Automatic deepness image registration method

A depth image and registration technology, which is applied in image analysis, image data processing, instruments, etc., can solve the problems of unstable feature point quality, increase the amount of feature value calculation, and difficult to accurately distinguish regions, so as to speed up the convergence speed and improve the Speed ​​and accuracy, the effect of increasing registration speed

Inactive Publication Date: 2007-12-05
BEIHANG UNIV
View PDF0 Cites 73 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, there are often similar areas on the surface of the model, and it is difficult to accurately distinguish these areas only by local features
In addition, the existing methods often use uniform sampling or random sampling when determining the feature point set. The former often introduces a large number of feature points, thereby further increasing the amount of calculation of feature values; while the latter will reduce the quality of the selected feature points. instability, thus affecting the final registration result

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
  • Automatic deepness image registration method
  • Automatic deepness image registration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] (1) Triangulate the depth image and convert the point cloud data into grid data.

[0029]The depth image is point cloud data, which only contains the coordinate information of the vertices, but does not have the connection relationship between them, that is, the topological information. In order to facilitate operations such as finding boundary points and calculating vertex eigenvalues ​​in the following steps, they need to be meshed first.

[0030] The gridding method is: for each depth image, set P={P 1 ,...,P n} are all the vertices in it. For Pi=(x i ,y i ,z i ), ignoring P i the Z coordinate, that is, P i P projected onto a two-dimensional plane i '=(x i ,y i ), let P’={P 1 ',...,P n '} is the new point set obtained by projection, and then use the two-dimensional Delaunay triangulation (B.Delaunay, Sur la sphère vide, lzvestia Akademii Nauk SSSR, Otdelenie Matematicheskikh i Estestvennykh Nauk, 7:793-800, 1934), to obtain P The connection relationship ...

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 automatic depth-image registration method, which comprises the following steps: proceeding triangularization method for depth image; transmitting point cloud data into triangle grid data; finding the boundary point in the depth image according to the triangle grid data; calculating the character value of non-boundary vertex in the depth image; extracting character point set with projected surface character; finding the mating relationship as corresponding point among character points of two depth images; finding at least three couples of corresponding vertex; calculating the estimating value of movement of two depth images according to the corresponding point; adopting modified ICP algorism to optimize the result; finishing the precise registration of two depth images. The invention improves the speed and precision of registration, which reduces the calculating quantity with simple course.

Description

technical field [0001] The invention belongs to the technical fields of computer virtual reality and computer graphics, in particular, it is a method for automatically reconstructing a three-dimensional model of an object according to depth image data, and the method is successfully applied to the reconstruction of various real object three-dimensional models, especially for the application of Reconstruction of 3D models of precious cultural relics in digital museums. Background technique [0002] Reconstructing the 3D model of objects in the real world is more and more widely used in virtual simulation, computer animation, reverse engineering, computer-aided design, and digital museums. With the continuous development of 3D scanning equipment, it has gradually become a popular 3D modeling method to reconstruct the model of the real object based on the point cloud data collected by the scanning equipment, that is, the depth image. The geometry of real objects is often compl...

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): G06T7/00
Inventor 赵沁平齐越沈旭昆杨棽
Owner BEIHANG 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