Adaptive spectral focusing band selection method for hyperspectral image

Abstract

The invention discloses an adaptive spectral focusing band selection method for a hyperspectral image. The method comprises the steps of firstly processing whole spectral domain hyperspectral originaldata of a ground object by utilizing three band selection algorithms, arranging results of the algorithms according to a sequence from large to small, and selecting out first N bands as optimal bandcombinations; and secondly assessing the optimal band combinations selected out by the three band selection algorithms by utilizing an independent component analysis (ICA) band assessment function, setting a J threshold, calculating out assessment results of the band combinations, and selecting the band combination with the maximum result as the optimal band combination. By utilizing an adaptive spectral focusing technology, automatic wavelength selection of wave bands can be realized during imaging of a spectrograph; a tunable light filtering component in an imaging control system is adaptively tuned to multiple spectral channels most favorable for detection and identification; spectral adaptive detection is realized; redundant and disorderly spectral information is deleted; the spectralimaging information utilization efficiency is improved; and the resource demand of information processing is reduced.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a hyperspectral image self-adaptive spectral focusing band selection method. Background technique [0002] In the past 30 years, with the development of hyperspectral remote sensing technology and imaging spectrometer, hyperspectral imaging technology has been successfully applied in the field of satellite and airborne remote sensing. However, due to the high dimensionality of hyperspectral image data, the large amount of data, and the large redundancy of data between bands, the Hughes phenomenon will appear, that is, under the premise of a certain number of sample points, the classification accuracy will "increase first" with the increase of the feature dimension. This is an important factor affecting the classification accuracy. Therefore, how to suppress the appearance of the Hughes phenomenon has become an important content of hyperspectral data processi...

AI Technical Summary

Problems solved by technology

However, due to the high dimensionality of hyperspectral image data, the large amount of data, and the large redundancy of data between bands, the Hughes phenomenon will appear, that is, under the premise of a certain number of sample points, the classification accuracy will "increase first" with the increase of the feature dimension. Back drop", which is an important factor affecting the classification accuracy

Images