IP Library Granted Patent US 11,816,865
Granted Patent B2
US 11,816,865 · App. 17/535,203 · Granted Nov 14, 2023

Extrinsic camera parameter calibration method, extrinsic camera parameter calibration apparatus, and extrinsic camera parameter calibration system

Inventors: Ye Tao (Shenzhen, CN); Hongzhi Zhang (Shenzhen, CN)
G06T7/80G06T7/337G06T2207/30244G06T2207/30268
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,816,865
App. No.
17/535,203
Granted
Nov 14, 2023
Kind
B2
Abstract

Disclosed are an extrinsic camera parameter calibration method, apparatus and system. The method includes: obtaining a calibration image photographed for a target location in a calibration cabin by a first camera provided therein; determining calibration feature information of the target location from the calibration image; obtaining reference feature information pre-determined from a reference image photographed for a target location in a reference cabin by a second camera provided therein; determining position-posture change data of the first relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image; and determining an extrinsic parameter of the first camera based on the position-posture change data. The extrinsic parameter of the first camera can be calibrated in real time and is closer to a currently actual state of the first camera when used.

Claims (87)

1. An extrinsic camera parameter calibration method, including:

obtaining a calibration image that is photographed for a target location in a calibration cabin by a first camera provided in the calibration cabin;

determining calibration feature information of the target location from the calibration image;

obtaining reference feature information pre-determined from a reference image, wherein the reference image is an image photographed for a target location in a reference cabin by a second camera provided in the reference cabin, wherein the reference cabin is a simulation cabin which is a space structure that is pre-configured as a standard for performing extrinsic parameter calibration to the camera in the calibration cabin, the first camera and the second camera are respectively provided at same locations in the calibration cabin and the reference cabin, and the target location in the reference cabin is the same as the target location in the calibration cabin;

determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image; and

determining an extrinsic parameter of the first camera based on the position-posture change data.

2. The method according to claim 1 , wherein the determining an extrinsic parameter of the first camera based on the position-posture change data includes:

determining whether the position-posture change data meets a preset camera displacement condition;

if the position-posture change data meets the preset camera displacement condition, adjusting the extrinsic parameter of the first camera to an extrinsic parameter corresponding to the position-posture change data based on the position-posture change data; and

if the position-posture change data does not meet the preset camera displacement condition, keeping the extrinsic parameter of the first camera unchanged.

3. The method according to claim 1 , wherein the determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image includes:

determining, based on the reference location and the calibration location, a coordinate transformation matrix for representing a relationship between the calibration location and the reference location, wherein the coordinate transformation matrix includes at least one of the following: a fundamental matrix, an essential matrix, and a homography matrix; and

determining a position-posture change of the second camera relative to the first camera based on the coordinate transformation matrix.

4. The method according to claim 1 , wherein after the determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image, the method further includes:

determining whether the position-posture change data meets a preset position-posture restriction condition of the first camera; and

if the position-posture change data does not meet the preset position-posture restriction condition, adjusting the position-posture change data to position-posture change data meeting the preset position-posture restriction condition.

5. The method according to claim 1 , wherein the determining an extrinsic parameter of the first camera based on the position-posture change data includes:

determining an error of the position-posture change data;

determining a calibration result of the extrinsic parameter of the first camera based on the error; and

if the calibration result indicates unsuccessful calibration, determining the extrinsic parameter of the first camera based on a preset extrinsic parameter.

6. The method according to claim 5 , wherein the determining an error of the position-posture change data includes:

determining a reprojection error of the calibration feature information relative to the reference feature information based on the extrinsic parameter of the first camera; and

determining the error of the position-posture change data based on the reprojection error;

wherein the determining a calibration result of the extrinsic parameter of the first camera based on the error includes:

based on the reprojection error and a preset first calibration success condition, determining whether the extrinsic parameter of the first camera is successfully calibrated.

7. The extrinsic camera parameter calibration system according to claim 1 , wherein when the calibration cabin is a cabin within a vehicle, the target location is a location including a part of a roof and/or a window of the vehicle.

8. An extrinsic camera parameter calibration system including:

a calibration cabin;

a reference cabin;

a first camera provided at a preset location in the calibration cabin;

a second camera provided at a preset location in the reference cabin; and

an extrinsic parameter calibration device configured to implement an extrinsic camera parameter calibration method including:

obtaining a calibration image that is photographed for a target location in the calibration cabin by the first camera;

determining calibration feature information of the target location from the calibration image;

obtaining reference feature information pre-determined from a reference image, wherein the reference image is an image photographed for a target location in the reference cabin by the second camera, wherein the reference cabin is a simulation cabin which is a space structure that is pre-configured as a standard for performing extrinsic parameter calibration to the camera in the calibration cabin, the first camera and the second camera are respectively provided at same locations in the calibration cabin and the reference cabin, and the target location in the reference cabin is the same as the target location in the calibration cabin;

determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image; and

determining an extrinsic parameter of the first camera based on the position-posture change data.

9. The extrinsic camera parameter calibration system according to claim 8 , wherein the determining an extrinsic parameter of the first camera based on the position-posture change data includes:

determining whether the position-posture change data meets a preset camera displacement condition;

if the position-posture change data meets the preset camera displacement condition, adjusting the extrinsic parameter of the first camera to an extrinsic parameter corresponding to the position-posture change data based on the position-posture change data; and

if the position-posture change data does not meet the preset camera displacement condition, keeping the extrinsic parameter of the first camera unchanged.

10. The extrinsic camera parameter calibration system according to claim 8 , wherein the determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image includes:

determining, based on the reference location and the calibration location, a coordinate transformation matrix for representing a relationship between the calibration location and the reference location, wherein the coordinate transformation matrix includes at least one of the following: a fundamental matrix, an essential matrix, and a homography matrix; and

determining a position-posture change of the second camera relative to the first camera based on the coordinate transformation matrix.

11. The extrinsic camera parameter calibration system according to claim 8 , wherein after the determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image, the method further includes:

determining whether the position-posture change data meets a preset position-posture restriction condition of the first camera; and

if the position-posture change data does not meet the preset position-posture restriction condition, adjusting the position-posture change data to position-posture change data meeting the preset position-posture restriction condition.

12. The extrinsic camera parameter calibration system according to claim 8 , wherein the determining an extrinsic parameter of the first camera based on the position-posture change data includes:

determining an error of the position-posture change data;

determining a calibration result of the extrinsic parameter of the first camera based on the error; and

if the calibration result indicates unsuccessful calibration, determining the extrinsic parameter of the first camera based on a preset extrinsic parameter.

13. The extrinsic camera parameter calibration system according to claim 12 , wherein the determining an error of the position-posture change data includes:

determining a reprojection error of the calibration feature information relative to the reference feature information based on the extrinsic parameter of the first camera; and

determining the error of the position-posture change data based on the reprojection error;

wherein the determining a calibration result of the extrinsic parameter of the first camera based on the error includes:

based on the reprojection error and a preset first calibration success condition, determining whether the extrinsic parameter of the first camera is successfully calibrated.

14. The extrinsic camera parameter calibration system according to claim 8 , wherein when the calibration cabin is a cabin within a vehicle, the target location is a location including a part of a roof and/or a window of the vehicle.

15. An electronic device, wherein the electronic device includes:

a processor; and

a memory configured to store processor-executable instructions,

wherein the processor is configured to read the executable instructions from the memory, and execute the instructions to implement an extrinsic camera parameter calibration method including:

obtaining a calibration image that is photographed for a target location in a calibration cabin by a first camera provided in the calibration cabin;

determining calibration feature information of the target location from the calibration image;

obtaining reference feature information pre-determined from a reference image, wherein the reference image is an image photographed for a target location in a reference cabin by a second camera provided in the reference cabin, wherein the reference cabin is a simulation cabin which is a space structure that is pre-configured as a standard for performing extrinsic parameter calibration to the camera in the calibration cabin, the first camera and the second camera are respectively provided at same locations in the calibration cabin and the reference cabin, and the target location in the reference cabin is the same as the target location in the calibration cabin;

determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image; and

determining an extrinsic parameter of the first camera based on the position-posture change data.

16. The electronic device according to claim 15 , wherein the determining an extrinsic parameter of the first camera based on the position-posture change data includes:

determining whether the position-posture change data meets a preset camera displacement condition;

if the position-posture change data meets the preset camera displacement condition, adjusting the extrinsic parameter of the first camera to an extrinsic parameter corresponding to the position-posture change data based on the position-posture change data; and

if the position-posture change data does not meet the preset camera displacement condition, keeping the extrinsic parameter of the first camera unchanged.

17. The electronic device according to claim 15 , wherein the determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image includes:

determining, based on the reference location and the calibration location, a coordinate transformation matrix for representing a relationship between the calibration location and the reference location, wherein the coordinate transformation matrix includes at least one of the following: a fundamental matrix, an essential matrix, and a homography matrix; and

determining a position-posture change of the second camera relative to the first camera based on the coordinate transformation matrix.

18. The electronic device according claim 15 , wherein when the calibration cabin is a cabin within a vehicle, the target location is a location including a part of a roof and/or a window of the vehicle,

or,

after the determining position-posture change data of the first camera relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image, the method further includes:

determining whether the position-posture change data meets a preset position-posture restriction condition of the first camera; and

if the position-posture change data does not meet the preset position-posture restriction condition, adjusting the position-posture change data to position-posture change data meeting the preset position-posture restriction condition.

19. The electronic device according to claim 15 , wherein the determining an extrinsic parameter of the first camera based on the position-posture change data includes:

determining an error of the position-posture change data;

determining a calibration result of the extrinsic parameter of the first camera based on the error; and

if the calibration result indicates unsuccessful calibration, determining the extrinsic parameter of the first camera based on a preset extrinsic parameter.

20. The electronic device according to claim 19 , wherein the determining an error of the position-posture change data includes:

determining a reprojection error of the calibration feature information relative to the reference feature information based on the extrinsic parameter of the first camera; and

determining the error of the position-posture change data based on the reprojection error;

wherein the determining a calibration result of the extrinsic parameter of the first camera based on the error includes:

based on the reprojection error and a preset first calibration success condition, determining whether the extrinsic parameter of the first camera is successfully calibrated.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 24, 2021
From: TAO, YE; ZHANG, HONGZHI
To: SHENZHEN HORIZON ROBOTICS TECHNOLOGY CO., LTD.
Reel/Frame 058209/0108 →
Priority Claims (1)
CN 202011344151.0 · Nov 25, 2020 · national
Continuity (1)
Related Publication 20220164987A1 · May 26, 2022
Cited By (1)
US 12,272,101