Improved hyperspectral image super-resolution reconstruction method based on POCS

Abstract

The invention discloses an improved hyperspectral image super-resolution reconstruction method based on POCS, and the method comprises the steps: firstly, randomly selecting one from gray images of a first wave band of a sequence low-resolution hyperspectral image, obtaining an initial reference frame through bicubic interpolation, and relieving the problem of edge blurring of a reconstructed image to a certain degree; correcting the residual grayscale image of the first wave band according to a projection formula into which a relaxation operator is introduced, so that burrs of a smooth region of the reconstructed image are inhibited; after more than two iterations, indicating that the iteration process is self-adaptive according to the condition whether the mean square error between the reconstructed images of the two iterations is smaller than a certain threshold value or not, so that the subjectivity of manually setting the number of iterations is avoided; and finally, repeating the above process on the grayscale image of each wave band of the hyperspectral image to obtain the hyperspectral image with improved spatial resolution. The method can be used as an effective means for improving the spatial resolution of the hyperspectral image.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a POCS-based hyperspectral image super-resolution reconstruction method. Background technique [0002] The spectral resolution of hyperspectral images is extremely high, but this high spectral resolution comes at the expense of spatial resolution. When taking a hyperspectral image, the exposure time of the camera is fixed, and the number of photons acquired is also fixed. The higher the spectral resolution, it means that when imaging, the number of photons allocated to each band for imaging is reduced. This leads to low spatial resolution of hyperspectral images. The mutual restriction of spectral resolution and spatial resolution limits the application of hyperspectral images, so how to improve the spatial resolution of hyperspectral images has become an urgent problem to be solved. [0003] Considering that starting from the hardware point of view, tha...

AI Technical Summary

Problems solved by technology

However, the image reconstructed by this type of algorithm will have problems such as blurred edges, glitches in smooth areas, and the number of iterations is too subjective.

Images