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

Large-scale scene free bending pipeline detection and point cloud completion method based on four-dimensional space-time perception

A technology of curved pipelines and large scenes, applied in the fields of industrial vision and 3D vision, to achieve the effect of wide applicability, high efficiency applicability, avoiding target scale changes and imaging projection deformation

Active Publication Date: 2021-02-26
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY +1
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technology of the present invention solves the problem: Aiming at the detection of three-dimensional free-bending pipelines on the body surface of industrial large-scale manufacturing parts, a large-scene free-bending pipeline detection and point cloud completion method with four-dimensional perception in time-space domain is provided, which can be adapted to be distributed in Pipelines with different thickness and bending degrees in complex large scenes can overcome the pipeline partition caused by pipeline connectors, realize the complete detection of multiple pipelines and complete the pipeline 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
  • Large-scale scene free bending pipeline detection and point cloud completion method based on four-dimensional space-time perception
  • Large-scale scene free bending pipeline detection and point cloud completion method based on four-dimensional space-time perception
  • Large-scale scene free bending pipeline detection and point cloud completion method based on four-dimensional space-time perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0040] The overall realization flowchart of a specific embodiment of the present invention, as figure 1 Specifically, the following steps are included:

[0041] Step 11: Evenly sample 3D points in the 3D point cloud of the scene to be inspected, set up a spherical support domain with a certain radius with each sampling point as the center, and extract the 3D point cloud blocks covered by each support domain; calculate each point cloud block in the ...

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 large-scale scene free bending pipeline detection and point cloud completion method based on four-dimensional space-time perception, and the method comprises the steps: uniformly obtaining three-dimensional sampling points in a three-dimensional point cloud of a to-be-detected scene, building a spherical support domain, building a point pair type cylindrical feature set in a three-dimensional point cloud block, carrying out the second-class decision according to the feature clustering, and achieving the automatic detection of three-dimensional pipeline surface featurepoints; establishing a parameterized geometric model and a time sequence parameter estimation model of the pipeline in a four-dimensional time-space domain, solving a local pipeline section axis where pipeline feature points are located according to the geometric model to serve as a time domain initial state, and iterating towards the two ends of the axis at the initial moment in combination withthe time sequence parameter estimation model to carry out continuous pipeline section parameter estimation; obtaining a three-dimensional free bending pipeline surface point cloud fusing the three-dimensional geometrical information and the time domain related information and geometrical parameters thereof; reconstructing the pipeline surface point cloud according to the geometric model and iteratively optimizing to complete the pipeline point cloud in the original scene. The method has the characteristics of high calculation efficiency and point cloud noise resistance.

Description

technical field [0001] The invention relates to a feature detection and point cloud completion method of a free-bending pipeline facing a three-dimensional point cloud of a large scene, belonging to the field of industrial vision, in particular to the field of three-dimensional vision. Background technique [0002] In the field of industrial manufacturing and assembly, it is often faced with large-scale operation objects, such as aeroengines. The surface structure of the airframe is complex, and the types and quantities of parts are numerous and densely distributed. Each part plays an important role in the operation quality and safety of the airframe. The pipeline is an important part of the aero-engine. It is densely and staggeredly distributed in the aero-engine body. It mainly transports media such as oil and gas for the engine and the aircraft to ensure the stable operation of the engine. [0003] Due to the influence of temperature and pressure in the operating environ...

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): G06F30/17G06F30/27G06K9/62G06T17/20G06F111/10G06F111/04G06F113/14
CPCG06F30/17G06F30/27G06T17/20G06F2111/10G06F2111/04G06F2113/14G06F18/2321
Inventor 张洁孙军华
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
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