SYSTEM AND METHOD FOR PERIODIC LANE MARKER IDENTIFICATION AND TRACKING

• US 20130028473A1
• Filed: 07/27/2012
• Published: 01/31/2013
• Est. Priority Date: 07/27/2011
• Status: Active Grant

• Current Assignee: HL Klemove Corporation
• Original Assignee: Gentex Corporation
• Inventors: Rycenga, Brock R., Hilldore, Benjamin B., TerHaar, Micah W.
• Granted Patent: US 9,098,751 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 5/40 using histogram techniques
• 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

Abstract

A system and method for determining the presence and period of dashed line lane markers in a roadway. The system includes an imager configured to capture a plurality of high dynamic range images exterior of the vehicle and a processor, in communication with the at least one imager such that the processor is configured to process at least one high dynamic range image. The period of the dashed lane markers in the image is calculated for detecting the presence of the dashed lane marker and for tracking the vehicle within the markers. The processor communicates an output for use by the vehicle for use in lane departure warning (LDW) and/or other driver assist features.

Claims

1. A system for periodic lane marker identification comprising:

at least one imager configured to capture a plurality of images exterior of the vehicle;

a processor in communication with the at least one imager where the processor is configured to process at least one image such that the period of the dashed lane markers in the image is calculated for tracking the vehicle within the detected dashed lane markers; and

wherein the processor communicates an output based upon the detected dashed lane markers for use by the vehicle.

2. A system for periodic lane marker identification as in claim 1, wherein a period of the lane marker is determined by identifying an edge location from the vehicle and storing a plurality of edge locations in at least one buffer for calculating a frequency of occurrence.

3. A system for periodic lane marker identification as claim 1, wherein the period is determined using a Poisson point process.

4. A system for period lane marker identification as in claim 1, wherein the period of the dashed lane markers is computed based on distance between leading edges of the lane dashed lane markers.

5. A system for periodic lane maker identification as in claim 1, wherein the period of the dashed lane markers is computed based on a distance between the trailing edges of the dashed lane markers.

6. A system for period lane marker identification as in claim 1, wherein the dashed lane marks are used by identifying a search region for the at least one imager.

7. A system for periodic roadway lane marker identification comprising:

at least one image sensor configured to capture a plurality of high dynamic range images exterior of a vehicle;

an image controller for communication data from the at least one imager;

a processor in communication with the image controller such that the processor is configured to process at least one high dynamic range image such that the period of a plurality of dashed roadway lane markers is determined based on points in the image; and

wherein the processor communicates an output based upon the determined period of the plurality of dashed roadway lane markers for assisting a driver.

8. A system for periodic lane marker identification as in claim 7, wherein a period of the lane marker is determined by identifying an edge location from the vehicle and storing a plurality of edge locations in at least one buffer.

9. A system for period lane marker identification as claim 7, wherein the period of dashed lane marker occurrence is determined using the frequency of occurrence of the periodic lane marker.

10. A system for period lane marker identification as in claim 7, wherein the period of the dashed lane markers is computed based on a distance between leading edges of the lane dashed lane markers.

11. A system for periodic lane maker identification as in claim 7, wherein the period of the dashed lane markers is computed based on a distance between the trailing edges of the dashed lane markers.

12. A system for periodic lane marker identification as in claim 7, wherein the dashed lane markers are used by identifying a search region used by the at least one imager.

13. A method of detecting a periodic dashed lane marker located on a roadway comprising the steps of:

capturing at least one high dynamic range image;

detecting a periodic lane marker in the image for identifying a roadway lane; and

determining if the vehicle will remain within the roadway lane such that an output is communicated for use by a vehicle.

14. A method for detecting a periodic lane marker as in claim 13, further comprising the step of:

determining the period of the lane marker by identifying an edge location from the vehicle; and

storing a plurality of edge locations in at least one buffer for calculating a frequency of occurrence.

15. A method for detecting a periodic lane marker as in claim 13, further comprising the step of:

computing a period of dashed line occurrence using a Poisson point process.

16. A method for detecting a periodic lane marker as in claim 13, further comprising the step of:

computing the period of the dashed lane marker occurrence based on distance between leading edges of the periodic lane markers.

17. A method for detecting a periodic lane marker as in claim 13, further comprising the step of:

computing the period of the dashed lane marker occurrence based on a distance between the trailing edges of the periodic lane markers.

18. A method for detecting a periodic lane marker as in claim 13, further comprising the step of:

utilizing a search region used by the at least one imager for identifying the periodic lane markers.

19. A system configured to detect a raised lane marker, the system comprising:

an imager configured to capture at least one image; and

a processor in communication with the imager, the processor configured to processes the at least one image, such that a horizontal slice of the image is taken, a vertical slice of a the image is taken, a plurality of points are sampled for substantially similar intensities, a raised lane marker confidence is determined, and points are group, wherein the process is configured to detect a raised lane marker in the image.

20. A collision avoidance system for a vehicle comprising:

an imager configured to capture a plurality of high dynamic range images exterior of the vehicle; and

at least one processor in communication with the imager, the processor configured to process the one or more captured high dynamic range images, such that motion of objects in the image are detected, and determining if the vehicle will collide with the detected object, such that the processor communicates an output to avoid the collision.