IP Library › Granted Patent US 11,373,333
Granted Patent B2
US 11,373,333 · App. 16/634,444 · Granted Jun 28, 2022

Calibration apparatus and method for in-vehicle camera

Inventors: Manabu Kawabe (Tokyo, JP); Tsukasa Saito (Saitama, JP); Morihiko Sakano (Tokyo, JP); Nobuyuki Matsuyama (Saitama, JP)
G06T7/80G06T7/70G06V20/56
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 11,373,333
App. No.
16/634,444
Granted
Jun 28, 2022
Kind
B2
Abstract

There are provided a calibration apparatus and method capable of obtaining a high-precision calibration result by taking out only feature points on a road surface from images captured by an in-vehicle camera which is a calibration target. A road surface range is estimated by using feature points appearing in an image(s) captured by a camera (a front camera 102 or a rear camera 103 ) that is not a camera on which the calibration is executed (a side camera 106 ); and the calibration is executed by using only feature points existing within the estimated road surface range from among the feature points appearing in an image(s) captured by the camera on which the calibration is executed.

Claims (29)

1. A calibration apparatus of a vehicle for executing calibration of an external parameter for a first in-vehicle camera in an in-vehicle camera system having input from a plurality of in-vehicle cameras, the calibration apparatus comprising a processor and memory,

wherein the processor estimates a road surface range, as a range for a road surface on which the vehicle travels on, by using a feature point appearing in an image captured by one or more in-vehicle cameras that are different from the first in-vehicle camera;

wherein the processor calculates heights of the feature points appearing in the image captured by one or more in-vehicle cameras;

wherein the processor estimates the road surface range by excluding feature points that have a height higher than a height of the road surface, based on the calculated heights of the feature points appearing in the image captured by one or more in-vehicle cameras;

wherein the processor determines whether a feature point appearing in an image captured by the first in-vehicle camera is within the estimated road surface range; and

wherein the calibration is executed by the processor using only a feature point that is determined to be within the estimated road surface range from among feature points appearing in the image captured by the first in-vehicle camera.

2. The calibration apparatus according to claim 1 , wherein the processor estimates the road surface range based on a moved distance or a moving speed of the feature point appearing in the image captured by the one or more in-vehicle cameras that are not the first in-vehicle camera.

3. The calibration apparatus according to claim 1 , wherein the in-vehicle camera that is different from the first in-vehicle camera is a front camera for capturing images of an area in front of a vehicle or a rear camera for capturing images of an area behind the vehicle.

4. The calibration apparatus according to claim 1 , wherein the first in-vehicle is a side camera for capturing images of an area on a lateral side of the vehicle.

5. A calibration apparatus for executing calibration of an external parameter for a first in-vehicle cameras in an in-vehicle camera system having input from the plurality of in-vehicle cameras comprising:

the calibration apparatus comprising a processor and memory, wherein the processor:

detects first feature points appearing in an image captured by a second in-vehicle camera that is different from the first in-vehicle camera;

tracks the first feature points from images captured by the second in-vehicle camera at different times of day;

calculates a height of each of the first feature points from a moved distance or a moving speed of the tracked first feature point;

estimates, as a road surface range for a road surface on which the vehicle travels on, a range where the first feature point having the same height as that of a road surface exists, from among the first feature points, wherein the road surface range excludes feature points that have a height higher than a height of the road surface, based on the calculated heights of the feature points;

sets the estimated road surface range as a road surface range for the first in-vehicle camera;

detects second feature points appearing in an image captured by the first in-vehicle camera;

tracks the second feature points from images captured by the first in-vehicle camera at different times of day;

determines whether any feature point of the second feature points in the image captured by the first in-vehicle camera is within the estimated road surface range; and

executes the calibration of the first in-vehicle camera from only the second feature points that are determined to be within the road surface range.

6. A calibration method for executing calibration of an external parameter for a first in-vehicle camera in an in-vehicle camera system having input from a plurality of in-vehicle cameras,

wherein a road surface range is estimated, as a range for a road surface on which the vehicle travels on, by using a feature point appearing in an image captured by one or more in-vehicle cameras that are different from the first in-vehicle camera;

wherein a calibration apparatus calculates heights of the feature points appearing in the image captured by one or more in-vehicle cameras;

wherein the calibration apparatus estimates the road surface range by excluding feature points that have a height higher than a height of the road surface, based on the calculated heights of the feature points appearing in the image captured by one or more in-vehicle cameras;

wherein the calibration apparatus determines whether a feature point appearing in an image captured by the first in-vehicle camera is within the estimated road surface range; and

wherein the calibration is executed by using only a feature point that is determined to be within the estimated road surface range from among feature points appearing in the image captured by the first in-vehicle camera.

7. The calibration method according to claim 6 , wherein the road surface range is estimated based on a moved distance or a moving speed of the feature point appearing in the image captured by the one or more in-vehicle cameras that are not the first in-vehicle camera.

8. The calibration method according to claim 6 , wherein the in-vehicle camera that is different from the first in-vehicle camera is a front camera for capturing images of an area in front of a vehicle or a rear camera for capturing images of an area behind the vehicle.

9. The calibration method according to claim 6 , wherein the first in-vehicle camera is a side camera for capturing images of an area on a lateral side of the vehicle.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 22, 2020
From: KAWABE, MANABU; SAITO, TSUKASA; SAKANO, MORIHIKO; MATSUYAMA, NOBUYUKI
To: CLARION CO., LTD.
Reel/Frame 054336/0272 →
Priority Claims (1)
JP JP2017-146551 · Jul 28, 2017 · national
Continuity (1)
Related Publication 20200211224A1 · Jul 2, 2020