Rapid disperse three-dimensional point cloud filtering method

A three-dimensional point cloud, discrete point technology, applied in the field of robot vision, can solve the problems of uneven data density, affecting work, huge data volume, etc., to achieve the effect of improving density unevenness, fast and effective compression and filtering

Inactive Publication Date: 2014-05-28
ZHEJIANG SHUREN UNIV
View PDF2 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the collected point cloud data is often very dense, and the amount of data is generally very large, and due to the interference of some factors, the data density is usually not very uniform, and many outliers and noises are superimposed, which will seriously affect the follow-up work, such as Processes such as point cloud data search or 3D reconstruction

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
  • Rapid disperse three-dimensional point cloud filtering method
  • Rapid disperse three-dimensional point cloud filtering method
  • Rapid disperse three-dimensional point cloud filtering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further described below in conjunction with the accompanying drawings.

[0026] Fixedly place a depth camera in three-dimensional space, figure 1 To obtain the discrete point cloud of the target. First, create a 3D voxel grid for the point cloud data, each voxel grid volume is 2cm 3 The cube, all points in the voxel grid finally use a center of gravity point express. Then the mean and variance of the global distance of the discrete point cloud are calculated respectively, and the distance threshold value of the global distance of the discrete point cloud is calculated. Finally, set the number of domain points of a certain point to 45, and calculate the average distance between a certain point and its domain points And judge the relationship between it and the global distance threshold, when The point is judged as an outlier point (outliers); when Determine that the point is an inlier.

[0027] Such as figure 2 It is a schematic...

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

A rapid disperse three-dimensional point cloud filtering method is characterized in that the point cloud filtering method comprises the following steps: 1) obtaining a disperse point cloud of a three-dimensional object by utilizing a fixed depth camera; 2) establishing a three-dimensional voxel grid for point cloud data, all points in the voxel grid being expressed by a gravity point finally; 3) calculating the mean value and variance of global distance of the disperse point cloud; 4) calculating threshold value of global distance of the disperse point cloud; and 5) calculating average distance between a certain point and field points of the certain point and judging the relationship between the certain point and the global distance threshold value. The advantages of the method are that the mass discrete point cloud data can be rapidly and effectively compressed and filtered; nonuniformity of the density of the point cloud data can be effectively improved; and outliers beyond reference range can be rapidly removed.

Description

technical field [0001] The invention relates to the field of robot vision, in particular to a three-dimensional point cloud filtering method. Background technique [0002] With the development of high-precision laser scanning equipment and computer vision technology, point cloud technology has also been more and more used in surface reconstruction and 3D simulation. However, the collected point cloud data is often very dense, and the amount of data is generally very large, and due to the interference of some factors, the data density is usually not very uniform, and many outliers and noises are superimposed, which will seriously affect the follow-up work, such as The process of searching or 3D reconstruction of point cloud data. [0003] For the filtering of point cloud data, there are mainly several algorithms such as filtering algorithm based on mathematical morphology, filtering algorithm based on triangulation network, and wavelet layering. Scholars at home and abroad ...

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): G06T5/50
Inventor 胡峰俊
Owner ZHEJIANG SHUREN 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