Hyper-spectral image super-resolution method based on hyper-parameter fidelity and depth prior joint learning

A hyperspectral image and multispectral image technology, which is applied in neural learning methods, graphics and image conversion, image data processing, etc., can solve problems that have not been fully studied, and achieve excellent fusion accuracy, simple network structure, and high fusion accuracy Effect

Active Publication Date: 2021-04-23
NANJING UNIV OF SCI & TECH
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above methods have achieved good fusion performance, how to learn the degradation model and its data priors to represent hyperspectral images in CNN network has not been fully studied

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hyper-spectral image super-resolution method based on hyper-parameter fidelity and depth prior joint learning
  • Hyper-spectral image super-resolution method based on hyper-parameter fidelity and depth prior joint learning
  • Hyper-spectral image super-resolution method based on hyper-parameter fidelity and depth prior joint learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] combine figure 1 , the implementation process of the present invention is described in detail below, and the steps are as follows:

[0020] The first step is to establish a hyperparameter fidelity model with deep prior regularization of the hyperspectral and multispectral image fusion variational model, that is, according to the hyperspectral image degradation model, design data fidelity items and regularization items, under the variational framework Building an objective function for hyperspectral-multispectral image fusion regularized by depth priors. Suppose the high-resolution hyperspectral image is where M, N, and L are the height, width, and number of bands of X, respectively; the low-resolution hyperspectral image is where m, n and L are its length, width and number of bands; the high-resolution multispectral image is M, N and l are its length, width and number of bands. Given the low-resolution hyperspectral image Y and the high-resolution multispectral i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a hyper-spectral image super-resolution method based on hyper-parameter fidelity and depth prior joint learning. The method comprises the following steps: establishing a hyper-spectral and multi-spectral image fusion variational model based on depth prior regularization of a hyper-parameter fidelity model; optimizing a hyperspectral multispectral image fusion variation model; carrying out tensor representation on the model optimization iteration process; performing network expansion on the iterative process of variational model optimization, and executing the iterative process of optimization; and training the network by using the L1 norm as a loss function. The method has the capability of representing the hyperspectral image degradation model and the data prior in the network at the same time, and has excellent performance when being applied to hyperspectral multispectral image fusion.

Description

technical field [0001] The invention relates to hyperspectral-multispectral image fusion technology, in particular to a hyperspectral image super-resolution method for joint learning of hyperparameter fidelity and depth prior. Background technique [0002] Hyperspectral images contain rich spatial spectral information, which can distinguish the material properties of the scene at the pixel level, and have important application value in remote sensing. However, the low resolution of hyperspectral image restricts its application in high-resolution earth observation. In contrast, multispectral images have high resolution and can provide ground object information for hyperspectral images. At present, hyperspectral-multispectral image fusion has become an important research direction of the enhancement technology of hyperspectral image resolution. [0003] Convolutional neural network (CNN) can use the spatial structure of the image to extract features, and can naturally extrac...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T3/40G06N3/04G06N3/08
CPCG06T3/4053G06T3/4046G06N3/04G06N3/08Y02A40/10
Inventor 杨劲翔肖亮
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap