A Point Cloud Segmentation Method for Scattered Workpieces Based on Improved European Clustering

A point cloud, workpiece technology, applied in image analysis, computer parts, character and pattern recognition, etc., can solve the effect of segmentation, under-segmentation and over-segmentation, etc., to improve efficiency, improve accuracy, and ensure efficiency. Effect

Active Publication Date: 2020-09-11
WUXI XINJIE ELECTRICAL
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Euclidean clustering algorithm classifies points according to the Euclidean distance between points, and classifies points whose distance is smaller than the threshold as the current class, but this method needs to manually set the distance threshold between points. If the threshold is too large or too small, it will Lead to different degrees of under-segmentation and over-segmentation, affecting the effect of segmentation

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
  • A Point Cloud Segmentation Method for Scattered Workpieces Based on Improved European Clustering
  • A Point Cloud Segmentation Method for Scattered Workpieces Based on Improved European Clustering
  • A Point Cloud Segmentation Method for Scattered Workpieces Based on Improved European Clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to illustrate the technical solutions and advantages of the present invention more clearly, the specific implementation manners of the present invention will be described below in conjunction with specific examples and with reference to the accompanying drawings.

[0034] The purpose of the present invention is to divide the point cloud of scattered workpieces in the box into multiple point cloud subsets containing a single workpiece. The main process is divided into the following five parts: point cloud preprocessing, template point cloud offline information registration, target point cloud Edge point extraction, cluster segmentation based on adaptive neighborhood search radius, and edge point completion, such as figure 1 shown.

[0035] The specific implementation steps are:

[0036] (1) Point cloud preprocessing (take the target point cloud P as an example)

[0037] (1.1) The plane equation of the bottom of the box is calculated using the random sampling c...

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 present invention provides a method for point cloud segmentation of scattered workpieces based on improved European clustering, which relates to the field of point cloud segmentation. The method takes into account the inherent chaos and disorder of point clouds of scattered workpieces, and proposes a corresponding scene segmentation scheme. Specifically The steps are: preprocessing the point cloud, including using the RANSAC method to remove background points and iterative radius filtering method to remove outliers; using the offline template point cloud information registration method to provide a parameter selection basis for online segmentation, thereby improving the line quality. The speed of upper segmentation; the idea of ​​removing edge points first, then clustering and segmentation, and finally filling edge points is proposed, which avoids the phenomenon of under-segmentation or over-segmentation in the clustering process. The clustering method of the domain search radius greatly improves the segmentation speed, and the edge point filling preserves the surface characteristics of the workpiece, which is conducive to improving the accuracy of subsequent pose positioning.

Description

technical field [0001] The invention relates to the field of point cloud segmentation, in particular to a point cloud segmentation method for scattered workpieces based on improved European clustering. Background technique [0002] In recent years, with the improvement of the accuracy and cost reduction of 3D scanning equipment, researchers can quickly and accurately obtain the 3D point cloud information of the object surface. Compared with two-dimensional images, point clouds contain the depth information of objects, and have unique advantages and potentials in target recognition and positioning. Therefore, this technology has aroused widespread interest in the field of Random Bin Picking (RBP). focus on. Using 3D scanning equipment to obtain point clouds on the surface of scattered workpieces in the box, combined with point cloud processing algorithms to calculate the pose of a single workpiece, and guide industrial robots to grasp, the efficiency is higher, the speed is ...

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 & AuthorityPatents(China)
IPC IPC(8): G06T7/11G06T7/136G06K9/62
CPCG06T7/11G06T7/136G06T2207/30164G06T2207/10028G06F18/2321
Inventor白瑞林田青华李杜
OwnerWUXI XINJIE ELECTRICAL