Method for detecting road lane markings

• US 8,239,085 B2
• Filed: 05/20/2006
• Issued: 08/07/2012
• Est. Priority Date: 09/20/2005
• Status: Active Grant

• Current Assignee: ADC Automotive Electric Motors GmbH (Continental AG)
• Original Assignee: ADC GmbH (TE Connectivity Ltd. (United Kingdom))
• Inventors: Fechner, Thomas, Heinrich, Stefan, Ulbricht, Dirk
• Primary Examiner(s): Dickson, Paul N
• Assistant Examiner(s): FRISBY, KEITH J
• Application Number:
  US12/067,477
• Publication Number:
  US 20080255724A1
• Time in Patent Office: 2,271 Days
• Field of Search: 701/28, 701/23, 701/223, 701/41, 701/42, 701/43, 701/44, 701/207, 701/205, 701/300, 340/905, 340/901, 382/103, 382/104, 382/181
• US Class Current: 701/28
• CPC Class Codes: G06T 7/73 using feature-based methods
• 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 road lane markings for a motor vehicle in motion with an image recording unit is presented. The image recording unit points to the road in front of the vehicle and in the recorded image data, brightness differences (contrasts) are analysed and/or edges are extracted. Road lane markings are detected by means of their periodic arrangement. For evaluation purposes, the measuring signal of the image recording unit is transformed into another coordinate system, and the auxiliary function thus obtained is tested for periodic structures.

Claims

1. A method for detecting road lane markings (5) for a motor vehicle (1) in motion with an image recording unit, the method comprising:

obtaining image data from an image recording unit (6), wherein the image recording unit (6) points to the road (3) in front of the vehicle;

analyzing the image data for at least one of contrasts or edges that are extracted;

detecting road lane markings (5) by means of a periodic arrangement on the road (3), wherein for evaluation purposes, a measurement signal from the image recording unit (6) having a first coordinate system is transformed into another coordinate system, and an auxiliary function thus obtained is tested for periodicity.

2. The method according to claim 1, wherein depending on a direction of view of the image recording unit (6), the auxiliary function with spatially equidistant measuring points is interpolated on the road.

3. The method according to claim 1, wherein the auxiliary function is tested for periodic brightness changes per route unit, and is characterized by means of the spatial frequency.

4. The method according to claim 1, wherein the image data or the auxiliary function is tested in temporal period by means of correlation with a specified signal or frequency analysis for specific signatures of the specified marking types, wherein the intrinsic speed of the motor vehicle is taken into account.

5. The method according to claim 1, wherein the auxiliary function in the spatial area is tested by means of a cross correlation or a convolution with a specified signal for specific signatures of the specified marking types.

6. The method according to claim 1, wherein a search is made for road markings (5) only in the specified areas of the image.

7. The method according to claim 1, wherein in order to identify evaluation errors in the image for individual segments (image sections) respectively along the identified road lane markings (5), a frequency spectrum of the temporal brightness progression is determined, and

the values are compared with each other;

and

with a significant deviation of the frequency in one segment, this measuring signal is discarded.

8. The method according to claim 7, wherein in order to identify evaluation errors in the image for individual segments (image sections) respectively along the identified road lane marking (5), a brightness progression is determined, comparisons are made with the other brightness progressions by means of correlation, and with a significant deviation in a segment, this measuring signal is discarded.

9. The method according to claim 8, wherein in order to identify evaluation errors, the brightness progressions are compared for individual image segments respectively, taking into account the intrinsic speed, with specified brightness progressions which correspond to those of typical road lane markings, by means of correlation and frequency analysis, wherein with a significant deviation of the brightness value in a segment from all specified signals, the measuring signal is discarded.

10. The method according to claim 1, wherein in order to identify evaluation errors, only those objects are detected as road markings (5) which are arranged along a straight line or a curve.

11. The method according to claim 1, wherein a direction of movement of the objects in the image detected as the road marking (5) is analysed, wherein measurement values of objects which deviate from the direction of movement of other markings are discarded.

12. The method according to claim 1, wherein at least one of a direction of movement and a movement speed of the objects in the image which are detected as the road marking (5) are tested and are compared with a predicated progression, wherein the predicated progression depends on the intrinsic speed of the device, and objects which deviate from this progression are discarded.

13. A device comprising:

an image recording unit; and

a control unit, wherein the control unit obtains image data from the image recording unit (6), analyzes the image data for at least one of contrasts or edges that are extracted, and detects road lane markings (5) by means of a periodic arrangement on the road (3), wherein for evaluation purposes, a measurement signal from the image recording unit (6) having a first coordinate system is transformed into another coordinate system, and an auxiliary function thus obtained is tested for periodicity.

14. A motor vehicle having a device according to claim 13.