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

Pipeline 3D reconstruction method, system, medium and equipment based on deep learning

A technology of deep learning and 3D reconstruction, applied in the field of 3D pipeline reconstruction based on deep learning, to achieve good accuracy and convergence, prevent errors, and high robustness

Active Publication Date: 2021-08-13
SHANDONG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to solve the deficiencies of the prior art, the present disclosure provides a method, system, medium and equipment for three-dimensional pipeline reconstruction based on deep learning, which reduces the complexity of common pipeline reconstruction problems to a combination of component detection and model fitting problems, Accurate 3D reconstruction of the pipeline is achieved

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
  • Pipeline 3D reconstruction method, system, medium and equipment based on deep learning
  • Pipeline 3D reconstruction method, system, medium and equipment based on deep learning
  • Pipeline 3D reconstruction method, system, medium and equipment based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] In piping design, a piping scene is assembled from piping components and piping supports. In this embodiment, due to the complexity of the problem, the pipeline components are mainly considered, and supports such as floors and fences are ignored.

[0044] Choose from six types of components as primitives: pipes, flanges, elbows, reducers, tees, and crosses. Points that do not belong to these six types of components are marked with an additional label. In this embodiment, the classes of components are learned, thus reducing the complexity of the common pipeline reconstruction problem to a combined component detection and model fitting problem.

[0045] In this embodiment, a priori-based learning method is adopted, and a deep learning network is trained to learn candidate features of 3D point clouds. The a priori detection of generating training sets and designing training networks is usually error-prone, so a combination of clustering and graph technology is used to fi...

Embodiment 2

[0129] Embodiment 2 of the present disclosure provides a pipeline three-dimensional reconstruction system based on deep learning, including:

[0130] The point cloud learning module is configured to: use a deep learning method to learn the characteristics of the point cloud, and at least obtain the category of the component to which the point belongs, the radius of the component to which the point belongs, and the direction vector of the point;

[0131] The candidate instance obtaining module is configured to: use the radius of the component to which the point belongs and the direction vector of the point to calculate the axis point, and combine the category labels of the component to which the point belongs to cluster the axis point to obtain a candidate instance;

[0132] The graph structure component module is configured to: use a graph-based method to obtain the connection relationship between different component instances, and use the components as nodes to form a graph st...

Embodiment 3

[0136] Embodiment 3 of the present disclosure provides a medium on which a program is stored, and when the program is executed by a processor, the steps in the deep learning-based pipeline three-dimensional reconstruction method described in Embodiment 1 of the present disclosure are implemented.

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 disclosure provides a method, system, medium, and device for three-dimensional pipeline reconstruction based on deep learning, which relate to the technical field of three-dimensional reconstruction of pipelines. The deep learning method is used to learn the characteristics of point clouds, and at least the category of the component to which the point belongs and the component of the point to which the point belongs are obtained. The radius and the direction vector of the point; use the radius of the component to which the point belongs and the direction vector of the point to calculate the axis point, and combine the category labels of the component to which the point belongs to cluster the axis points to obtain candidate instances; use a graph-based method to obtain the relationship between different candidate instances The connection relationship between components is used to form the structure of the graph; the actual three-dimensional component model is used to replace the nodes in the graph to complete the reconstruction of the entire pipeline; The complexity of the pipeline reconstruction problem is reduced to a combination of component detection and model fitting problems, enabling accurate 3D reconstruction of pipelines.

Description

technical field [0001] The present disclosure relates to the technical field of three-dimensional pipeline reconstruction, and in particular to a method, system, medium and equipment for three-dimensional pipeline reconstruction based on deep learning. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] High-quality 3D models of power plants, petrochemical plants, and other plants are critical in many applications, including disaster simulation, monitoring, and executive training. Industrial sites are built according to specific plans, often combined with 3D CAD models. However, building a complete and accurate 3D model is a daunting task. Also, these models may not exist in older facilities or may not reflect the current look of the venue. Today, modern laser scanners can capture 3D surfaces and geometries with high precision, generating...

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 Patents(China)
IPC IPC(8): G06T17/00G06N20/00
CPCG06T17/00G06N20/00
Inventor 屠长河程莉莉魏卓孙铭超辛士庆安德劳李扬彦陈宝权
Owner SHANDONG UNIV
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