Method for recovering three-dimensional geometric information from image

A technology in 3D geometry and images, applied in the field of computer vision, can solve problems such as difficult heuristic constraints

Inactive Publication Date: 2010-09-15
PEKING UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Many monocular cues not only rely on prior knowledge, but also rely on the overall context information, so it is not only difficult to use heuristic constraints, but also difficult to speculate from the local part of the image

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
  • Method for recovering three-dimensional geometric information from image
  • Method for recovering three-dimensional geometric information from image
  • Method for recovering three-dimensional geometric information from image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The following examples are used to illustrate the present invention, but not to limit the scope of the present invention.

[0038] The technical scheme of the present invention is simply described as follows: First, obtain training data. Use a laser scanner and a calibrated camera to simultaneously acquire the pictures of the scene and its corresponding depth map; then extract features from each image in the training library, and use the joint Laplacian Markov random field model to describe the image features Corresponding to the relationship between the probabilities of different depths and the depth values ​​of adjacent positions, the model parameters are obtained by learning the training library. Then build a two-layer graph structure to combine high-resolution binocular cues and low-resolution monocular cues; use the parameters obtained in the previous step to define the energy term of the image block layer, and add it as a constraint to the traditional The stereo mat...

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 relates to a method for restoring 3D geometric information from images. The method comprises the following steps: a large amount of scene images and the corresponding depth maps thereof are obtained and used as a training library; the images are divided into image blocks, the probabilities thereof corresponding to different depths are described by the statistical learning method to obtain different parameter values; a graph structure including an image block layer, a pixel layer, and the edges connecting the pixels and the corresponding image blocks is constructed for the image pairs used for the scene reconstruction; the energy term of the graph structure is defined by the parameters obtained from the statistical learning; the energy term is taken as a constraint and added to an image describing parallax relation among pixels based on the conventional stereo matching; and a parallax image of the two images is solved.

Description

Technical field [0001] The invention relates to the field of computer vision, in particular to a method for recovering three-dimensional geometric information from an image. Background technique [0002] Stereo matching has always been an important issue in computer vision and photogrammetry. The two images record real-world scenes from very close perspectives. Binocular cues refer to objects projected at different positions on the two imaging planes, and the difference in position changes with the depth of the object. In the past few decades, a large number of stereo vision systems have been proposed, which has made considerable progress in the field of research. However, due to the pathological nature of the problem itself, it still has not been completely resolved. [0003] Among the existing stereo matching methods, the graph-based method is the most popular technique among them. It can get a smooth disparity map consistent with the observed data. A typical approach is to u...

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 Patents(China)
IPC IPC(8): G06T7/00
Inventor 马祥音李仁举查红彬英向华
Owner PEKING 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