Hyperspectral image classification method and system based on stack width learning

Abstract

The invention provides a hyperspectral image classification method and system based on stack width learning, and the method comprises the steps: carrying out the preprocessing of an input image, whichcomprises the normalization, wavelet decomposition, and difference; secondly, selecting a small number of samples as training samples, and learning the spatial spectrum characteristics of the hyperspectral image by using a stack width learning model; then, a training sample is used for training to obtain a width learning classifier, and finally, the characteristics of the test sample are input into the trained width learning classifier to obtain a class label. By using the stack width learning model of the invention, more abstract spatial spectrum characteristics can be obtained, so that themethod of the invention can obtain a very accurate classification result. Due to the characteristic of width learning, the method has relatively low sample complexity, and a relatively good classification result can be obtained only by a small number of training samples, so that the method is more beneficial to practical application.

Description

technical field [0001] The invention belongs to the technical field of remote sensing impact processing and analysis, and designs a hyperspectral image classification method and system, which can be used for resource management, scene interpretation, precision agriculture, urban planning, disaster prevention and mitigation, and the like. Background technique [0002] As a cutting-edge technology in the field of remote sensing, hyperspectral remote sensing has a wide range of applications in military and civilian fields. The rich spectral information of hyperspectral images not only provides more information for object classification, but also brings a series of new problems of feature extraction and pattern recognition. Researchers have conducted in-depth research on a series of problems in hyperspectral image classification, such as high data dimensionality and few training samples. However, the above-mentioned problems have not been effectively solved so far. [0003] Fi...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose a hyperspectral image classification method based on stack width learning to solve the difficulty in learning effective classification features and high sample complexity in the hyperspectral image classification problem in the prior art. problem, improving the performance of spectral image classification

Images