METHOD FOR ESTIMATING TRAFFIC LANES

• US 20180173970A1
• Filed: 05/13/2016
• Published: 06/21/2018
• Est. Priority Date: 05/22/2015
• Status: Active Grant

• Current Assignee: Continental Teves AG & Co. OHG (Continental AG)
• Original Assignee: Continental Teves AG & Co. OHG (Continental AG)
• Inventors: Bayer, Christopher, Loy, Claudia
• Granted Patent: US 10,650,253 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/253 of extracted features
• 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 method for estimating traffic lanes uses as input data the position and direction of feature vectors, which are measured from multiple different sensors independently of one another. A feature vector is formed by a position in the coordinate system of the ego-vehicle, which position describes a point on the border of a traffic lane, and a direction or an angle which indicates the direction in which the border of the traffic lane runs at this position. Further input data are variables which represent the quality of the measurement of the positional and the directional accuracy and the probability of the existence of a feature vector. The input data are accumulated chronologically together. The geometry of traffic lanes is estimated from the accumulated input data, taking into account the quality of the measurement. The estimated geometry of traffic lanes is output.

Claims

1. A method for estimating traffic lanes using input data, wherein the input data comprise

the position and direction of feature vectors, which are measured from multiple different sensors independently of one another, wherein the position describes a point on the border of a traffic lane and the direction indicates in which direction the border of the traffic lane runs at this position, and

variables which represent the quality of the measurement of the positional and the directional accuracy and the probability of the existence of a feature vector,

wherein the method has the following steps:

the input data are accumulated chronologically together,

the geometry of traffic lanes is estimated from the accumulated input data, taking into account the quality of the measurement of the positional and the directional accuracy as well as the probability of existence of the feature vector, and

the estimated geometry of traffic lanes is output.

2. The method according to claim 1, wherein accumulated feature vectors, which lie together, are associated in an additional step.

3. The method according to claim 2, wherein associated feature vectors are fused in an additional step.

4. The method according to claim 3, wherein, based on the accumulated, associated or fused feature vectors, geometric model assumptions are used during the estimation of the geometry of traffic lanes.

5. The method according to claim 4, wherein a GraphSLAM method is used in order to estimate traffic lanes.

6. The method according to claim 5, wherein the input data are measured by at least two of the following sensors:

monocular front camera looking in the direction of travel of a vehicle,

stereo camera looking in the direction of travel of a vehicle,

a camera having a lateral and/or rearward detection range

a camera of a panoramic view system,

other optical 3D sensor technology,

beam sensor,

vehicle sensors, or

position detecting device in conjunction with a digital map, a backend database and/or vehicle-to-vehicle communication devices.

7. The method according to claim 6, wherein the input data are ascertained from:

traffic lane sideline marking detection,

detection of objects which delimit a traffic lane,

trajectory measurement of vehicles driving in front and/or oncoming vehicles.

8. The method according to claim 7, wherein the output estimated geometry of traffic lanes is used within the framework of

lane departure warning,

fatigue warning,

lane change assistance,

active lane keeping assistance,

lane centering,

route guidance,

road sign assistance,

overtaking maneuver assistance,

assistance with observing traffic regulations,

emergency braking assistance,

emergency steering assistance, and/or

autonomous vehicle guidance.

9. A device for estimating traffic lanes comprising:

accumulating means which are configured to accumulate input data from multiple different sensors chronologically together, wherein the input data comprise;

the position and direction of feature vectors, which are measured from multiple different sensors independently of one another, wherein the position describes a point on the border of a traffic lane and the direction indicates in which direction the border of the traffic lane runs at this position, and

variables which represent the quality of the measurement of the positional and the directional accuracy as well as the probability of the existence of a feature vector,

estimating means which are configured to estimate the geometry of traffic lanes from the accumulated input data, taking into account the quality of the vectors, and

output means which are configured to output the estimated geometry of traffic lanes.