Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Improved point cloud splicing method of icp object to be tested by fusing fast point feature histogram

A point feature histogram and point cloud splicing technology, applied in the field of point cloud processing, can solve the problems of low splicing efficiency, low splicing accuracy, and insufficient stability, so as to avoid falling into local optimum, improve the difficulty of falling into local optimum, The effect of improving the stability of the algorithm

Active Publication Date: 2022-06-24
ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of low splicing accuracy, insufficient stability, and low splicing efficiency in the point cloud splicing process, the present invention proposes an improved iterative closest point (ICP) point cloud splicing method that fuses fast point feature histograms. Improve on the basis of point iteration, use the k-d tree search method, combine the Euclidean distance of the point cloud and the direction angle threshold to remove the wrong point pair, and realize the efficient and accurate splicing of the point cloud

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
  • Improved point cloud splicing method of icp object to be tested by fusing fast point feature histogram
  • Improved point cloud splicing method of icp object to be tested by fusing fast point feature histogram
  • Improved point cloud splicing method of icp object to be tested by fusing fast point feature histogram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0062] like figure 2 As shown, the embodiment according to the method of the present invention and its implementation process include the following steps:

[0063] The specific implementation adopts a structured light detection system, such as figure 1 As shown, the structured light detection system includes a projector, a computer, a CCD camera and a platform. The object to be measured is placed on the platform, the projector is connected to the computer, the projector and the camera are placed on both sides of the object to be measured, and the lens of the projector The lens of the camera and the CCD camera are all facing the object to be measured; the object to be measured is placed on the desktop, the computer sends out a signal of the input grating pattern, which is input to the projector to generate a fringe grating as a grating light source to il...

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 improved ICP point cloud splicing method of an object to be measured by fusing fast point feature histograms. Project the standard sinusoidal digital grating onto the surface of the object to be measured, and shoot the fringe images of the projected standard sinusoidal digital grating on the object surface from different angles of view through the CCD camera to obtain a multi-angle shooting point cloud; for the two shooting point clouds that need to be spliced, each Construct a k-d tree from each shooting point cloud and interpolate to obtain the interpolated point cloud; for splicing two interpolated point clouds, calculate the fast point feature histogram, perform random sampling consistent transformation to obtain the point cloud result; use the improved iterative closest point The point cloud obtained by the first interpolation point cloud after fine registration is obtained by means of processing; the point cloud is superimposed and meshed to realize the splicing of two shooting point clouds from different perspectives. The invention has low requirements on the initial position of the spliced ​​point cloud, significantly improves the robustness and is not easy to fall into a local optimum, improves the splicing accuracy, realizes accurate splicing of point clouds under multi-view angles, and can meet the actual industrial application requirements.

Description

technical field [0001] The present invention relates to a point cloud processing method and system, in particular to an improved iterative closest point (ICP) point cloud splicing method that fuses fast point feature histograms. Background technique [0002] Multi-view point cloud stitching is an important part of reconstructing object surface data. This technology has always been a research hotspot and difficulty in the fields of reverse engineering, computer vision, surface quality detection and photogrammetry. The core of point cloud splicing is to find the coordinate transformation parameters R (rotation matrix) and T (translation matrix), so that the distance of the three-dimensional data measured from two perspectives after coordinate transformation is the smallest. [0003] At present, point cloud stitching methods mainly fall into the following two categories. Automatically stitching on the basis of manual assistance, using the motion positioning device to calculate...

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): G06T17/00G06T7/30
CPCG06T7/30G06T17/005G06T2207/10028
Inventor 赵昕玥连巧龙何再兴张树有谭建荣
Owner ZHEJIANG 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
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