Image processing method and system based on nonsubsampled Cotourlet transform

A non-subsampling, image processing technology, applied in the field of image processing, can solve the problem of poor fusion of infrared and visible light, and achieve the effect of rich information content, clear image, and enhanced scene understanding

Inactive Publication Date: 2017-09-22
FUYANG NORMAL UNIVERSITY
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Makes the fusion of infrared and visible light poor

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
  • Image processing method and system based on nonsubsampled Cotourlet transform
  • Image processing method and system based on nonsubsampled Cotourlet transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] see figure 1 , an image processing method based on non-subsampling Cotourlet transform provided by Embodiment 1 of the present invention, such as figure 1 As shown, the method includes:

[0025] S101: Use non-subsampling Cotourlet transform to perform J-level multi-scale decomposition on the standard infrared image A and visible light image B to be fused respectively, and obtain the respective decomposition coefficients {c of the source images A and B J A , d Lj A} and {c J B , d Lj B}, where 1≤j≤J, L j is the direction decomposition coefficient at the jth scale, 1≤L j ≤2 j ,c J is the low-pass subband coefficient, d Lj is the subband coefficient in the bandpass direction;

[0026] S102: For the low-pass subband coefficient c J A 、c J B And the band-pass direction coefficient d of each level Lj A 、d Lj B Different fusion rules are adopted for fusion processing, and the fused non-subsampled Cotourlet transform coefficients {c J F , d Lj F}; Because...

Embodiment 2

[0031] Corresponding to the image processing method based on non-subsampling Cotourlet transform provided in Embodiment 1 of the present invention, Embodiment 2 of the present invention also provides an image processing system based on non-subsampling Cotourlet transform. Please refer to figure 2 , is a schematic diagram of an image processing system based on non-subsampling Cotourlet transform provided according to an embodiment of the present invention, such as figure 2 As shown, the system includes:

[0032] The sub-band coefficient determination unit 201 is used to perform J-level multi-scale decomposition on the standard infrared image A and visible light image B to be fused by using non-subsampling Cotourlet transform to obtain the respective decomposition coefficients {c J A , d Lj A} and {c J B , d Lj B}, where 1≤j≤J, L j is the direction decomposition coefficient at the jth scale, 1≤L j ≤2 j ,c J is the low-pass subband coefficient, d Lj is the subband ...

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 an image processing method and a system based on nonsubsampled Cotourlet transform. The method comprises steps: nonsubsampled Cotourlet transform is adopted to carry out J-level multiscale decomposition on an infrared image A and a visible light image B in standard configuration which are ready to be fused, and the decomposition coefficient of each of source images A and B is obtained; different fusion rules are adopted to a low pass subband coefficient and each-level bandpass direction coefficient for fusion processing, and the nonsubsampled Cotourlet transform coefficient after fusion is obtained; and inverse transform is carried out on the nonsubsampled Cotourlet transform coefficient obtained after fusion, and a fusion result image F is obtained. Through the method provided by the invention, area features and edge information of the image can be thoroughly integrated and explored, scene understanding is enhanced, and goals are highlighted. When the infrared image and the visible light image are fused, the region information and the detail texture information of the source images can be further captured, the image acquired by fusion is more distinct, and more information is contained.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image processing method and system based on non-subsampling Cotourlet transform. Background technique [0002] With the development of sensor technology, the application of infrared imaging sensors and visible light sensors in the fields of military and security monitoring has been continuously promoted. However, the imaging characteristics and limitations of these two types of sensors make it difficult for them to use a single sensor to complete tasks in certain imaging environments. How to use the complementary information between infrared and visible imaging sensors to effectively discover and synthesize image feature information, highlight infrared targets, and enhance scene understanding has always been a research hotspot in infrared and visible light image fusion technology. [0003] In the prior art, most of the infrared and visible light image fusion ...

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): G06T5/50
CPCG06T5/50G06T2207/20221
Inventor 刘辉冯莹莹
Owner FUYANG NORMAL UNIVERSITY
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