Method and device for positioning vehicle, device, and computer readable storage medium

Patent metadata

Field	Value
Publication number	US-11144770-B2
Application number	US-201916560548-A
Country	US
Kind code	B2
Filing date	Sep 4, 2019
Priority date	Sep 29, 2018
Publication date	Oct 12, 2021
Grant date	Oct 12, 2021

Abstract

Embodiments of the present disclosure provide a method and a device for positioning a vehicle, a device, and a computer readable storage medium. The method includes: determining first edge information of a vehicle from an image related to the vehicle and acquired by a sensing device; determining a contour model corresponding to the vehicle; determining second edge information that matches the first edge information from an edge information set associated with the contour model, in which each edge information in the edge information set corresponds to a position of the contour model relative to the sensing device; and determining a position of the vehicle relative to the sensing device based on a position corresponding to the second edge information.

First claim

What is claimed is:

1. A method for positioning a vehicle, comprising:
determining first edge information of a vehicle from an image related to the vehicle and acquired by a sensing device;
determining a contour model corresponding to the vehicle;
determining second edge information that matches the first edge information from an edge information set associated with the contour model, wherein each edge information in the edge information set corresponds to a position of the contour model relative to the sensing device; and
determining a position of the vehicle relative to the sensing device based on a position corresponding to the second edge information.

2. The method according to claim 1 , wherein determining the first edge information comprises:
determining at least one component of the vehicle from the image; and
extracting an edge of each of the at least one component.

3. The method according to claim 1 , wherein determining the contour model comprises:
determining identification information of the vehicle from the image; and
determining the contour model corresponding to the vehicle from a preset contour model set based on the identification information.

4. The method according to claim 3 , wherein the identification information comprises registration plate information of the vehicle.

5. The method according to claim 1 , wherein determining the second edge information that matches the first edge information from the edge information set associated with the contour model comprises:
determining a plurality of points on a first edge indicated by the first edge information;
determining a second edge from a plurality of edges indicated by the edge information set, wherein a sum of distances between the second edge and the plurality of points is less than a preset threshold; and
selecting edge information indicating the second edge from the edge information set, as the second edge information.

6. The method according to claim 1 , wherein determining the position of the vehicle relative to the sensing device comprises:
determining a coordinate and a Euler angle of the vehicle in a roadside coordinate system having the sensing device as an origin.

7. The method according to claim 1 , further comprising:
obtaining a conversion matrix from a roadside coordinate system having the sensing device as an origin to a world coordinate system; and
converting the position of the vehicle relative to the sensing device to a geographic position of the vehicle based on the conversion matrix.

8. The method according to claim 7 , further comprising:
transmitting the geographic position to the vehicle.

9. A device for positioning a vehicle, comprising:
one or more processors; and
a storage device, configured to store one or more programs,
wherein when the one or more programs are executed by the one or more processors, causes the one or more processors to:
determine first edge information of a vehicle from an image related to the vehicle and acquired by a sensing device;
determine a contour model corresponding to the vehicle;
determine second edge information that matches the first edge information from an edge information set associated with the contour model, wherein each edge information in the edge information set corresponds to a position of the contour model relative to the sensing device; and
determine a position of the vehicle relative to the sensing device based on a position corresponding to the second edge information.

10. The device according to claim 9 , wherein in determining the first edge information, the one or more processors are configured to:
determine at least one component of the vehicle from the image; and
extract an edge of each of the at least one component.

11. The device according to claim 9 , wherein in determining the contour model, the one or more processors are configured to:
determine identification information of the vehicle from the image; and
determine the contour model corresponding to the vehicle from a preset contour model set based on the identification information.

12. The device according to claim 11 , wherein the identification information comprises registration plate information of the vehicle.

13. The device according to claim 9 , wherein in determining the second edge information that matches the first edge information from the edge information set associated with the contour model, the one or more processors are configured to:
determine a plurality of points on a first edge indicated by the first edge information;
determine a second edge from a plurality of edges indicated by the edge information set, wherein a sum of distances between the second edge and the plurality of points is less than a preset threshold; and
select edge information indicating the second edge from the edge information set, as the second edge information.

14. The device according to claim 9 , wherein in determining the position of the vehicle relative to the sensing device, the one or more processors are configured to:
determine a coordinate and a Euler angle of the vehicle in a roadside coordinate system having the sensing device as an origin.

15. The device according to claim 9 , wherein the one or more processors are further configured to:
obtain a conversion matrix from a roadside coordinate system having the sensing device as an origin to a world coordinate system; and
convert the position of the vehicle relative to the sensing device to a geographic position of the vehicle based on the conversion matrix.

16. The device according to claim 15 , wherein the one or more processors are further configured to:
transmit the geographic position to the vehicle.

17. A non-transitory computer readable storage medium having stored thereon a computer program that, when executed by a processor, causes a method for positioning a vehicle to be implemented, the method comprising:
determining first edge information of a vehicle from an image related to the vehicle and acquired by a sensing device;
determining a contour model corresponding to the vehicle;
determining second edge information that matches the first edge information from an edge information set associated with the contour model, wherein each edge information in the edge information set corresponds to a position of the contour model relative to the sensing device; and

determining a position of the vehicle relative to the sensing device based on a position corresponding to the second edge information.

Assignees

• Baidu online network technology beijing co ltd

Inventors

• Rui Xiaofei
• Song Shiyu
• Ding Wendong

Classifications

• G06V20/653 Primary

  by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces · CPC title

• G06V20/54

  of traffic, e.g. cars on the road, trains or boats · CPC title

• G06V10/752

  Contour matching · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06V20/584 Primary

  of vehicle lights or traffic lights · CPC title