Point cloud meshing method, apparatus, device and computer storage media

US10706622B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10706622-B2
Application numberUS-201816157038-A
CountryUS
Kind codeB2
Filing dateOct 10, 2018
Priority dateOct 11, 2017
Publication dateJul 7, 2020
Grant dateJul 7, 2020

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A method, an apparatus, a device and a computer storage media for point cloud meshing are provided. The method includes performing a mesh reconstruction on point cloud data corresponding to a target object to obtain a reconstruction model for characterizing a surface contour of the target object; performing image registration on the reconstruction model with respect to a standard model corresponding to the target object; determining a mesh portion in the registered reconstruction model that does not overlap with the standard model; and removing the determined mesh portion from the registered reconstruction model to obtain a resulting reconstruction model of the target object. The point cloud meshing method repairs a hole structure of an object surface without the need of post-editing manually, and thus is able to improve the efficiency of repairing the hole structure of the object surface.

First claim

Opening claim text (preview).

What is claimed is: 1. A method implemented by one or more computing devices, the method comprising: performing a mesh reconstruction on point cloud data corresponding to a target object to obtain a reconstruction model for characterizing a surface contour of the target object; determining a type of the target object; determining a standard model of the target object based on the type of the target object; performing image registration between the reconstruction model and the standard model; determining a mesh portion in the registered reconstruction model that does not overlap with the standard model by setting a difference operation result that is obtained by performing a three-dimensional graphic Boolean operation on the registered reconstruction model and the standard model as the mesh portion of the registered reconstruction model that does not overlap with the standard model; and removing the determined mesh portion from the registered reconstruction model to obtain a resulting reconstruction model of the target object. 2. The method of claim 1 , wherein the standard model is a generic appearance model of the type to which the target object belongs. 3. The method of claim 1 , wherein performing mesh reconstruction on the point cloud data corresponding to the target object comprises meshing and reconstructing the point cloud data corresponding to the target object based on a Poisson reconstruction algorithm. 4. The method of claim 1 , wherein performing the image registration between the reconstruction model and the standard model comprises performing the image registration on the reconstruction model with respect to the standard model through texture features of a surface of the target object. 5. The method of claim 1 , wherein performing the image registration between the reconstruction model and the standard model comprises performing the image registration on the reconstruction model with respect to the standard model through structural features of the target object. 6. The method of claim 1 , wherein performing the image registration between the reconstruction model and the standard model comprises performing the image registration on the reconstruction model with respect to the standard model through reference points that are set on a surface of the target object. 7. An apparatus comprising: one or more processors; memory; a reconstruction module stored in the memory and executable by the one or more processors to perform a mesh reconstruction on point cloud data corresponding to a target object to obtain a reconstruction model for characterizing a surface contour of the target object; a registration module in the memory and executable by the one or more processors to: determine a type of the target object, determine a standard model of the target object based on the type of the target object, perform image registration between the reconstruction model and the standard model; a determination module in the memory and executable by the one or more processors to determine a mesh portion in the registered reconstruction model that does not overlap with the standard model, the determination module used for setting a difference operation result that is obtained by performing a three-dimensional graphic Boolean operation on the registered reconstruction model and the standard model as the mesh portion of the registered reconstruction model that does not overlap with the standard model; and a removal module in the memory and executable by the one or more processors to remove the determined mesh portion from the registered reconstruction model to obtain a resulting reconstruction model of the target object. 8. The apparatus of claim 7 , wherein the reconstruction module is used for meshing and reconstructing the point cloud data corresponding to the target object based on a Poisson reconstruction algorithm. 9. The apparatus of claim 7 , wherein the registration module is used for performing the image registration between the reconstruction model and the standard model corresponding to the target object through texture features of a surface of the target object. 10. The apparatus of claim 7 , wherein the registration module is used for performing the image registration between the reconstruction model and the standard model corresponding to the target object through structural features of the target object. 11. The apparatus of claim 7 , wherein the registration module is used for performing the image registration between the reconstruction model and the standard model corresponding to the target object through reference points that are set on a surface of the target object. 12. One or more computer readable media storing executable instructions that, when executed by one or more processors, cause the one or more processors to perform acts comprising: performing a mesh reconstruction on point cloud data corresponding to a target object to obtain a reconstruction model for characterizing a surface contour of the target object; determining a type of the target object; determining a standard model of the target object based on the type of the target object; performing image registration between the reconstruction model and the standard model; determining a mesh portion in the registered reconstruction model that does not overlap with the standard model by setting a difference operation result that is obtained by performing a three-dimensional graphic Boolean operation on the registered reconstruction model and the standard model as the mesh portion of the registered reconstruction model that does not overlap with the standard model; and removing the determined mesh portion from the registered reconstruction model to obtain a resulting reconstruction model of the target object. 13. The one or more computer readable media of claim 12 , wherein the standard model is a generic appearance model of the type to which the target object belongs. 14. The one or more computer readable media of claim 12 , wherein performing mesh reconstruction on the point cloud data corresponding to the target object comprises meshing and reconstructing the point cloud data corresponding to the target object based on a Poisson reconstruction algorithm. 15. The one or more computer readable media of claim 12 , wherein performing the image registration between the reconstruction model and the standard model comprises performing the image registration on the reconstruction model with respect to the standard model through texture features of a surface of the target object. 16. The one or more computer readable media of claim 12 , wherein performing the image registration between the reconstruction model and the standard model comprises performing the image registration on the reconstruction model with respect to the standard model through structural features of the target object. 17. The one or more computer readable media of claim 12 , wherein performing the image registration between the reconstruction model and the standard model comprises performing the image registration on the reconstruction model with respect to the standard model through reference points that are set on a surface of the target object.

Assignees

Inventors

Classifications

  • G06T17/20Primary

    Finite element generation, e.g. wire-frame surface description, {tesselation} · CPC title

  • Range image; Depth image; 3D point clouds · CPC title

  • Image-based rendering · CPC title

  • Curved planar reformation of 3D line structures · CPC title

  • General purpose rendering architectures · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US10706622B2 cover?
A method, an apparatus, a device and a computer storage media for point cloud meshing are provided. The method includes performing a mesh reconstruction on point cloud data corresponding to a target object to obtain a reconstruction model for characterizing a surface contour of the target object; performing image registration on the reconstruction model with respect to a standard model correspo…
Who is the assignee on this patent?
Alibaba Group Holding Ltd
What technology area does this patent fall under?
Primary CPC classification G06T17/20. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Jul 07 2020 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 5 related publications on this page (citations in our corpus or others sharing the same primary CPC).