Hyperspectral image classification method based on wavelet packet transformation and grey prediction model

Abstract

A novel hyperspectral image classification method based on wavelet packet transformation and a grey prediction model belongs to the hyperspectral image processing field. The method comprises the following steps: firstly, acquiring hyperspectral data to be processed; secondly, using the wavelet packet transformation to decompose a hyperspectral response curve of each pixel; thirdly, using the grey prediction model to process a decomposition result; fourthly, using a characteristic construction result to supervise and classify hyperspectral data; fifthly, outputting a hyperspectral image ground object classification result. The method is an automatic hyperspectral image classification method. By using the method, wave band correlation can be effectively removed; data redundancy can be reduced; a negative effect of a dimension disaster on classification precision can be avoided; an application range is wide.

Description

technical field [0001] The invention relates to a novel hyperspectral image classification method based on wavelet packet transform and gray prediction model, which belongs to the field of hyperspectral image processing. Background technique [0002] Hyperspectral Remote Sensing (Hyperspectral Remote Sensing) technology is a ground remote sensing technology that has developed rapidly in the past three decades. Whether in commercial, military or civilian fields, it has important theoretical value and broad application prospects. Hyperspectral remote sensing technology uses imaging spectrometers to obtain spectral responses with narrow intervals from the target to be measured, which can capture features that are difficult to find with conventional remote sensing technology, thus laying a solid physical foundation for quantitative analysis of material components. my country is one of the few countries in the world that independently developed a complete set of hyperspectral rem...

AI Technical Summary

Problems solved by technology

[0006] 3) Additive noise

[0008] 5) The mechanism and action process from ground object to image spectral response are very complicated

[0013] In the hyperspectral data processing system, due to the requirement of computational complexity, the less calculation of the classification algorithm, the better, but the classification accuracy of the traditional algorithm that meets this requirement is poor.

On the other hand, due to the requirement of classification accuracy, the classification algorithm should have good robustness to different classification scenarios, and the algorithm to meet this requirement has high computational complexity

Images