Hyperspectral image classification based on gradient lifting decision tree and semi-supervise algorithm integration

Abstract

The invention discloses a hyperspectral image classification based on gradient lifting decision tree and semi-supervise algorithm integration in order to solve the technical problem that hyperspectral image classification based on active learning and semi-supervise learning is low in classification precision. Hyperspectral image classification includes the steps that firstly, hyperspectral image data is input; secondly, features of sample points are extracted; thirdly, parameters of a gradient lifting decision tree classifier are trained; fourthly, massed learning sample points are classified; fifthly, the confidence degree of the sample points are assessed; sixthly, the sample points are screened through sparse representation; seventhly, a marked training set is updated; eighthly, a classification result is output. Assessment is conducted on the confidence degree of the unmarked sample points through the prediction result of the classifier and sparse representation, according to the confidence degree of the unmarked sample points, the sample points are divided into two sets for different kinds of processing, burdens for manual marking are reduced while classification precision is improved, and hyperspectral image classification can be used in the fields of geological survey, atmospheric pollution and like.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a hyperspectral image classification method, in particular to a hyperspectral image classification method based on gradient lifting decision tree semi-supervised algorithm fusion, which can be used for geological surveys, air pollution and military target strikes, etc. field. Background technique [0002] With the development of optical remote sensing technology, the history of remote sensing imaging has evolved from panchromatic (black and white) images, color photography, multi-spectral scanning imaging to today's hyperspectral remote sensing imaging and hyperspectral imaging. Hyperspectral remote sensing technology uses 10 -2 The λ and continuous spectral channel performs continuous remote sensing imaging of ground objects, obtains a large amount of ground object image data with complete spectral information, and realizes the simultaneous acquisition of ground object s...

AI Technical Summary

Problems solved by technology

However, the disadvantage of semi-supervised learning is that when the number of samples is small and the model training is insufficient, the class label prediction of unlabeled data is often inaccurate, and adding wrongly labeled samples to the training set will lead to the failure of the classifier. Decreased learning performance

This method saves time and manpower, but due to the lack of manual labeling process and only relies on the classifier itself for class label prediction, the classification accuracy needs to be improved

Images