Method and system for estimating road lane geometry

Patent metadata

Field	Value
Publication number	US-12014554-B2
Application number	US-202217807715-A
Country	US
Kind code	B2
Filing date	Jun 18, 2022
Priority date	Jun 18, 2021
Publication date	Jun 18, 2024
Grant date	Jun 18, 2024

Abstract

A method and system for estimating road lane geometry includes a camera-estimated lane segment, for estimating lane geometry based on camera detection of road markings and a leading-vehicle-estimated lane segment, for estimating lane geometry based on traces of at least one leading vehicle. Estimated road geometry is obtained from a combination of the camera-estimated lane segment and the leading-vehicle-estimated lane segment.

First claim

The invention claimed is:

1. A method for estimating road lane geometry of a lane of a road on which a vehicle travels, the method comprising:
detecting a camera-estimated lane segment of the lane of the road based on road markings of the lane of the road in images obtained from a camera;
detecting a leading-vehicle-estimated lane segment of a lane of the road based on a trace of a leading vehicle traveling on the road in front of the vehicle;
extrapolating the camera-estimated lane segment or the leading-vehicle-estimated lane segment until the camera-estimated lane segment or the leading-vehicle-estimated lane segment overlaps with an adjacent lane segment; and
determining the road lane geometry of the lane of the road based on the extrapolated at least one of the camera-estimated lane segment or the leading-vehicle-estimated lane segment overlapping with the adjacent lane segment.

2. The method according to claim 1 , wherein detecting the camera-estimated lane segment and the leading-vehicle-estimated lane segment comprises detecting a left edge of the lane of the road and detecting a right edge of the lane of the road as a list of two-dimensional points.

3. The method according to claim 1 , wherein detecting the camera-estimated lane segment comprises performing image recognition of the road markings based on the images obtained by the camera, and
wherein the road markings comprise at least one of lane markings, curb stones, guide posts and guardrails.

4. The method according to claim 1 , wherein detecting the leading-vehicle-estimated lane segment comprises tracking the leading vehicle, storing temporal location information of the leading vehicle to obtain the trace of the leading vehicle, and determining a lane width of the lane of the road based on the trace.

5. The method according to claim 2 , further comprising:
smoothing data of the camera-estimated lane segment and the leading-vehicle-estimated lane segment by fitting a polynomial to the list of two-dimensional points; and
sampling the data of the camera-estimated lane segment and the leading-vehicle-estimated lane segment fit to the polynomial as the list of two-dimensional points.

6. The method according to claim 5 , wherein the determining comprises combining adjacent lane segments are stitched together if the overlap of the camera-estimated lane segment or the leading-vehicle-estimated lane segment with the adjacent lane segment in a direction perpendicular to a driving direction of the lane is greater than 50%.

7. The method according to claim 6 , further comprising assigning a stitching quality measure to each of the adjacent lane segments based on the overlap of the camera-estimated lane segment or the leading-vehicle-estimated lane segment with the adjacent lane segment in the direction perpendicular to the driving direction of the lane.

8. The method according to claim 7 , further comprising determining an extra road lane of the road if the overlap of the leading-vehicle-estimated lane segment with another lane segment in the direction perpendicular to the driving direction of the lane is less than 15%.

9. The method according to claim 8 , further comprising:
providing a road boundary estimation of a road boundary of the road based on radar detection of road boundaries of the road; and
rejecting leading-vehicle-estimated lane segments that lie more than 25% outside the road boundary.

10. The method according to claim 9 , further comprising broadcasting the road lane geometry to an advanced driver assistance system.

11. A system for estimating road lane geometry of the lane of the road on which a vehicle travels, the system comprising:
at least one camera; and
a computing unit configured to detect a camera-estimated lane segment of the lane of the road based on road markings of the lane of the road in images obtained from a camera, detect a leading-vehicle-estimated lane segment of a lane of the road based on a trace of a leading vehicle traveling on the road in front of the vehicle, extrapolate the camera-estimated lane segment or the leading-vehicle-estimated lane segment until the camera-estimated lane segment or the leading-vehicle-estimated lane segment overlaps with an adjacent lane segment, and determine the road lane geometry of the lane of the road based on the extrapolated at least one of the camera-estimated lane segment or the leading-vehicle-estimated lane segment overlapping with the adjacent lane segment.

Assignees

• Continental Automotive Gmbh

Inventors

• Kramadhari Prashant
• Barth Peter

Classifications

• G06T2207/30256

  Lane; Road marking · CPC title

• G06T7/60

  Analysis of geometric attributes · CPC title

• B60W40/06 Primary

  Road conditions · CPC title

• G06V20/588 Primary

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title