A Denoising Method for Tunnel Point Cloud Based on Low Rank Restoration

A point cloud denoising and tunneling technology, used in image enhancement, image analysis, instruments, etc., can solve the problems that point clouds cannot be unified, and it is difficult to restore geometric information, and achieve good noise removal, normal regularization, strong The effect of robustness

Active Publication Date: 2022-01-25
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the disorder of the point cloud, the point cloud cannot represent the structure of the point cloud in a unified way.
On the other hand, how to effectively deal with low-rank models and recover geometric information from low-rank approximations is also a difficult problem in the field of point clouds
[0005] At present, for the noisy 3D tunnel point cloud data obtained by the existing 3D scanners, how to express the tunnel point cloud structure in a unified way and restore the tunnel geometric information, thereby effectively reducing the impact of noise on the quality of the tunnel point cloud has not yet been proposed. effective solution

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 Denoising Method for Tunnel Point Cloud Based on Low Rank Restoration
  • A Denoising Method for Tunnel Point Cloud Based on Low Rank Restoration
  • A Denoising Method for Tunnel Point Cloud Based on Low Rank Restoration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0056] see figure 1 The flowchart of the present invention, the tunnel point cloud noise removal method of the present invention, specifically includes the following steps:

[0057] Step 1: For example figure 2 The shown input is the tunnel point cloud model map with noise and local projection is performed to generate image 3 The height map of the tunnel point cloud model is shown, and the height map matrix of similar point cloud blocks is constructed. The spec...

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 method for removing noise from tunnel point clouds based on low-rank recovery. The method uses PCA to calculate the normal of each point, and constructs a local coordinate system of each point; uses bilateral filtering to smooth the normal. , rotate the Z axis of each point so that it coincides with the normal; construct a discrete two-dimensional descriptor-height map for each point; for similar tunnel point cloud blocks, combine their height maps into a matrix, and pass the low The method for solving the order matrix approximation obtains the height map after the denoising; the height map after the denoising is mapped to the three-dimensional coordinates of the point to obtain the tunnel point cloud after the denoising, and the method of the present invention is effective in removing the tunnel point cloud noise and due to On the basis of the outliers generated by the attachment structure, the local fine features of the tunnel point cloud model are preserved, and it is especially robust to large noises.

Description

technical field [0001] The invention relates to the technical field of noise processing, in particular to a method for denoising tunnel point clouds based on low-rank recovery. Background technique [0002] In recent years, the development of rail transit has developed in parallel with the expansion of urban construction. In particular, the subway has become an important part of the rail transit system with high capacity. Therefore, the effective realization of quality inspection in the process of subway construction has become a necessary condition for building a safe and reliable rail transit system. [0003] In recent years, with the rapid development of data measurement technology, the tunnel point clouds collected by 3D scanners have become more and more dense and contain rich object information. Therefore, three-dimensional laser scanning technology is basically used to replace the traditional manual detection method for deformation detection of subway tunnels. But ...

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): G06T5/00
CPCG06T5/002G06T2207/10028G06T2207/20028
Inventor 张沅汪俊董竟萱刘树亚鲁德宁
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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