Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sparse and low-rank matrix approximation-based hyperspectral image restoration method

A hyperspectral image, low-rank matrix technology, applied in the field of hyperspectral image restoration, can solve the problems of ignoring hyperspectral image correlation and unsatisfactory effect.

Inactive Publication Date: 2017-02-15
XIAMEN UNIV
View PDF5 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the effects of these methods are not satisfactory, because they all ignore the correlation between different bands of hyperspectral images.

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
  • Sparse and low-rank matrix approximation-based hyperspectral image restoration method
  • Sparse and low-rank matrix approximation-based hyperspectral image restoration method
  • Sparse and low-rank matrix approximation-based hyperspectral image restoration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] Concrete implementation steps of the present invention include:

[0070] Step 1, acquire hyperspectral image data affected by mixed noise.

[0071] Use a hyperspectral imager to obtain a set of multi-band hyperspectral image data d, and normalize it to [0,1]. Its size is M×N×B, where M and N represent the length and width of the hyperspectral image of each band, respectively, and B represents how many bands there are in total. The estimated noise level for this set of data is η = 20 / 255.

[0072] Step 2, initialize iteration variables.

[0073] (2a) Let the denoised data noisy data Gaussian noise level η (0) = η.

[0074] (2b) Initialize the iteration, set the loop variable k=1, and the horizontal and vertical coordinates of the center are i=10, j=10 respectively.

[0075] Step 3, iterative regularization

[0076] Step 4, obtain the two-dimensional data of the low-rank model to be established.

[0077] (4a) For the M×N hyperspectral image of B bands, take o...

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 relates to a sparse and low-rank matrix approximation-based hyperspectral image restoration method and belongs to the image processing field. The method includes the following steps that: a hyperspectral data sequence affected by mixed noises is acquired, or simulated mixed noises are artificially added into a clear hyperspectral image sequence, so that hyperspectral data to be processed can be obtained; the multi-band hyperspectral image data are segmented into a plurality of small data blocks, and each three-dimensional data block is pieced into one two-dimensional data matrix; a weighted Schatten p-normal type low-rank matrix approximation model is constructed for each two-dimensional data matrix; an extended Lagrange multiplier method is adopted to solve the model to obtain mixed noise-removed two-dimensional data matrixes; each two-dimensional data matrix is restored into three-dimensional hyperspectral data, so that a mixed noise-removed multi-band hyperspectral image can be obtained; and the above steps are repeated by using an iteration method to obtain a better restoration effect. The method can be effectively applied to fields such as remote sensing, geography, agriculture and military fields.

Description

technical field [0001] The invention relates to image processing, in particular to a hyperspectral image restoration method based on sparse and low-rank matrix approximation. Background technique [0002] Hyperspectral imaging technology is a kind of earth observation technology developed since the 20th century, which has achieved high practical value in military, geological survey, agricultural detection and other aspects. Hyperspectral image data is a three-dimensional image data. In addition to the two-dimensional image itself, there is also a band dimension. Its main feature is the fusion of traditional image space and spectral information. Hyperspectral image data contains rich spectral information of ground features, which can realize target recognition of ground features. [0003] Although with the development of computer technology and spectral imaging technology, the imaging quality of hyperspectral image data has been greatly improved. But inevitably, hyperspectr...

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
IPC IPC(8): G06T5/00
CPCG06T2207/10036G06T5/70
Inventor 曲延云吴伟伟谢源
Owner XIAMEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com