Semi-supervised dimension reduction-based hyper-spectral image classification method

Abstract

The invention discloses a semi-supervised dimension reduction-based hyper-spectral image classification method for mainly solving the problems of high calculation quantity caused by over high hyper-spectral image data dimensions and low classification accuracy of the conventional method. The method comprises the following steps of: expressing each pixel point of a hyper-spectral image by using a feature vector, and selecting a marked training set, a test set and a total training set; constructing local inter-class and local intra-class dissimilarity matrixes of the marked training set respectively to obtain a total local dissimilarity matrix; constructing and solving a feature value equation to obtain a projection matrix; projecting the marked training set and the test set to a low-dimensional space respectively to obtain a new marked training set and a new test set; and inputting the new marked training set and the new test set to a support vector machine, and performing classification to obtain class information of the test set. By adopting the thought of semi-supervision, higher classification accuracy can be acquired; and the method can be applied to the fields of map design, vegetation survey and military intelligence acquisition.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to dimensionality reduction of high-dimensional data, and is used for classifying hyperspectral remote sensing images. Background technique [0002] Hyperspectral remote sensing is one of the most important developments in the field of remote sensing since the 1980s, and it is also the frontier technology of remote sensing today and in the next few decades. Hyperspectral remote sensing technology uses imaging spectrometers to image surface objects simultaneously with tens or hundreds of bands with nanoscale spectral resolution, and can obtain continuous spectral information of surface objects, and realize spatial information, radiation information, and spectral information of surface objects. The synchronous acquisition has the characteristics of "integration of maps and maps", which makes human's ability to observe the earth and obtain information a big step forward. [0003] C...

AI Technical Summary

Problems solved by technology

[0006] The above PCA and KPCA are unsupervised dimensionality reduction methods, because without the guidance of effective supervision information, that is, category information, it is often difficult to obtain better subsequent classification results; LDA and KDA are supervised dimensionality reduction methods, although they can make full use of a large number of Obtaining ideal results by monitoring information, but obtaining a large amount of monitoring information requires paying a high price.

Especially for hyperspectral image data, the acquisition of its category information is time-consuming, labor-intensive and very difficult

Images