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

Depth extraction method of light field image

A technology for depth extraction and light field images, which is applied in the fields of image processing and computer vision, and can solve problems such as narrow baselines

Inactive Publication Date: 2017-09-05
SOUTHEAST UNIV
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Due to the limitations of the equipment hardware conditions of the light field image and the relationship between the parameters of each optical equipment, the baseline between adjacent sub-images is extremely narrow, and the parallax range is within a few pixels. Even if the current optimal stereo matching algorithm is used Satisfactory results cannot be obtained, and it is necessary to study the characteristics of the light field to find a depth extraction method suitable for light field 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
  • Depth extraction method of light field image
  • Depth extraction method of light field image
  • Depth extraction method of light field image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further illustrated below in conjunction with specific embodiments, and it should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0033] The invention provides a depth extraction method for light field images. The invention consists of two stages: light field reconstruction and depth extraction. The steps of the reconstruction stage are as follows: first, calculate the parameters and image calibration tables obtained from various shooting situations of the camera, then decode, optimize and regularize the input light field data, and finally reconstruct the light field according to the light field imaging equation, Obtain multi-view images. The depth extraction stage includes: extracting multi-viewpoint images into extreme plane maps corresponding to the viewpoints, using the sub-gradient method to obtain the optimal di...

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 a depth extraction method of a light field image. The method of the present invention includes two stages: light field reconstruction and depth extraction, and the light field reconstruction stage includes: S1: after preprocessing the input light field data, reconstruct the light field according to the image center position of the image, Generate a multi-viewpoint image; the depth extraction stage includes: S2: extracting a polar plane map from the viewpoint image, calculating a disparity map, and optimizing to obtain an optimal depth map. The invention can obtain clear multi-viewpoint images after processing the light field data and perform accurate depth extraction.

Description

[0001] Technical field: [0002] The invention relates to a method for extracting the depth of a light field image, belonging to the technical fields of image processing and computer vision. [0003] Background technique: [0004] In 1991, Adelson et al. proposed the concept of plenoptic function for the first time, which is described in seven dimensions, which are the spatial position of the observation point (Vx, Vy, Vz), the elevation angle and azimuth angle (θ, φ) of the light, and the wavelength l The moment t at which the recording light is observed is expressed as L=P(Vx, Vz, θ, φ, l, t). In 1992, Adelson successfully applied the light field theory to computer vision, and proposed the plenary field theory. In 1996, Levoy's light field rendering theory and Steven et al.'s lumen diagram further improved the light field theory. The light field representation of the 4D light field L(u, v, s, t) given by Leovy et al. means the radiance value of light rays along a certain di...

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): H04N13/02H04N13/00
Inventor 姚莉刘云建
Owner SOUTHEAST 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