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

RGB-D point cloud splicing method and system based on 2D-3D weak feature 3D neighborhood probability matching

A 2D-3D, RGB-D technology, applied in the field of computer vision, can solve the problem that the stability and accuracy of stitching cannot reach a higher standard.

Active Publication Date: 2020-04-10
INST OF AUTOMATION CHINESE ACAD OF SCI +1
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the unassisted point cloud stitching method, the stitching method based on geometric features and the stitching method based on image are widely used, but these two have certain requirements on the geometric features and texture information of the measured object. Stitching stability and accuracy cannot meet high standards

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
  • RGB-D point cloud splicing method and system based on 2D-3D weak feature 3D neighborhood probability matching
  • RGB-D point cloud splicing method and system based on 2D-3D weak feature 3D neighborhood probability matching
  • RGB-D point cloud splicing method and system based on 2D-3D weak feature 3D neighborhood probability matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] In order to solve the problems of the prior art, the inventor has conducted in-depth research and found that:

[0072] The existing technology is a point cloud splicing method based on the combination of the labeling method and the iterative closest point algorithm (ICP). The labeling method is used to complete the initial rough splicing, and then the improved ICP algorithm is used to improve the splicing accuracy.

[0073] However, the labeling method is still unable to measure items that are not suitable for pasting (such as cultural relics, large objects). For this reason, prior art 2 proposes a registration algorithm based on the geometric properties of point clouds. The curvature of the point cloud is used as the registration relationship, and then By introducing the geometric properties of the rigid body transformation vector to eliminate the mismatch points, the algorithm can get effective coupling points to calculate the original transformation matrix, but the ra...

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 RGB-D point cloud splicing method and a system based on 2D-3D weak feature 3D neighborhood probability matching. The method mainly comprises the following steps: calculatingweak feature points of an RGB image corresponding to a point cloud, calculating 2D-3D descriptors of the weak feature points, and performing feature matching based on the 2D-3D descriptors to obtaininitial matching point pairs; screening matching point pairs according to a 3D neighborhood probability method; and performing point cloud splicing and the like. The method has the advantages of highmatching precision, high speed, simple method, easy implementation and the like.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a three-dimensional point cloud splicing method. Background technique [0002] With the rapid development of modern information technology and machine vision, all walks of life have an increasing demand for complete 3D data acquisition, whether robots use 3D information of the environment to navigate, or archaeologists use 3D data Restoration and preservation both rely on processed 3D data. However, the objects in real life cannot scan out the data completely at one time. It needs to scan from multiple angles to collect complete data. Since the data collected from multiple perspectives will not be available because they are not in the same coordinate system, It is necessary to unify the data from different perspectives into the same coordinate system, which is the process of point cloud stitching. Based on this, the degree of automation, stability and accuracy of point cloud stit...

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): G06T3/40G06T7/35
CPCG06T3/4038G06T2207/10012G06T7/35
Inventor 陈梦娟刘希龙顾庆毅马学健
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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