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

Light field full-focus image fusion method based on edge enhancement guided filtering

An all-focus image and guided filtering technology, which is applied in the field of image processing, can solve the problems of edge information loss of refocused images and reduce the fusion accuracy of all-focus images.

Active Publication Date: 2020-01-03
TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF12 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] When the guided filtering method is used for the calculation of the light field all-focus image, the geometric calibration error of the microlens center of the light field camera makes the decoded 4D light field information have a small error in the angle direction, resulting in the loss of edge information of the refocused image after integration , reducing the accuracy of all-focus image fusion

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
  • Light field full-focus image fusion method based on edge enhancement guided filtering
  • Light field full-focus image fusion method based on edge enhancement guided filtering
  • Light field full-focus image fusion method based on edge enhancement guided filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0047] A light field all-focus image fusion method based on edge-enhanced guided filtering, as follows:

[0048] 1), refocus image calculation

[0049] like figure 1 As shown, by geometrically calibrating the microlens coordinate center of the light field camera, the 4D light field L can be decoded from the original image of the light field F (x, y, u, v), according to the light field digital refocusing theory, combined with the light field biplane parameterized model, when the imaging plane of the light field camera moves from the sensor plane to the refocusing ...

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 belongs to the technical field of image processing. According to the specific technical scheme, the method comprises the steps that aplurality of refocusing images obtained through digital refocusing of a light field is subjected to multi-scale decomposition, and a feature layer decision diagram guides filtering optimization to obtain a final full-focusing image. Edge information loss caused by 4D light field calibration errors is compensated; in a refocusing image multi-scale decomposition process, extraction of an edge layer is added to realize image high-frequency informationenhancement. A multi-scale image evaluation model is established to achieve edge layer guided filtering parameter optimization, a light field full-focus image with higher quality can be obtained, andon the premise that the similarity between the full-focus image and an original image is not obviously reduced, the method can enable the image perception definition of the full-focus image to be averagely improved by 18.4%.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a light field all-focus image fusion method based on edge enhancement guided filtering. Background technique [0002] All-focus image fusion refers to the fusion of multiple locally focused images at different depths of the same scene into a clear overall focused image, so that it has more complete spatial information. The full-focus fusion of traditional images is based on multi-focus images obtained by multiple camera focusing. During the focusing process, changes in the imaging geometric relationship and mechanical jitter will cause changes in the size and viewpoint position of objects in the captured images at different times. The robustness requirements of image fusion methods are higher. The light field camera can obtain multiple refocused images through digital refocusing technology after a single exposure, which does not involve the limitation of sce...

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): G06T5/50G06T5/20
CPCG06T5/50G06T5/20G06T2207/20192G06T2207/20221G06T2207/10052
Inventor 王玉梅武迎春李素月王钢飞王安红
Owner TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY
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