Semi-supervised hyperspectral remote sensing image classification and labeling method

Abstract

Aiming at the classification and labeling problem of hyperspectral remote sensing images, the present invention discloses a semi-supervised method for classifying and labeling hyperspectral remote sensing images. Mark the training samples and test samples; construct the correlation potential function of the conditional random field through the transductive support vector machine; construct the interaction potential function of the conditional random field through the improved Potts model; train the conditional random field model through the genetic algorithm; The obtained conditional random field model infers the test sample and obtains its classification and labeling results. Compared with the results of classification and labeling of hyperspectral remote sensing images obtained by using the conditional random field algorithm or transductive support vector machine alone, the hyperspectral remote sensing image classification and labeling results obtained by the present invention have removed a large number of isolated noise points, and have better regional continuity and accuracy. higher.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and in particular relates to a semi-supervised method for classifying and marking hyperspectral remote sensing images. Background technique [0002] With the rapid development of remote sensing imaging sensors, hyperspectral remote sensing imaging has gradually become an important means for human beings to explore the earth. The effective acquisition of a large number of hyperspectral remote sensing images demonstrates the ability of human beings to obtain remote sensing data, provides complete information resources for the development of scientific research, and also puts forward higher requirements for hyperspectral remote sensing image processing technology. [0003] In the field of remote sensing, hyperspectral image classification and labeling is one of the most basic problems in remote sensing image processing technology, and it is also the basis of image an...

AI Technical Summary

Problems solved by technology

[0005] (1) Purpose of the invention: In view of this, the present invention expects to provide a semi-supervised hyperspectral remote sensing image classification and labeling method to solve technical problems such as hyperspectral remote sensing image classification and labeling under the condition of a small number of labeled training samples

Images