Method for Determining a Course of a Traffic Lane for a Vehicle

• US 20150149076A1
• Filed: 08/09/2013
• Published: 05/28/2015
• Est. Priority Date: 08/27/2012
• Status: Active Grant

• Current Assignee: Continental Teves AG & Co. OHG (Continental AG)
• Original Assignee: Continental Teves AG & Co. OHG (Continental AG)
• Inventors: Strauss, Matthias, Komar, Matthias, Waldbauer, Dirk, Lueke, Stefan, Guenther, Wolfgang
• Granted Patent: US 9,360,332 B2
• Time in Patent Office: Days
• US Class Current: 701/410
• CPC Class Codes: B60R 2300/102 using 360 degree surveillance camera system
• CPC Class Codes: B60R 2300/804 for lane monitoring
• CPC Class Codes: G01C 21/34 Route searching; Route guidance
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G06V 10/507 Summing image-intensity values; Histogram projection analysis
• 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

Abstract

The invention relates to a method for determining a course of a traffic lane for a vehicle (10), in which structures that demarcate a space that is fit for traffic are detected by means of at least one image acquisition unit (2) and these structures are plotted on a surroundings map (20) that subdivides the surroundings of the vehicle into a two-dimensional grid structure (20a) of cells (21), wherein the invention provides that

• • the position in the grid structure (21) of the surroundings map (20) is determined and continually updated by means of odometric data of the vehicle (10),
  • the distance and the direction of the vehicle (10) with respect to those cells (21b) of the grid structure (20a) of the surroundings map (20) which feature structures that demarcate the pavement and/or the traffic lane are determined,
  • bright-to-dark and dark-to-bright transitions in the image data generated by the image acquisition unit (2) are detected and are plotted on the cells (21) of the grid structure (20a) of the surroundings map (20) and
  • the course of the traffic lane (22) is determined from the cells with the detected bright-to-dark and dark-to-bright transitions.

Claims

1. Method for determining a course of a traffic lane for a subject vehicle (10), in which structures that demarcate a space that is fit for traffic are detected by at least one image acquisition unit (2) and the structures are plotted on a surroundings map (20) that subdivides surroundings of the subject vehicle into a two-dimensional grid structure (20a) of cells (21), characterized in that

a position of the subject vehicle in the grid structure (21) of the surroundings map (20) is determined and continually updated by odometric data of the subject vehicle (10),

a distance and a direction of the subject vehicle (10) with respect to particular cells (21b) of the grid structure (20a) of the surroundings map (20) which feature structures that demarcate a pavement and/or the traffic lane are determined,

bright-to-dark and dark-to-bright transitions in image data generated by the image acquisition unit (2) are detected and are plotted on the cells (21) of the grid structure (20a) of the surroundings map (20) and

the course of the traffic lane (22) is determined from the cells with the detected bright-to-dark and dark-to-bright transitions.

2. Method according to claim 1, characterized in that if there are no image data from a region of the surroundings which is in front of the subject vehicle (10), the determined course of the traffic lane (22) will be extrapolated into the region of the surroundings which is in front of the subject vehicle (10).

3. Method according to claim 1, characterized in that a stationary coordinate system is used for the surroundings map (20).

4. Method according to claim 1, characterized in that the bright-to-dark and dark-to-bright transitions that are present in a line structure are detected.

5. Method according to claim 1, characterized in that the grid cells (21) of the surroundings map are classified respectively as grid cells that can be driven over or cannot be driven over.

6. Method according to claim 1, characterized in that the odometric data are determined by sensors (7) belonging to the subject vehicle.

7. Method according to claim 1, characterized in that in addition to the odometric data, an optical flow from the image data of the image acquisition unit (2) is used to determine the position of the subject vehicle (10) in the grid structure (20a) of the surroundings map (20).

8. Method according to claim 1, characterized in that

other vehicles driving parallel to the subject vehicle (10) are detected by the image acquisition unit (2),

distances, transversely to a direction of motion of the subject vehicle, to the other vehicles driving parallel to the subject vehicle (10) are determined, and

the distances to the other vehicles are used to verify the course of the traffic lane (22).