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

Planar feature matching-based point cloud crude splicing method

A feature matching and plane technology, applied in image data processing, instrumentation, computing, etc., can solve problems such as large amount of calculation, demanding shape of point cloud data, and low stitching accuracy.

Active Publication Date: 2017-04-19
SHANDONG UNIV OF SCI & TECH
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the shape requirements of the point cloud data are relatively strict, and point cloud data with obvious points of the same name are required
The disadvantages of this method are: large amount of calculation, high sensitivity to noise points, and low stitching accuracy

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
  • Planar feature matching-based point cloud crude splicing method
  • Planar feature matching-based point cloud crude splicing method
  • Planar feature matching-based point cloud crude splicing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] Below in conjunction with specific embodiment the present invention is described in further detail:

[0074] A point cloud rough stitching method based on plane feature matching, including the following steps:

[0075] a Extract the plane in the point cloud

[0076] a.1 Parameter acquisition and growth of seed plane

[0077] a.11 In the way of human-computer interaction, select part of the data on a certain plane in the point cloud data as the seed plane, denoted as P 0 , using the eigenvalue method to calculate the parameter equation of the seed plane: a 0 x+b 0 y+c 0 z-d 0 = 0;

[0078] Among them, (a 0 ,b 0 ,c 0 ) is the unit normal vector of the plane, d 0 is the distance from the coordinate origin to the plane;

[0079] a.12 Set the threshold of seed plane growth d max ;

[0080] a.13 The direction of the selected range in the three-dimensional space is doubled, and more point cloud data are automatically selected;

[0081] a.14 Judgment that the poin...

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 planar feature matching-based point cloud crude splicing method. The method comprises the following steps of firstly, selecting one part of data in one plane of all point cloud data as a seed plane, calculating the parameter equation of the seed plane based on the feature value method and starting the growth; secondly, conducting the optimizing process based on the RANSAC algorithm, and effectively reducing the influence of noise points; thirdly, selecting four or more pairs of matched planes and calculating the normal vectors of the planes; finally, according to the normal vectors of the four or more pairs of matched planes, respectively calculating a rotation matrix and a translation amount based on the least-squares method to complete the crude splicing of point clouds.

Description

technical field [0001] The invention relates to a point cloud rough splicing method based on plane feature matching. Background technique [0002] High-quality and complete 3D point cloud data is the basis of point cloud post-processing. However, in actual measurement, due to the limitations of the on-site environment and the measurement range of the 3D laser scanner itself, it is necessary to perform multi-station scanning of the target object. Therefore, it is very important to effectively stitch together point cloud data from different viewpoints. At present, the splicing technology at home and abroad is generally divided into two steps: rough splicing and fine splicing. Rough stitching roughly aligns point clouds in different coordinate systems to the same coordinate system, providing initial values ​​for fine stitching. The most commonly used rough stitching methods are mainly the three-point method and the point cloud rough stitching method based on point features. ...

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): G06T3/40G06T7/33
CPCG06T3/4038G06T2207/10028
Inventor 石波崔强宋世柱陈焕剑卢秀山阳凡林
Owner SHANDONG UNIV OF SCI & TECH
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