Hyperspectral image semi-supervised classification method based on space-spectral information

Abstract

The invention discloses a hyperspectral image semi-supervised classification method based on space-spectral information. The hyperspectral image semi-supervised classification method combines spectral information and spatial information in a hyperspectral image to act on a support vector machine classifier, adopts a self-training semi-supervised classification framework, utilizes an active learning method as a sample selecting strategy of semi-supervised classification, decomposes initial classification results obtained through semi-supervised classification according to classes so as to obtain various classes of binary images as input images of an edge preserving filter, regards a first principal component content as a reference image of the filter, utilizes the edge preserving filter to perform local smoothing, eliminates noise, and classifies image elements according to a class with maximum probability, thus the classification process is completed. The hyperspectral image semi-supervised classification method combines the spectral information and the spatial information to improve the classifiability of classes, utilizes the self-training semi-supervised classification framework to solve the classification problem of hyperspectral image small samples, can effectively eliminate spot-like errors in the initial classification results, and increases classification precision.

Description

technical field [0001] The invention belongs to the field of information technology, relates to pattern recognition and image processing technology, and in particular relates to a semi-supervised classification method using spectral information and spatial information of hyperspectral images in combination. Background technique [0002] The classification of hyperspectral image (spectral image with spectral resolution in the range of 10l) is an important content of hyperspectral remote sensing data information processing, and it is also an important way for people to obtain useful information from remote sensing images. Hyperspectral image classification is based on the spatial and spectral characteristics of image pixels, and determines and labels the category attributes of different types of ground objects represented by each pixel or a relatively homogeneous group of pixels. [0003] In recent years, with the continuous development of aerospace technology and remote sensi...

AI Technical Summary

Problems solved by technology

[0005] Traditional classification methods usually only use the information on the spectral dimension of data, but ignore the information contained in the spatial dimension, and the effect of a single spectral information on the classification accuracy is limited.

Images