Multi-hypothesis prediction hyperspectral image compressed sensing reconstruction method based on space-spectrum combination

Abstract

The invention discloses a multi-hypothesis prediction hyperspectral image compressed sensing reconstruction method based on space-spectrum combination. The method comprises the following steps: firstly sampling each waveband image of a hyperspectral image at a sampling end through block compressed sensing, and transmitting measurement values to a reconstruction end; then, at the reconstruction end, constructing a global reconstruction model, and constructing a global measurement matrix for reconstructing a whole image; analyzing the smoothing characteristics of each waveband image and the inter-spectrum correlation between different waveband images, describing the smoothing characteristics and the inter-spectrum correlation by utilizing total variation and multi-hypothesis prediction, andconstructing a composite reconstruction optimization problem with minimum total variation and minimum inter-spectrum prediction residual by taking minimum total variation and multi-hypothesis prediction residual as regular terms; and finally, solving the composite reconstruction optimization problem by using an augmented Lagrange multiplier algorithm and an alternating direction process to obtaina reconstruction result of the hyperspectral image. The reconstructed hyperspectral image obtained by the method is clear, and the peak signal-to-noise ratio of the reconstructed image is high.

Description

technical field [0001] The invention relates to the technical field of image compression, in particular to a multi-hypothesis prediction hyperspectral image compressive sensing reconstruction method based on space-spectrum union. Background technique [0002] Hyperspectral images not only contain the spatial distribution information of the observed target, but also each pixel in the image has dozens or even hundreds of narrow bands of rich spectral information, which has the property of "integrating graphs and spectra into one". Since hyperspectral images can combine spectral features reflecting material properties with image information presenting material geometric space information, it has greatly improved the ability of human beings to recognize the objective world, and has been widely used in remote sensing, military, agriculture, medicine and other fields. It is proved to have great application value. [0003] Due to the high spatial and spectral resolution of hypersp...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a multi-hypothesis predictive hyperspectral image compressive sensing based on space-spectrum joint for the shortcomings of the existing hyperspectral image compressive sensing reconstruction algorithm that does not fully utilize the spatial and spectral characteristics, and the reconstruction image accuracy is low. Reconstruction method to make the reconstructed hyperspectral image clear and high peak signal-to-noise ratio

Images