Method and apparatus for camera calibration

• US 10,304,210 B2
• Filed: 05/25/2017
• Issued: 05/28/2019
• Est. Priority Date: 05/25/2017
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Lewis, Allan, Naserian, Mohammad
• Primary Examiner(s): Aghevli, Reza
• Application Number:
  US15/605,470
• Publication Number:
  US 20180342082A1
• Time in Patent Office: 733 Days
• Field of Search: None
• CPC Class Codes: B60R 2300/308 by overlaying the real scene, e.g. through a head-up display on the windscreen
• CPC Class Codes: B60R 2300/402 Image calibration
• CPC Class Codes: B60R 2300/808 for facilitating docking to a trailer
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/10 Segmentation; Edge detection motion-based segmentation G06T7/215
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/80 Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
• CPC Class Codes: H04N 17/002 for television cameras

Abstract

A method and apparatus for calibrating a camera are provided. The method includes: detecting at least one edge of fixed object in image received from a camera, determining at least one horizontal midpoint of the at least one edge, calculating a first pixel distance between the determined at least one horizontal midpoint and a pre-stored at least one horizontal midpoint, calculating second pixel distances between a plurality of points on the detected at least one edge of the fixed object and a pre-stored plurality of points of the at least one edge of the fixed object, determining whether to recalibrate the camera based on the first pixel distance and the second pixel distances, and recalibrating the camera if the determining determines to recalibrate the camera.

Claims

1. A method for calibrating a camera, the method comprising:

detecting at least one edge of fixed object in image received from a camera;

determining at least one horizontal midpoint of the at least one edge;

calculating a first pixel distance between the determined at least one horizontal midpoint and a pre-stored at least one horizontal midpoint;

calculating second pixel distances between a plurality of points on the detected at least one edge of the fixed object and a pre-stored plurality of points of the at least one edge of the fixed object;

determining whether to recalibrate the camera based on the first pixel distance and the second pixel distances; and

recalibrating the camera if the determining determines to recalibrate the camera,

wherein the determining whether to recalibrate the camera based on the first pixel distance and the second pixel distances comprises determining whether the first pixel distance or the second pixel distances are greater than a predetermined threshold distance and determining whether an affine movement has occurred based on the determined horizontal midpoint and the plurality of points on the at least one edge of the fixed object.

2. The method of claim 1, wherein the fixed object comprises a vehicle bed,

wherein the plurality of points correspond to the corners of the vehicle bed, and

wherein the determining the at least one horizontal midpoint of the at least one edge comprises determining a horizontal midpoint of an edge corresponding to a gate of the vehicle bed and a horizontal midpoint of an edge corresponding to a side opposite the gate of the vehicle bed.

3. The method of claim 1, wherein the fixed object comprises a bumper,

wherein the determining the at least one horizontal midpoint of the at least one edge comprises determining a horizontal midpoint of an edge corresponding to the bumper, and

wherein the plurality of points are points on the bumper corresponding to one or more from among:

a) a first end of the bumper and a second end of the bumper; and

b) a point between the horizontal midpoint and the first end of the bumper and a point between the horizontal midpoint and the second end of the bumper.

4. The method of claim 1, wherein the recalibrating the camera comprises transforming the received image and re-cropping the transformed image.

5. The method of claim 4, wherein the transforming the received image comprises performing an affine transformation on the received image based on the first pixel distance between the determined at least one horizontal midpoint and a pre-stored at least one horizontal midpoint and the second pixel distances between a plurality of points on the detected at least one edge of the fixed object and a pre-stored plurality of points of the at least one edge of the fixed object.

6. The method of claim 1, wherein the camera comprises a camera imaging an area behind a vehicle including the vehicle bumper or a camera imaging an area including a vehicle bed.

7. The method of claim 1, wherein the plurality of points comprises four points or six points.

8. A non-transitory computer readable medium comprising instructions executable by a computer to perform the method of claim 1.

9. An apparatus for calibrating a camera, the apparatus comprising:

at least one memory comprising computer executable instructions; and

at least one processor configured to read and execute the computer executable instructions, the computer executable instructions causing the at least one processor to;

detect at least one edge of fixed object in image received from a camera;

determine at least one horizontal midpoint of the at least one edge;

calculate a first pixel distance between the determined at least one horizontal midpoint and a pre-stored at least one horizontal midpoint;

calculate second pixel distances between a plurality of points on the detected at least one edge of the fixed object and a pre-stored plurality of points of the at least one edge of the fixed object;

determine whether to recalibrate the camera based on the first pixel distance and the second pixel distances; and

recalibrate the camera if the determining determines to recalibrate the camera;

wherein the computer executable instructions cause the at least one processor to determine whether to recalibrate the camera based on the first pixel distance and the second pixel distances by determining whether the first pixel distance or the second pixel distances are greater than a predetermined threshold distance and further determining whether an affine movement has occurred based on the determined horizontal midpoint and the plurality of points on the at least one edge of the fixed object.

10. The apparatus of claim 9, wherein the fixed object comprises a vehicle bed,

wherein the plurality of points correspond to the corners of the vehicle bed, and

wherein the computer executable instructions cause the at least one processor to determine the at least one horizontal midpoint of the at least one edge by determining a horizontal midpoint of an edge corresponding to a gate of the vehicle bed and a horizontal midpoint of an edge corresponding to a side opposite the gate of the vehicle bed.

11. The apparatus of claim 9, wherein the fixed object comprises a bumper,

wherein the plurality of points are points on the bumper corresponding to one or more from among:

a) a first end of the bumper and a second end of the bumper; and

b) a point between the horizontal midpoint and the first end of the bumper and a point between the horizontal midpoint and the second end of the bumper, and

wherein the computer executable instructions cause the at least one processor to determine the at least one horizontal midpoint of the at least one edge by determining a horizontal midpoint of an edge corresponding to the bumper.

12. The apparatus of claim 9, wherein the computer executable instructions further cause the at least one processor to recalibrate the camera by transforming the received image and re-cropping the transformed image.

13. The apparatus of claim 12, wherein the computer executable instructions further cause the at least one processor to transform the received image by performing an affine transformation on the received image based on the first pixel distance between the determined at least one horizontal midpoint and a pre-stored at least one horizontal midpoint and the second pixel distances between a plurality of points on the detected at least one edge of the fixed object and a pre-stored plurality of points of the at least one edge of the fixed object.

14. The apparatus of claim 9, further comprising a camera imaging an area behind a vehicle including the vehicle bumper.

15. The apparatus of claim 9, further comprising a camera imaging an area including a vehicle bed.

16. The apparatus of claim 9, wherein the plurality of points comprises four points or six points.