Hyperspectral image super-resolution processing method based on a convolutional network

Abstract

The invention discloses a hyperspectral image super-resolution processing method based on a convolutional network, mainly solves the problem that a hyperspectral image generated in the prior art is low in resolution, and adopts the implementation scheme that firstly, a training sample and a test sample are formed by an acquired low-resolution hyperspectral image and a high-resolution multispectralimage; then constructing a convolutional network composed of an inference sub-network and a generation sub-network; training the convolutional network by using the training sample, and obtaining theconvolutional network with the highest similarity between the approximate distribution and the real distribution by maximizing a joint likelihood function of the low-resolution hyperspectral image andthe high-resolution multispectral image; and finally, inputting the test sample into the trained convolutional network, and carrying out optimization processing on the generated high-resolution hyperspectral image to obtain a final high-resolution hyperspectral image. According to the method, the resolution of generating the high-resolution hyperspectral image is improved by utilizing the deep convolutional neural network, and the method can be used for medical diagnosis, remote sensing, computer vision and monitoring.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an image super-resolution processing method, which can be used in medical diagnosis, remote sensing, computer vision and monitoring. Background technique [0002] Super-resolution optical images can overcome the limitations of low-resolution optical images and have shown promising results in many applications such as medical diagnosis, remote sensing, computer vision, and surveillance. To obtain high-resolution optical images, the most direct way is to use high-resolution image sensors, but due to the limitations of the manufacturing process and cost of sensors and optical devices, it is difficult to achieve in many occasions and large-scale deployment. Therefore, it is of great practical significance to obtain high-resolution images through super-resolution technology using existing equipment. In order to break the limitation of the inherent resolution of the ima...

AI Technical Summary

Problems solved by technology

However, there are still deficiencies: this method does not take into account the hidden variables hidden in the model, thus affecting the resolution of the generated high-resolution images

However, there are still shortcomings: this method uses a shallow probability model and only uses the information on the surface of the low-resolution image, and does not take into account the hidden information in the high-resolution / low-resolution image block pair. Therefore, more information cannot be generated to improve the resolution of the image, which affects the resolution of the final generated high-resolution image

Images