Positioning model optimization method, positioning method, positioning device, and storage medium

Patent metadata

Field	Value
Publication number	US-12494028-B2
Application number	US-202118000375-A
Country	US
Kind code	B2
Filing date	Jul 22, 2021
Priority date	Aug 3, 2020
Publication date	Dec 9, 2025
Grant date	Dec 9, 2025

Abstract

A positioning model optimization method, an image-based positioning method and positioning device, and a computer-readable storage medium are provided. The positioning model optimization method includes: inputting a positioning model for a scene, the positioning model including a three-dimensional (3D) point cloud and a plurality of descriptors corresponding to each 3D point in the 3D point cloud; determining, for each 3D point in the 3D point cloud, a plurality of neighboring points of the 3D point, and if a distance relationship between each of the plurality of neighboring points and the 3D point is smaller than a predetermined threshold, outputting the 3D point and the plurality of descriptors corresponding to the 3D point to an optimized positioning model for the scene; and outputting the optimized positioning model for the scene.

First claim

What is claimed is:

1 . A positioning model optimization method, comprising:
inputting a positioning model for a scene, the positioning model comprising a three- dimensional (3D) point cloud and a plurality of descriptors corresponding to each 3D point in the 3D point cloud; determining, for each 3D point in the 3D point cloud, a plurality of neighboring points of the 3D point, and if a distance relationship between each of the plurality of neighboring points and the 3D point is smaller than a predetermined threshold, outputting the 3D point and the plurality of descriptors corresponding to the 3D point to an optimized positioning model for the scene; and outputting the optimized positioning model for the scene, wherein the distance relationship between each of the plurality of neighboring points and the 3D point being smaller than the predetermined threshold comprises: a distance between a plurality of descriptors of each of the plurality of neighboring points and a plurality of descriptors of the 3D point being smaller than a third predetermined threshold, or a distance between each of the plurality of neighboring points and the 3D point being smaller than a second predetermined threshold, and a distance between a plurality of descriptors of each of the plurality of neighboring points and a plurality of descriptors of the 3D point being smaller than a third predetermined threshold.

2 . The positioning model optimization method according to claim 1 , wherein said determining the plurality of neighboring points of the 3D point comprises:
determining a plurality of points in the 3D point cloud, each having a distance to the 3D point that is smaller than a first predetermined threshold, as the plurality of neighboring points.

3 . The positioning model optimization method according to claim 1 , wherein the distance between the plurality of descriptors of each of the plurality of neighboring points and the plurality of descriptors of the 3D point being smaller than the third predetermined threshold comprises:
a distance between an average value of the plurality of descriptors of each of the plurality of neighboring points and an average value of the plurality of descriptors of the 3D point being smaller than the third predetermined threshold.

4 . The positioning model optimization method according to claim 1 , wherein the positioning model for the scene is a 3D positioning model obtained by performing 3D reconstruction of the scene.

5 . A non-transitory computer-readable storage medium, having computer-readable instructions stored thereon, the computer-readable instructions, when executed by a processor, causing the processor to perform the method according to claim 1 .

6 . An image-based positioning method, comprising:
inputting an image to be queried; positioning the image to be queried using an optimized positioning model for a scene to which the image to be queried belongs; and outputting a pose of a camera capturing the image to be queried, wherein the optimized positioning model for the scene is obtained by:
inputting a positioning model for the scene, the positioning model comprising a three-dimensional (3D) point cloud and a plurality of descriptors corresponding to each 3D point in the 3D point cloud;
determining, for each 3D point in the 3D point cloud, a plurality of neighboring points of the 3D point, and if a distance relationship between each of the plurality of neighboring points and the 3D point is smaller than a predetermined threshold, outputting the 3D point and the plurality of descriptors corresponding to the 3D point to an optimized positioning model for the scene; and
outputting the optimized positioning model for the scene,
wherein the distance relationship between each of the plurality of neighboring points and the 3D point being smaller than the predetermined threshold comprises:
a distance between a plurality of descriptors of each of the plurality of neighboring points and a plurality of descriptors of the 3D point being smaller than a third predetermined threshold, or
a distance between each of the plurality of neighboring points and the 3D point being smaller than a second predetermined threshold, and a distance between a plurality of descriptors of each of the plurality of neighboring points and a plurality of descriptors of the 3D point being smaller than a third predetermined threshold.

7 . The positioning method according to claim 6 , wherein said determining the plurality of neighboring points of the 3D point comprises:
determining a plurality of points in the 3D point cloud, each having a distance to the 3D point that is smaller than a first predetermined threshold, as the plurality of neighboring points.

8 . The positioning method according to claim 6 , wherein the distance between the plurality of descriptors of each of the plurality of neighboring points and the plurality of descriptors of the 3D point being smaller than the third predetermined threshold comprises:
a distance between an average value of the plurality of descriptors of each of the plurality of neighboring points and an average value of the plurality of descriptors of the 3D point being smaller than the third predetermined threshold.

9 . The positioning method according to claim 6 , wherein the positioning model for the scene is a 3D positioning model obtained by performing 3D reconstruction of the scene.

10 . An image-based positioning device, comprising:
one or more processors; and one or more memories having computer-readable codes stored therein, the computer-readable codes, when executed by the one or more processors, causing the one or more processors to perform the method according to claim 6 .

11 . A non-transitory computer-readable storage medium, having computer-readable instructions stored thereon, the computer-readable instructions, when executed by a processor, causing the processor to perform the method according to claim 6 .

12 . An image-based positioning device, comprising:
one or more processors; and one or more memories having computer-readable codes stored therein, the computer-readable codes, when executed by the one or more processors, causing the one or more processors to: input a positioning model for a scene, the positioning model comprising a three-dimensional (3D) point cloud and a plurality of descriptors corresponding to each 3D point in the 3D point cloud; determine, for each 3D point in the 3D point cloud, a plurality of neighboring points of the 3D point, and if a distance relationship between each of the plurality of neighboring points and the 3D point is smaller than a predetermined threshold, output the 3D point and the plurality of descriptors corresponding to the 3D point to an optimized positioning model for the scene; and output the optimized positioning model for the scene, wherein the distance relationship between each of the plurality of neighboring points and the 3D point being smaller than the predetermined threshold comprises: a distance between a plurality of descriptors of each of the plurality of neighboring points and a plurality of descriptors of the 3D point being smaller than a third predetermined threshold, or a distance between each of the plurality of neighboring points and the 3D point being smaller than a second predetermined threshold, and a distance between a plurality of descriptors of each of the plurality of neighboring points and a plurality of descriptors of the 3D point being smaller than a third predetermined threshold.

13 . The image-based positioning device according to claim 12 , wherein said determining the plurality of neighbor

Assignees

• Bytedance Inc

Inventors

• Luo Linjie
• Liu Jing
• Chen Zhili
• Wang Guohui
• Yang Xiao
• Yang Jianchao
• Lian Xiaochen

Classifications

• G06T2219/2004

  Aligning objects, relative positioning of parts · CPC title

• G06T2207/30244

  Camera pose · CPC title

• G06T2207/10028

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

• G06T7/75

  involving models · CPC title

• G06T2210/56

  Particle system, point based geometry or rendering · CPC title