High spectral image compression sensing method based on manifold structuring sparse prior

Abstract

The invention discloses a high spectral image compression sensing method based on manifold structuring sparse prior and solves a technical problem of low precision existing in a high spectral image compression sensing method in the prior art. The method is characterized in that a few linear observation values of each pixel spectrum are sampled randomly and are taken as compression data, through the manifold structuring sparse prior, sparsity of a high spectral image after sparsification in the spectrum dimension and manifold structure of the high spectral image in the space dimension are etched, through a hidden variable Bayes model, signal reconstruction is carried out, and sparse prior learning and noise estimation are unified to one regularization regression model for optimization solution. The sparse prior acquired through learning can not only fully describe the three-dimensional structure of the high spectral image, but also has relatively strong noise robustness. The sparse prior is utilized to realize high precision reconstruction of the high spectral image. Based on tests, Gauss white noise is added to the compression data to make the signal to noise ratio of the compression data to be 15db, the sampling rate is 0.09, and thereby the 23db peak value signal to noise ratio is acquired.

Description

technical field [0001] The invention relates to a hyperspectral image compression sensing method, in particular to a hyperspectral image compression sensing method based on manifold structured sparse prior. Background technique [0002] A hyperspectral image contains hundreds or thousands of bands, and each pixel contains a continuous spectrum. Rich spectral information makes hyperspectral images have great advantages in target detection and recognition. However, the huge amount of data in hyperspectral images imposes strict requirements on image acquisition, transmission and processing, which restricts its practical application. Therefore, hyperspectral image compression is one of the hot research areas in the hyperspectral field. Compressed sensing imaging theory proves that only a small number of linear observations can be collected to accurately reconstruct the image of the original scene. Compared with the traditional image compression algorithm, the resource consumpt...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiency of low accuracy of the existing hyperspectral image compressive sensing meth...

Images