Novel point cloud parallel Softassign registering algorithm

A registration algorithm and point cloud technology, applied in the field of image processing, can solve the problem of low point cloud registration accuracy, achieve the effects of avoiding local registration, improving computing speed, and reducing the amount of information

Inactive Publication Date: 2015-03-25
镇江福人网络科技有限公司
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the problem of huge data scale and low point cloud registration accuracy, the present invention proposes a new point cloud parallel

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
  • Novel point cloud parallel Softassign registering algorithm
  • Novel point cloud parallel Softassign registering algorithm
  • Novel point cloud parallel Softassign registering algorithm

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0012] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0013] 1. Use kd-tree for point cloud simplification

[0014] Assuming that the original point cloud data bit X of the three-dimensional object is first established, a kd-tree (K-dimension tree) of the original point is used to quickly search the neighborhood and the nearest point. Kd-tree is a useful data structure for dividing data in k-dimensional space. The 3D object point cloud can create a kd-tree, the main application is data point search, and there are two search methods: one is neighborhood search, which can search for neighborhood points within the specified neighborhood radius; the other is k-neighborhood search, The k data points closest to the target point can be searched, and when k=1, the nearest point is searched. Because kd-tree is a data structure based on space division, when searching for data, starting from the small spac...

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 novel point cloud parallel Softassign registering algorithm. On the basis that CUDA performs parallel acceleration on a Softassign algorithm, by use of a method of combining three-dimensional point cloud discrete curvature estimation and three-dimensional Kd-tree, point-cloud simplification is performed on a three-dimensional object point cloud to enable the simplified three-dimensional object point cloud to maintain sufficient geometric characteristics, and then Softassign registering is performed on the simplified object point cloud, such that the registering precision of the Softassign algorithm in three-dimensional object point cloud registering is improved. The algorithm provided by the invention has the following advantages: first of all, the point-cloud simplification is performed on the three-dimensional object point cloud, such that the information content of the Softassign registering is reduced; and secondly, through the improved Softassign registering algorithm, the registering precision in object cloud registering is improved, and through a parallel acceleration technology, the operation speed of the Softassign registering method is enhanced.

Description

technical field [0001] The invention relates to an image processing technology, in particular to a simplification and registration technology of point cloud information of a three-dimensional object. Background technique [0002] With the development and popularization of 3D scanning technology, recognition and matching based on object 3D shape information has become a new research direction in the field of recognition in recent years. Point cloud matching is one of the key issues in the 3D data matching of object scanning. First, due to the limitation of scanning angle, a complete object depth image cannot be obtained through a 3D scan. The point cloud data obtained by each scan is only part of the surface data. The data of multiple scans are fused and stitched into a complete 3D point cloud data, and the core technology of fusion stitching is 3D registration; secondly, when comparing the shape characteristics of the object model to be recognized with the object model in th...

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): G06T7/00G06T17/00
CPCG06T2207/10028
Inventor 孙晓鹏颜士新
Owner 镇江福人网络科技有限公司
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