Method and device for detecting a position of a vehicle on a lane

• US 9,569,673 B2
• Filed: 08/01/2013
• Issued: 02/14/2017
• Est. Priority Date: 08/29/2012
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Renner, Christian, Hahn, Markus
• Primary Examiner(s): BLOUNT, ERIC
• Application Number:
  US14/425,100
• Publication Number:
  US 20150278610A1
• Time in Patent Office: 1,293 Days
• Field of Search: 340/435, 340/436
• US Class Current: 1/1
• CPC Class Codes: G06V 10/10 Image acquisition document image scanning and transmission H04N1/00; control of digital cameras H04N23/60
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 10/16 using multiple overlapping images; Image stitching
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

A method for detecting a vehicle position on a lane, including: reading in a first image of a first camera, having a first optical axis and reading in at least a second image of at least a second camera having a second optical axis, the cameras being oriented so that the first and second optical axis intersect outside of the detection angle of the first and/or second camera, the first and the at least second image each enclosing a viewing angle deviating by an angle of 90 degrees maximum from the driving direction. Determining at least one interlinked image gradient for each of the first image and the at least second image. Assigning the at least one interlinked image gradient to a boundary object and assigning the at least one additional interlinked image gradient to a boundary object and/or to one additional boundary object, and ascertaining a relative position of the vehicle as to the boundary object and/or to the additional boundary object to detect the vehicle position.

Claims

1. A method for detecting a position of a vehicle on a lane, the method comprising:

reading in one first image of a first camera having a first optical axis and of at least one second image of at least one second camera having a second optical axis, the first camera and the second camera being oriented so that the first optical axis and the second optical axis intersect outside of the detection angle of the first camera and/or the second camera, wherein the first image and at least the second image each enclose a viewing angle which deviates by an angle of 90 degrees maximum from a driving direction of the vehicle;

determining at least one interlinked image gradient in the first image and at least one additional interlinked image gradient in the at least second image;

assigning the at least one interlinked image gradient to a roadway boundary object and the at least one additional interlinked image gradient to the roadway boundary object and/or to an additional roadway boundary object; and

ascertaining a relative position of the vehicle to the roadway boundary object and/or the additional roadway boundary object to detect the position of the vehicle on the lane.

2. The method of claim 1, further comprising:

classifying the at least one interlinked image gradient and the at least one additional interlinked image gradient using image sections along the interlinked image gradients and selecting at least one classified interlinked image gradient, which represents the interlinked image gradient which is usable for a line trend estimate of the lane.

3. The method of claim 2, wherein in the classifying, one quality value is assigned to the at least one interlinked image gradient and the at least one additional interlinked image gradient each, the quality value representing an accuracy and/or an expected variance of the at least one interlinked image gradient as a boundary of the lane.

4. The method of claim 1, wherein in the reading in, the image and the at least second image are calibrated intrinsically and/or extrinsically.

5. The method of claim 1, wherein in the reading in, the first image and the at least second image have an overlapping subarea.

6. The method of claim 1, wherein in the reading in, at least one additional image of at least a third camera is read in, the optical axis of the at least third camera deviating from the optical axis of the first camera and from the optical axis of the at least second camera).

7. The method of claim 1, further comprising:

creating a line trend model as a boundary of the lane using the roadway boundary object and/or the additional roadway boundary object, the line trend model describing the course of the lane and/or a future course of the lane.

8. A device for detecting a position of a vehicle on a lane, comprising:

a reading arrangement to read in one first image of a first camera having a first optical axis and of at least one second image of at least one second camera having a second optical axis, the first camera and the second camera being oriented so that the first optical axis and the second optical axis intersect outside of the detection angle of the first camera and/or the second camera, wherein the first image and at least the second image each enclose a viewing angle which deviates by an angle of 90 degrees maximum from a driving direction of the vehicle;

a determining arrangement to determine at least one interlinked image gradient in the first image and at least one additional interlinked image gradient in the at least second image;

an assigning arrangement to assign the at least one interlinked image gradient to a roadway boundary object and the at least one additional interlinked image gradient to the roadway boundary object and/or to an additional roadway boundary object; and

an ascertaining arrangement to ascertain a relative position of the vehicle to the roadway boundary object and/or the additional roadway boundary object to detect the position of the vehicle on the lane.

9. A computer readable medium having a computer program, which is executable by a processor, comprising:

a program code arrangement having program code for detecting a position of a vehicle on a lane, by performing the following;

reading in one first image of a first camera having a first optical axis and of at least one second image of at least one second camera having a second optical axis, the first camera and the second camera being oriented so that the first optical axis and the second optical axis intersect outside of the detection angle of the first camera and/or the second camera, wherein the first image and at least the second image each enclose a viewing angle which deviates by an angle of 90 degrees maximum from a driving direction of the vehicle;

determining at least one interlinked image gradient in the first image and at least one additional interlinked image gradient in the at least second image;

assigning the at least one interlinked image gradient to a roadway boundary object and the at least one additional interlinked image gradient to the roadway boundary object and/or to an additional roadway boundary object; and

ascertaining a relative position of the vehicle to the roadway boundary object and/or the additional roadway boundary object to detect the position of the vehicle on the lane.

10. A lane detection system for detecting a position of a vehicle on a lane, comprising:

a first camera having a first optical axis;

at least one second camera having a second optical axis, the first camera and the second camera being oriented so that the first optical axis and the second optical axis intersect outside of the detection angle of the first camera and/or the second camera, and the first camera and the at least second camera being configured to each enclose a viewing angle which deviates by an angle of 90 degrees maximum from a driving direction of the vehicle; and

a device for detecting a position of a vehicle on a lane, including;

a reading arrangement to read in the first image of the first camera having the first optical axis and of the at least one second image of the at least one second camera having the second optical axis;

a determining arrangement to determine at least one interlinked image gradient in the first image and at least one additional interlinked image gradient in the at least second image;

an assigning arrangement to assign the at least one interlinked image gradient to a roadway boundary object and the at least one additional interlinked image gradient to the roadway boundary object and/or to an additional roadway boundary object; and

an ascertaining arrangement to ascertain a relative position of the vehicle to the roadway boundary object and/or the additional roadway boundary object to detect the position of the vehicle on the lane.