Vehicle, vehicle positioning system, and vehicle positioning method

Patent metadata

Field	Value
Publication number	US-11024055-B2
Application number	US-201916508471-A
Country	US
Kind code	B2
Filing date	Jul 11, 2019
Priority date	Nov 29, 2018
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

A vehicle, a vehicle positioning system and a vehicle positioning method are provided. The vehicle positioning system includes a 2D image sensor, a 3D sensor and a processor. The 2D image sensor is configured for obtaining 2D image data. The 3D sensor is configured for obtaining 3D point cloud data. The processor is coupled to the 2D image sensor and the 3D sensor, and configured for merging the 2D image data and the 3D point cloud data to generate 3D image data, identifying at least one static object from the 2D image data, obtaining 3D point cloud data of the static object from the 3D image data based on each one of the at least one static object, and calculating a vehicle relative coordinate of the vehicle based on the 3D point cloud data of the static object.

First claim

What is claimed is:

1. A vehicle positioning system, comprising:
a 2D image camera configured for capturing images at different angles and views of field to obtain 2D image data;
a LiDAR sensor configured for receiving optical signals relating to a reflected object within a scanning range to obtain 3D point cloud data; and
a processor coupled to the 2D image camera and the LiDAR sensor and configured for:
mapping a pixel point of the 2D image data to the 3D point cloud data by using transformation matrix to merge the 2D image data and the 3D point cloud data according to an alignment algorithm to generate 3D image data;
identifying at least one static object from the 2D image data to obtain 3D point cloud data of the static object from the 3D image data that is generated by merging the 2D image data and the 3D point cloud data based on each one of the at least one static object; and
calculating a vehicle relative coordinate of a vehicle based on the 3D point cloud data of the static object by iteratively comparing the 3D point cloud data with map point cloud data and calculating a mean squared distance of a point cloud data of the vehicle and the 3D point cloud data of the static object via a positioning algorithm.

2. The vehicle positioning system of claim 1 , wherein the vehicle relative coordinate maps to predefined map information stored in a storage circuit in advance to obtain 3D vehicle absolute coordinate of the vehicle.

3. The vehicle positioning system of claim 1 , wherein the 3D point cloud data of the static object map to predefined map information stored in a storage circuit in advance to obtain 3D object absolute coordinate of the static object.

4. The vehicle positioning system of claim 3 , wherein the processor calculates 3D vehicle absolute coordinate of the vehicle based on the 3D object absolute coordinate of the static object.

5. The vehicle positioning system of claim 1 , wherein the 2D image camera is a charge coupled element camera or a complementary metal oxide semiconductor camera.

6. A vehicle positioning method applicable to a vehicle positioning system, the vehicle positioning method comprising:
obtaining 2D image data;
obtaining 3D point cloud data;
mapping a pixel point of the 2D image data to the 3D point cloud data by using transformation matrix to merge the 2D image data and the 3D point cloud data according to an alignment algorithm to generate 3D image data;
identifying at least one static object from the 2D image data;
obtaining 3D point cloud data of the static object from the 3D image data that is generated by merging the 2D image data and the 3D point cloud data based on the static object; and
calculating a vehicle relative coordinate of a vehicle based on the 3D point cloud data of the static object by iteratively comparing the 3D point cloud data with map point cloud data and calculating a mean squared distance of a point cloud data of the vehicle and the 3D point cloud data of the static object via a positioning algorithm.

7. The vehicle positioning method of claim 6 , further comprising mapping the vehicle relative coordinate to predefined map information stored in advance to obtain 3D vehicle absolute coordinate of the vehicle.

8. The vehicle positioning method of claim 6 , further comprising mapping the 3D point cloud data of the static object to predefined map information stored in advance to obtain 3D object absolute coordinate of the static object.

9. The vehicle positioning method of claim 8 , further comprising calculating 3D vehicle absolute coordinate of the vehicle based on the 3D object absolute coordinate of the static object.

10. A vehicle equipped with a vehicle positioning system, the vehicle comprising:
a 2D image camera configured for capturing images at different angles and views of field to obtain 2D image data;
a LiDAR sensor configured for receiving optical signals relating to a reflected object within a scanning range to obtain 3D point cloud data; and
a processor coupled to the 2D image camera and the LiDAR sensor and configured for:
mapping a pixel point of the 2D image data to the 3D point cloud data by using transformation matrix to merge the 2D image data and the 3D point cloud data according to an alignment algorithm to generate 3D image data;
identifying at least one static object from the 2D image data to obtain 3D point cloud data of the static object from the 3D image data that is generated by merging the 2D image data and the 3D point cloud data based on each one of the at least one static object; and
calculating a vehicle relative coordinate of the vehicle based on the 3D point cloud data of the static object by iteratively comparing the 3D point cloud data with map point cloud data and calculating a mean squared distance of a point cloud data of the vehicle and the 3D point cloud data of the static object via a positioning algorithm.

11. The vehicle of claim 10 , wherein the vehicle relative coordinate maps to predefined map information stored in a storage circuit in advance to obtain 3D vehicle absolute coordinate of the vehicle.

12. The vehicle of claim 10 , wherein the 3D point cloud data of the static object maps to predefined map information stored in a storage circuit in advance to obtain 3D object absolute coordinate of the static object.

13. The vehicle of claim 12 , wherein the processor calculates 3D vehicle absolute coordinate of the vehicle based on the 3D object absolute coordinate of the static object.

14. The vehicle of claim 10 , wherein the 2D image camera is a charge coupled element camera or a complementary metal oxide semiconductor camera.

Assignees

• Ind Tech Res Inst

Inventors

• Hsu Bo-Chun
• Nien Wei-Po
• Wu Yi-Ling
• Lin Hsiu-Yu
• CHEN Shi-xin
• Jeng An-Kai
• Yang Chung-Hsien

Classifications

• G06T2207/10028

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

• G01S17/931 Primary

  of land vehicles · CPC title

• G01S17/42

  Simultaneous measurement of distance and other co-ordinates (indirect measurement G01S17/46) · CPC title

• G01S7/4817

  relating to scanning · CPC title

• G01S17/89

  for mapping or imaging · CPC title