infrared and visible light image fusion method based on ADC-SCM and low-rank matrix expression

A low-rank matrix and image fusion technology, applied in the field of image processing, can solve problems such as artificial noise, inability to retain source image details, texture and main feature information, and inability to better integrate infrared and visible light information to achieve good infrared and visible light. The effect of visible light information

Pending Publication Date: 2019-05-24
YUNNAN UNIV
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, the fusion method of infrared and visible light images in the prior art has flaws in subjective visual effects or objective evaluation standards, and cannot better preserve target information and thermal radiation information in infrared images, and cannot better preserve target information and thermal

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
  • infrared and visible light image fusion method based on ADC-SCM and low-rank matrix expression
  • infrared and visible light image fusion method based on ADC-SCM and low-rank matrix expression
  • infrared and visible light image fusion method based on ADC-SCM and low-rank matrix expression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] Such as Figure 1-2 shown

[0043] An infrared and visible light image fusion method based on ADC-SCM and low-rank matrix expression, comprising the following steps:

[0044] Step 1: Perform frequency modulation (FT) saliency detection on the infrared source image to obtain the initial saliency map, then perform low-rank decomposition on the infrared source image to obtain the low-rank matrix and sparse matrix, and subtract the low-rank matrix from the initial saliency map to obtain the final Salient map, binarize the salient map to separate the salient area from the background area; the FT algorithm and the low-rank decomposition formula are as follows:

[0045] S p (i,j)=||I μ -I ωhc (i,j)||

[0046] Among them, I μ Indicates the average pixel value of the image, I ωhc (i, j) represents the image after Gaussian filtering, |||| represents the Euclidean distance, S p represents the initial saliency map;

[0047]

[0048]

[0049] S g =(S P -Z)*S p

[...

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 infrared and visible light image fusion method based on ADC-SCM and low-rank matrix expression, relating to the technical field of image processing.. The fusion method combinesadaptive dual channel pulsed cortex (ADC-SCM) and low rank matrix (LRR) theory to propose an effective infrared and visible image fusion algorithm. According to the fusion method, an effective infrared and visible light image fusion algorithm is provided by combining an adaptive double-channel pulse distribution cortex (ADC-SCM) and a low-rank matrix (LRR) theory; The method comprises the following steps: firstly, combining low-rank expression with a frequency modulation (FT) saliency algorithm to carry out salient region detection on an infrared source image, thereby separating a salient region from a background region in the source image; Secondly, fusing the two obtained regions respectively, and selecting a fusion rule with the maximum absolute value to fuse the significant regions inorder to retain the significant features to the maximum extent; And finally, obtaining a fused background through NSST inverse transformation, and superposing the fused salient region and the fused background region to obtain a final fused image. Experimental results show that the algorithm provided by the invention is superior to other common image fusion algorithms in subjective visual effect and objective evaluation indexes.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an infrared and visible light image fusion method based on ADC-SCM and low-rank matrix expression. Background technique [0002] With the rapid development of sensor and computer science and technology, image fusion technology plays an important role in RGB-D image processing, satellite cloud image, medical image analysis, pattern recognition, modern military, remote sensing and many other application fields. Especially combining multi-modal images such as infrared and visible light images to improve the efficiency of human visual perception and target recognition. Infrared sensors mainly capture the thermal radiation emitted by objects, and can obtain significant target information in low-light environments. In contrast, visible light images are obtained based on the principle of spectral reflectance of objects, so they usually contain rich textures and environmental d...

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): G06T5/50G06T3/40G06T7/00G06T7/194
Inventor 聂仁灿侯瑞超周冬明刘栋阮小利贺康建李华光
Owner YUNNAN UNIV
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