Vehicle vision system

Patent metadata

Field	Value
Publication number	US-9536306-B2
Application number	US-201213527361-A
Country	US
Kind code	B2
Filing date	Jun 19, 2012
Priority date	Jun 30, 2011
Publication date	Jan 3, 2017
Grant date	Jan 3, 2017

Abstract

In order to determine extrinsic parameters of a vehicle vision system or an aspect of a vehicle vision system, road lane markings may be identified in an image captured by a camera and provided to the vehicle vision system. For one or more of the identified road lane markings, a first set of parameters defining an orientation and a position of a line along which a road lane marking extends in an image plane may be determined. Also, a second set of parameters defining an orientation and a position of a line along which a road lane marking extends in a road plane may be determined. A linear transformation that defines a mapping between the first set of parameters and the second set of parameters may be identified. The extrinsic parameters may be established based on the identified linear transformation.

First claim

We claim:

1. A computer implemented method of determining extrinsic parameters for a vehicle vision system, the method comprising:
processing an image of a road captured by a camera to identify a first road lane marking and a second road lane marking in the image, where the first road lane marking and the second road lane marking are two road lane markings that extend parallel to each other;
determining, for at least one of the two road lane markings:
a first set of parameters defining an orientation and a position of a line along which the at least one of the two road lane markings extends in an image plane, where the determining the first set of parameters comprises determining parameter values a′ i , b′ i and c′ i , such that the line along which the at least one of the two road lane markings extends in the image plane is defined by
a′ i ·x′+b′ i ·y′+c′ i =0,

 where i denotes a road lane marking identifier and x′ and y′ denote coordinates in the image plane; and
a second set of parameters defining an orientation and a position of a line along which the at least one of the two road lane markings extends in a road plane, where the second set of parameters is determined based on information related to spacing of the two road lane markings, wherein at least one of the first set of parameters and the second set of parameters includes coefficients of a bilinear equation;

identifying a linear transformation which, for at least one of the two road lane markings, defines a mapping between the first set of parameters and the second set of parameters, where the identifying the linear transformation comprises determining matrix elements of a homographs matrix; and
establishing the extrinsic parameters based on the identified linear transformation, where the established extrinsic parameters include an orientation of the camera with respect to a vehicle coordinate system.

2. The method of claim 1 , where the matrix elements of the homography matrix are determined such that
H T {right arrow over (p′)} i

approximates {right arrow over (p)} i for i=1, . . . , M, where i denotes a road lane marking identifier, M denotes a count of the two road lane markings, H denotes the homography matrix that comprises three rows and three columns, T denotes a matrix transposition, {right arrow over (p′)} i denotes a 3-tuple of the first set of parameters identified for an i th road lane marking, and {right arrow over (p)} i denotes a 3-tuple of the second set of parameters identified for the i th road lane marking.

3. The method of claim 1 , where the determining the second set of parameters comprises determining parameter values a i , b i , and c i , such that the line along which the at least one of the two road lane markings extends in the road plane is defined by
a i ·x+b i ·y+c i =0,

where x and y denote coordinates in the road plane.

4. The method of claim 3 , where the matrix elements of the homography matrix are determined based on

N
⁡

[

H
T

⁡

(

a
i
′

b
i
′

c
i
′

)

-

(

a
i

b
i

c
i

)

]

,

for i=1, . . . , M, where N[•] denotes a vector norm, where i denotes a road lane marking identifier, M denotes a count of the two road lane markings, H denotes the homography matrix that comprises three rows and three columns, and T denotes a matrix transposition.

5. The method of claim 3 , where the matrix elements of the homography matrix may be determined such that

∑

i
=
1

M

⁢



H
T

⁡

(

a
i
′

b
i
′

c
i
′

)

-

(

a
i

b
i

Assignees

• Natroshvili Koba
• Vacek Stefan
• Harman Becker Automotive Systems Gmbh

Inventors

• Natroshvili Koba
• Vacek Stefan

Classifications

• G06T7/0018 Primary

  Physics · mapped topic

• G06T2207/30256

  Lane; Road marking · CPC title

• G06T7/80 Primary

  Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration · CPC title