Hyperspectral image classification method based on compression spectrum clustering integration

Abstract

The invention discloses a hyperspectral image classification method based on compression spectrum clustering integration. The hyperspectral image classification method comprises a classification process including the steps that (1) image characteristic sets of hyperspectral images are obtained; (2) an image characteristic set sub space subjected to dimension reduction is obtained; (3) a plurality of hyperspectral image dividing results are obtained; (4) the final hyperspectral image dividing result is obtained; (5) the hyperspectral image classification result is obtained; (6) the accurate classification of the hyperspectral image is obtained. Compared with the prior art, the hyperspectral image classification method has the advantages that the defect that a k-means algorithm adopted in the classical spectral clustering is sensitive to initialization is overcome; the characteristic dimension of the hyperspectral images is reduced; meanwhile, the classification precision is obviously improved, and the dividing effect is good.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a hyperspectral image classification method based on compressed spectrum clustering integration. Background technique [0002] Hyperspectral images have high spectral resolution and provide rich information about the types of ground objects. The classification of remote sensing images is one of the key technologies for the analysis and application of remote sensing images. How to face the massive data and high-dimensional characteristics of hyperspectral images and combine various features of hyperspectral images to study fast and efficient target recognition and classification algorithms It is a hotspot in hyperspectral image processing research at present and in the future. [0003] One of the important reasons why hyperspectral remote sensing has received widespread attention from remote sensing scientists around the world is that this technology revoluti...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to overcome the deficiencies of the prior art, that is, the k-means algorithm used in classical spectral clustering is sensitive to initialization, which leads to the disadvantage that it is not easy to implement, and the hyperspectral image dimension is too high to cause the disaster of dimensionality, resulting in the classification accuracy of t

Images