Unlock instant, AI-driven research and patent intelligence for your innovation.

Global stereo matching method for video depth information recovery

A technology of stereo matching and depth information, applied in image data processing, instruments, calculations, etc., can solve problems such as unsatisfactory accuracy and applicability, and achieve the effect of improving applicability

Active Publication Date: 2013-09-11
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a global stereo matching method for video depth information recovery in view of the technical problems that the accuracy and applicability of the above-mentioned global stereo matching algorithm are not ideal.

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
  • Global stereo matching method for video depth information recovery
  • Global stereo matching method for video depth information recovery
  • Global stereo matching method for video depth information recovery

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described below in conjunction with the accompanying drawings and examples.

[0029]The present invention realizes a global stereo matching method for restoring video depth information on the basis of the global stereo matching algorithm based on the Markov random field framework mentioned in the background technology. After analyzing the role of each energy item in the energy model of the global stereo matching algorithm based on the Markov random field framework, the inventor invented a dynamic weight allocation strategy based on texture complexity for the algorithm energy model, namely, The appropriate weight is calculated for each pixel based on the texture complexity of the image, so that each item in the energy model has different influences on different pixels, thereby improving the applicability of the energy model and the accuracy of the matching results.

[0030] Specifically, let α p Matching cost weight value for the da...

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

A global stereo matching method for video depth information recovery includes building an energy model on the basis of a Markov random field frame serving as a stereo matching problem, and performing optimization solution on the energy module so as to obtain parallax values of pixels. The energy model is represented in a formula I, wherein D(p, dp) represents pixel data matching cost when the parallax value of a pixel p is dp; S(dp, dq) represents cost caused by smoothness constraint between the pixel p and a pixel q when the pixel p is given the parallax value of dp while the pixel q is given the parallax value of dq; theta refers to a weight parameter, a formula II and a formula III represent corresponding gradient magnitudes of the pixel p in an image I, and a formal IV represents a maximum of the gradient magnitudes in the image I. The method is good in accuracy and applicability.

Description

technical field [0001] The present invention relates to a method for recovering the three-dimensional structure of a scene from a two-dimensional video. More specifically, a global stereo matching method for video depth information recovery is proposed, which can effectively calculate dense point correspondences between images, for Recovering the dense depth map of the video and reconstructing the 3D structure of the scene provide the necessary conditions. Background technique [0002] The restoration of video depth information is the key technology to transform 2D video into 3D video and reconstruct the 3D structure of the scene. As the main step in this process, the accuracy of stereo matching results has a significant impact on the calculation results of depth information. The main work of stereo matching is to find accurate pixel correspondences for all pixels of different image frames by using the similarity relationship of features such as color or gradient between co...

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): G06T7/00
Inventor 袁春梁尚立
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com