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

Abstract

The invention belongs to the technical field of remote sensing information processing and particularly relates to a hyperspectral semi-supervised classification method based on space-spectral information. The hyperspectral semi-supervised classification method based on the space-spectral information includes the step of parameter setting, the step of space-spectral information extracting, the step of classification process conducting and the step of semi-supervised classification non-label sample selecting. According to the hyperspectral semi-supervised classification method based on the space-spectral information, space information and spectral information can be combined to effectively supervise the performance of the classification method, as the number of non-label training samples is increased, the performance of the method is also promoted because when the number of the non-label samples is increased, more space distribution information is provided, and a better prediction can be made for a classifier.

Description

technical field The invention belongs to the technical field of remote sensing information processing, in particular to a hyperspectral semi-supervised classification method based on space-spectral information. Background technique With the development of remote sensing technology, hyperspectral images have been widely used. However, when dealing with hyperspectral data, supervised classification methods are limited: 1. The contradiction between the high dimensionality of hyperspectral data and limited training samples causes the Hughes phenomenon, which seriously affects the performance of supervised classification; 2. High The spectral image covers a large area, and the field survey is difficult and long-term. The acquisition of labeled samples requires a lot of manpower and material resources. Different from supervised classification that only uses labeled samples and unsupervised classification that only uses unlabeled samples, semi-supervised classification is a techn...

AI Technical Summary

Problems solved by technology

Although this method effectively alleviates the problem of insufficient labeled samples in supervised learning, there are still obvious shortcomings. When there are too few labeled samples, the performance of this method does not improve significantly.

Traditional classification methods are generally based on spectral information, and spatial information has not been effectively mined and utilized.

Images