Method and device for lane detection

• US 8,842,884 B2
• Filed: 03/18/2010
• Issued: 09/23/2014
• Est. Priority Date: 03/30/2009
• Status: Active Grant

• Current Assignee: Conti Temic Microelectronic GmbH (Continental AG)
• Original Assignee: Conti Temic Microelectronic GmbH (Continental AG)
• Inventors: Klein, Wladimir, Walter, Michael
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): CONNER, SEAN M
• Application Number:
  US13/258,080
• Publication Number:
  US 20120099766A1
• Time in Patent Office: 1,650 Days
• Field of Search: None
• US Class Current: 382/104
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• 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 1/16 Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

A lane detection method wherein a digitized image of a lane is evaluated, including the following steps: detecting edges in the image, determining the angles of the detected edges with respect to a reference edge, removing the edges from the plurality of detected edges, the angle of which lies within a predetermined angle sector, and detecting the lane based on the remaining edges of the plurality of detected edges.

Claims

1. A lane detection method, wherein a digitized image of a lane in which a vehicle is traveling is evaluated, comprising the following steps:

detecting edges in the image by performing horizontal edge filtering and vertical edge filtering which produce horizontal edge components and vertical edge components,

determining angles of the detected edges with respect to a vertical reference edge, by computing a quotient of the horizontal edge components and the vertical edge components,

determining an orientation of the detected edges in the image;

removing nearly vertical edges from the plurality of detected edges when the vehicle is located in the lane, the nearly vertical edges having angles which lie within a predetermined angle section with respect to the vertical reference edge, wherein the angles of the nearly vertical edges differ from the vertical reference edge by a predetermined threshold such that the orientations of the nearly vertical edges do not exactly coincide with an orientation of the vertical reference edge;

maintaining the nearly vertical edges from the plurality of detected edges when the vehicle is located outside of the lane; and

detecting the lane based on the nearly vertical edges that have been maintained and the remaining edges of the plurality of detected edges, the remaining edges having angles which lie outside the predetermined angle section with respect to the vertical reference edge.

2. A method according to claim 1,

wherein the reference edge is a vertical edge in the image, which is rotated by a predetermined roll angle of a vehicle.

3. A method according to claim 1,

wherein the predetermined angle section is configured such that it comprises all edges, the orientation of which corresponds to approximately the orientation of the reference edge.

4. A method according to claim 1,

wherein the detection of edges comprises a horizontal and then a vertical edge filtering of a region of the image in order to determine pairs of horizontal and vertical edge components each pertaining to an edge, and that determining of the angles of the detected edges, includes calculation of the arc tangent of the quotient of the horizontal and vertical edge component of each pair of edges in the region of the image.

5. A method according to claim 1,

wherein in a detection mode of an automatic lane detection removal of the edges takes place only if a vehicle using the automatic lane detection is located on the lane.

6. A method according to claim 4,

wherein in a histogram-based tracking mode regions are masked out by the edge removal, in which there are edges, in which the difference between the angle of the edge, the angle of which lies within the predetermined angle section, and a predicted orientation exceeds the predetermined threshold.

7. A device for lane detection, which includes a processor for evaluating a digitized image of a lane in which a vehicle is traveling is configured such that it comprises the following steps:

detecting, by the processor, edges in the image by performing horizontal edge filtering and vertical edge filtering which produce horizontal edge components and vertical edge components,

determining, by the processor, angles of the detected edges with respect to a vertical reference edge, by computing a quotient of the horizontal edge components and the vertical edge components,

determining, by the processor, an orientation of the detected edges in the image;

removing, by the processor, nearly vertical edges from the plurality of detected edges when the vehicle is located in the lane, the nearly vertical edges having angles which lie within a predetermined angle section with respect to the vertical reference edge, wherein the angles of the nearly vertical edges differ from an angle of the vertical reference edge by a predetermined threshold such that the orientations of the nearly vertical edges do not exactly coincide with an orientation of the vertical reference edge;

maintaining the nearly vertical edges from the plurality of detected edges when the vehicle is located outside of the lane; and

detecting, by the processor, the lane based on the nearly vertical edges that have been maintained and the remaining edges of the plurality of detected edges, the remaining edges having angles which lie outside the predetermined angle section with respect to the vertical reference edge.

8. An automatic lane detection system, which comprises a device according to claim 7 and which delivers lane data.

9. A lane changing warning system and lane keeping system, which comprises an automatic lane detection system according to claim 8 and which processes the delivered lane data to detect a lane change.

10. A vehicle with an automatic lane change warning system or lane keeping system according to claim 9.