

Description

technical field [0001] The invention relates to an automatic endmember extraction method combined with extended morphology and orthogonal subspace projection, which belongs to the field of hyperspectral data processing methods and application technologies, and is suitable for theoretical methods of hyperspectral data endmember extraction and in fine classification of crops, mineral erosion, etc. Applied technology research in fields such as variable information extraction. Background technique [0002] An essential difference between hyperspectral data processing and traditional remote sensing data processing is that the latter usually divides a single pixel into a different category according to certain rules when classifying ground objects, so as to more accurately reflect remote sensing objects. status. Mixed pixel decomposition is not only an important method to improve the recognition accuracy of ground objects, but also an effective way to quantitatively detect the co...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the shortcomings of existing endmember extraction methods starting from a single aspect of data spectrum or space or feature information to decompose mixed pixels, and it is difficult to distinguish different types of endmembers. A Method for Automatically Extracting Endmembers Based on Spatial Projection Combination

Images