Method and device for lane detection

• US 8,611,650 B2
• Filed: 03/18/2010
• Issued: 12/17/2013
• 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): Bayat, Ali
• Application Number:
  US13/256,664
• Publication Number:
  US 20130004067A1
• Time in Patent Office: 1,370 Days
• Field of Search: 382/103, 382/162, 382/165, 382/167, 382/274, 348/223.1, 348/148, 348/254
• US Class Current: 382/165
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding

Abstract

A method for lane detection, wherein a digitized color image of a roadway is processed using the following steps:

• • identifying markings on the roadway with a grayscale value below the grayscale value of the roadway (S18),
  • setting the grayscale value of the markings thus identified to a value above the grayscale value of the roadway, and
  • outputting the image thus processed and modified to be processed by a lane detection algorithm for monochrome images.

Claims

1. A method for lane detection, wherein a digitized color image of a roadway is processed using the following steps:

evaluating individual color components of the color image;

identifying the colors of markings on the image of the roadway based on the evaluated color components;

identifying the markings on the image of the roadway with having a grayscale value below a grayscale value of the roadway;

setting the grayscale value of the identified markings to a value above the grayscale value of the roadway; and

outputting the image for processing by a lane detection algorithm for monochrome images.

2. The method according to claim 1 further comprising the steps of:

outputting the identified colors of markings for verification of a lane detection.

3. The method according to claim 1, wherein

prior to the step of identifying markings, an automatic white balance of the color image is performed.

4. The method according to claim 3, wherein

the white balance is performed by adaptive evaluation of the roadway immediately in front of a vehicle.

5. The method according to claim 4, wherein

a segment of the roadway is selected which is sufficiently large so as to be able to neglect any influence of local variations in chromaticness on the white balance.

6. A method for lane detection, wherein a digitized color image of a roadway is processed using the following steps:

identifying markings on an image of the roadway with a grayscale value below a grayscale value of the roadway,

setting the grayscale value of the identified markings to a value above the grayscale value of the roadway,

outputting the image for processing by a lane detection algorithm for monochrome images,

wherein prior to the step of identifying markings, an automatic white balance of the color image is performed, and

further comprising the step of determining a color difference and, as a function thereof, a correction factor for the white balance, assuming a roadway of neutral color.

7. A device for lane detection that is configured to process a digitized color image of a roadway as follows:

evaluating individual color components of the color image;

identifying the colors of markings on the image of the roadway based on the evaluated color components;

identifying the markings on the image of the roadway with having a grayscale value below a grayscale value of the roadway,

setting the grayscale value of the identified markings to a value above the grayscale value of the roadway, and

outputting the image for processing by a lane detection algorithm for monochrome images.

8. An automatic lane detection system comprising a device according to claim 7 and outputting traffic lane data.

9. A lane change warning system or a lane keeping system comprising an automatic lane detection system according to claim 8 that is configured to process the traffic lane data outputted by said lane detection system to detect a lane change.

10. A vehicle including a lane change warning system or a lane keeping system according to claim 9.