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

Point cloud segmentation method and device

A point cloud and point cloud data technology, applied in image analysis, image enhancement, instruments, etc., can solve problems such as long time consumption, influence of manipulator grasping accuracy, and effect of point cloud registration, so as to improve positioning accuracy, The effect of improving the efficiency of object capture and avoiding the introduction of noise points

Active Publication Date: 2019-12-24
中国大恒(集团)有限公司 +1
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1) Acquisition, reconstruction and splicing of point cloud data take a long time;
[0005] 2) During the fusion (splicing) process of multi-piece point cloud data, new noise points will be introduced in the overlapping part of the point cloud data, which will affect the grasping accuracy of the manipulator;
[0006] 3) When there are holes in the point cloud data or the point cloud data is missing, it will affect the point cloud registration effect

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
  • Point cloud segmentation method and device
  • Point cloud segmentation method and device
  • Point cloud segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 2 As shown, the present embodiment provides a method for point cloud segmentation, including:

[0041] Step 1, obtain the first point cloud data set P(x, y, z) of the object to be grasped, and calculate the first point cloud data set P( x, y, z) the x-axis point cloud data set rotated around the x-axis and the y-axis point cloud data set rotated around the y-axis, and the first point cloud data set P(x, y, z), x-axis The point cloud data set and the y-axis point cloud data set are merged to generate the second point cloud data set P'(x, y, z), where the x-axis point cloud data set and the y-axis point cloud data set are recorded as rotation data set.

[0042] In this embodiment, the normal phase direction of the object to be grasped is set as the z-axis, its advancing direction as the y-axis, and the right side of its advancing direction as the x-axis, and a three-dimensional rectangular coordinate system is established. A single 3D sensor for a singl...

Embodiment 2

[0117] This embodiment provides a point cloud segmentation device, using the point cloud segmentation method as in the first embodiment to capture the object to be grasped, the point cloud segmentation device is arranged above the transmission device, connected to the movement mechanism, and the point cloud segmentation The device includes a three-dimensional sensor, and the three-dimensional sensor is used to perform a single scan on the object to be grasped above the conveying device to generate the first point cloud data set. The point cloud segmentation device also includes: a data set generation unit, an angle determination unit, a segmentation unit and information generating unit;

[0118] In this embodiment, the normal phase direction of the object to be grasped is set as the z-axis, its advancing direction as the y-axis, and the right side of its advancing direction as the x-axis, and a three-dimensional rectangular coordinate system is established. A single 3D sensor ...

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 point cloud segmentation method and device, wherein the method comprises the steps of 1, obtaining a first point cloud data set of a to-be-grabbed object, calculating a rotation data set of the first point cloud data set according to a preset step size increment, and combining the first point cloud data set and the rotation data set to generate a second point cloud data set; 2, according to a preset point cloud projection resolution, selecting a three-dimensional point with a maximum z coordinate value in the second point cloud data set, performing projection, and determining a selection angle according to a minimum entropy value of the projection image; 3, calculating a histogram and a segmentation position of the projection image according to the selection angle, and generating a point cloud segmentation result of the to-be-grabbed object; and 4, according to a point cloud segmentation result, determining a center coordinate and a clamping jaw posture of a grabbing plane, and according to the center coordinate and the clamping jaw posture, generating the grabbing information. According to the technical scheme, the object grabbing efficiency is improved by utilizing the influence of the offset data on the positioning.

Description

technical field [0001] The present application relates to the technical field of machine vision, in particular, to a point cloud segmentation method and a point cloud segmentation device. Background technique [0002] In common industrial applications, manipulators are mostly responsible for handling and assembly work, such as loading and unloading of processing equipment, installation and welding of workpieces, etc. The guidance of the manipulator can be written in advance through the program, and each time it moves according to a fixed point, it can also be guided by a visual sensor or a 3D sensor. Obviously the latter is more flexible and adaptable. In order to make the grasping field of view larger and the equipment to operate more flexibly, we will use the sensor and the robot arm to follow up the project implementation. Due to the limited load of the manipulator, we need to use the most streamlined collection equipment to obtain relevant data to guide the work of the...

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): G06T7/11G06T7/215
CPCG06T7/11G06T7/215G06T2207/10028G06T2207/20032
Inventor 彭潇
Owner 中国大恒(集团)有限公司
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