Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Improved laser point cloud registration method based on covariance matrix

A covariance matrix, laser point cloud technology, applied in image data processing, instruments, 3D modeling and other directions, can solve the problem that the extraction method is easily affected by noise, and achieve the effect of reducing the false matching rate

Pending Publication Date: 2022-04-12
ZHONGBEI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that existing key point extraction methods are easily affected by noise, the present invention provides an improved laser point cloud registration method based on covariance matrix

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
  • Improved laser point cloud registration method based on covariance matrix
  • Improved laser point cloud registration method based on covariance matrix
  • Improved laser point cloud registration method based on covariance matrix

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Developed using Vs2017+PCL1.9.2 under Win10 environment.

[0052] Step 1. Combining tensor voting with the key point selection method of ISS

[0053] Step 1.1, use the built-in method in PCL to get the point cloud neighborhood information.

[0054] Step 1.2, for each sampling point combined with its neighbors, use the above formula (1) to obtain the covariance matrix, and the operation of the matrix can be completed using the C++ matrix library Eigen to obtain the eigenvalues ​​and corresponding eigenvectors of the matrix. Select the eigenvector corresponding to the smallest eigenvalue as the normal vector.

[0055] Step 1.3. Construct the tensor voting matrix according to formula (2) and formula (3). After the matrix is ​​decomposed, it is sorted according to the eigenvalues ​​from large to small to obtain λ 1 ≥λ 2 ≥λ 3 , and then classify the point cloud according to the following relationship:

[0056] (1) If λ 1 >>λ 2 ≈λ 3 ≈0 At this point, the point is a po...

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 an improved laser point cloud registration method based on a covariance matrix, and belongs to the technical field of graphics three-dimensional reconstruction. According to the method, a key point extraction method combining tensor voting and ISS is adopted, so that the method has certain noise immunity, and meanwhile, part of boundary points can be eliminated to reduce the mismatching rate. The construction of the feature descriptor needs to fully contain neighborhood information of the point cloud, is not easily influenced by translation and rotation, and has robustness. The covariance matrix descriptor is a descriptor capable of fully describing neighborhood information, the angle quantity is not influenced by translation and rotation, and the covariance matrix descriptor is an excellent choice for constructing a feature description vector. According to the method, a covariance matrix containing angle quantity and curvature information is constructed in combination with an establishment method of a three-dimensional coordinate system in a feature histogram, a bidirectional nearest distance method is used for feature matching, and the mismatching rate is reduced.

Description

technical field [0001] The invention belongs to the technical field of three-dimensional reconstruction of graphics, and in particular relates to an improved laser point cloud registration method based on a covariance matrix. Background technique [0002] In recent years, 3D point cloud has been widely used in cultural relics protection, digital medical treatment, 3D geographic information system and other fields. Point cloud has become the mainstream 3D model data, and a series of research work has been carried out on point cloud. The point cloud obtained by laser scanning is messy, featureless, contains holes, and is even incomplete. It is difficult to reconstruct on the basis of this point cloud, and the reconstruction result has low precision and large deviation, making it unusable. Therefore, some necessary processing needs to be performed on the scanned point cloud, such as filtering, registration, enhancement, hole repair, etc. The goal is to obtain a complete point ...

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): G06T7/33G06T17/20G06K9/62G06V10/46G06V10/74G06V10/764G06V10/762
Inventor 张元韩浩宇杨晓文韩慧妍庞敏
Owner ZHONGBEI UNIV
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
Eureka Blog
Learn More
PatSnap group products