Infrared light intensity and polarization image fusion method based on significance migration and detail classification

A polarization image and fusion method technology, which is applied in image enhancement, image analysis, image data processing, etc., can solve the problems of simultaneous fusion and poor fusion effect, and achieve the effect of avoiding edge effect and distortion

Inactive Publication Date: 2017-06-13
ZHONGBEI UNIV
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the current infrared light intensity and polarization image fusion method cannot fuse the significant bright and dark features and more detailed information in the source image into one image at the same time, resulting in poor fusion effect. Infrared Intensity and Polarization Image Fusion Method for Saliency Shift and Detail Classification

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 light intensity and polarization image fusion method based on significance migration and detail classification
  • Infrared light intensity and polarization image fusion method based on significance migration and detail classification
  • Infrared light intensity and polarization image fusion method based on significance migration and detail classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] according to figure 1 The fusion flow chart of Figure 2 to Figure 5 Totally 4 groups of scene infrared light intensity and the fusion of polarized image are taken as an example to carry out experimental explanation, then the specific implementation steps of the present invention are:

[0026] S1: Perform NSCT two-layer decomposition on the registered infrared light intensity and polarization images of the same input scene to obtain the low frequency components of the infrared light intensity and polarization images and the high frequency components of the 4 directions of the first layer and the 8 directions of the second layer ;

[0027] S2: Perform AC saliency detection on the infrared light intensity and low-frequency components of the polarization image in S1, respectively, and perform percentile activity threshold segmentation on the obtained saliency map to obtain the light intensity salient area S I and polarization significant region S P ,Specific steps are a...

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 infrared light intensity and polarization image fusion method based on significance migration and detail classification. The method comprises the following steps that: firstly, carrying out NSCT (Non-Subsampled Contourlet Transform) multiscale decomposition on a source image; secondly, carrying out significance detection on a low-frequency component obtained by decomposition, carrying out activity threshold segmentation by a significance image percentile, and determining a significant region; then, migrating the specific low-frequency significant region of polarization into a low-frequency fusion image, taking the rest low-frequency parts as a background region to take a big rule to keep strength information; dividing phase congruency and the threshold of a high-frequency component into an edge outline class and a texture detail class, and independently utilizing the phase congruency and a local standard deviation to fuse two classes of details; and finally, through NSCT inverse transformation, reconfiguring a final fusion image. By use of the method, source image significance bright and dark features and more detail information can be effectively fused into one image, and the method is mainly used for (but is not limited to) the fusion of the infrared light intensity and the polarization image.

Description

technical field [0001] The invention belongs to the field of infrared image processing, and in particular relates to a fusion method based on saliency transfer and detail classification based on infrared light intensity and polarization images, specifically a fusion method of infrared light intensity and polarization images based on saliency transfer and detail classification method. Background technique [0002] Traditional infrared detection is imaging in the form of thermal perception, and distinguishes objects by differences in thermal radiation. Therefore, the obtained light intensity image has good brightness characteristics and regional characteristics, but lacks edge and texture detail information; infrared polarization imaging can capture scene polarization information, suppress Complicated backgrounds can detect targets that cannot be detected by traditional infrared. The image has more structure and texture details, but the overall brightness information is not pr...

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): G06T5/50G06T7/10G06T7/136
Inventor 杨风暴吉琳娜董安冉王建萍郝晋萍王肖霞
Owner ZHONGBEI 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

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