Lane relative position estimation method and system for driver assistance systems

• US 9,352,746 B2
• Filed: 01/21/2015
• Issued: 05/31/2016
• Est. Priority Date: 01/22/2014
• Status: Active Grant

• Current Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Original Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Inventors: Fritsch, Jannik, Khnl, Tobias
• Primary Examiner(s): Beaulieu, Yonel
• Application Number:
  US14/601,584
• Publication Number:
  US 20150203114A1
• Time in Patent Office: 496 Days
• Field of Search: 701/41
• US Class Current: 1/1
• CPC Class Codes: B60W 30/12 Lane keeping
• 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 system and method for lane relative position estimation. The environment of a vehicle is first sensed, and spatial features are then extracted and classified from information obtained from the sensing. The spatial features capture lateral position information within a lane, and an output signal including the result of the classification, which represents the relative lateral positioning of a road location with respect to the overall lane shape, is generated.

Claims

1. A method for lane relative position estimation, wherein this method comprises:

sensing the environment of a vehicle with at least one sensor means;

extracting spatial features from information obtained from the sensor means;

classifying the extracted spatial features, wherein the spatial features capture lateral position information within a lane by including information having a correlation with a particular location on the lane,

wherein a lateral location change results in a different spatial feature value, and

wherein the classifying generates directly as a result a lane relative position estimation; and

outputting in an output signal the result of the classification which represents the relative lateral positioning of a road location with respect to an overall lane shape.

2. The method according to claim 1, wherein

a continuous lane relative position value is obtained by the classification of the extracted spatial features.

3. The method according to claim 1, wherein

a classifier that performs classification is trained by means of a training signal which contains different lane relative position values for laterally neighboring locations within a particular lane.

4. The method according to claim 1, wherein

information contained in the spatial features represents spatial relation of the road location to at least one road entity with an associated area in the two-dimensional road environment.

5. The method according to claim 4, wherein

the spatial relation to a road entity is capturing the geometric properties of the road location relative to a road entity.

6. The method according to claim 4, wherein

the spatial relation to a road entity is capturing geometric properties of the road location that is positioned within the area covered by the scene element.

7. The method according to claim 2, wherein

the lane relative position value is extracted for one road location, in order to extract information about the course of the lane at this road location.

8. The method according to claim 1, wherein

multiple road locations are analyzed in order to extract the course of multiple lanes or the overall road.

9. The method according to claim 1, wherein

a human machine interface (HMI), communicates the lane relative position of an expected future vehicle location to a driver of a vehicle in order to warn about a critical lateral position of the vehicle.

10. The method according to claim 1, wherein

a human machine interface (HMI) provides feedback to a driver about the lateral positioning within its lane in order to improve the driver'"'"'s driving skill.

11. The method according to claim 1, wherein

a depth sensor provides additional depth information.

12. A system for lane relative position estimation, comprising sensor means sensing the environment of a vehicle, a spatial features generating block for extracting spatial features from information obtained from the sensor means and a classifier for classifying the extracted spatial features, wherein

the spatial feature generating block is configured to generate spatial features that capture lateral position information within a lane by including information having a correlation with a particular location on the lane, wherein a lateral location change results in a different spatial feature value, and

the classifier is configured to generate directly as a result the lane relative position estimation, and to output in an output signal the result of the classification which represents the relative lateral positioning of the road location with respect to an overall lane shape.

13. The system according to claim 12, wherein

the classifier is configured to output a continuous lane relative position value obtained by the classification of the extracted spatial features.

14. The system according to claim 12, wherein

the classifier is trained by means of a training signal which contains different lane relative position values for laterally neighboring locations within a particular lane.

15. The system according to claim 12, wherein

information contained in the spatial features represents a spatial relation of the road location to at least one road entity with an associated area in the two-dimensional road environment.

16. The system according to claim 12, wherein

the spatial relation to a road entity captures geometric properties of the road location relative to a road entity.

17. The system according to claim 12, wherein

the spatial relation to a road entity captures geometric properties of the road location that is positioned within the area covered by the scene element.

18. The system according to claim 13, wherein

the classifier is configured to extract the lane relative position value for one road location, in order to extract information about the course of the lane at this road location.

19. The system according to claim 12, wherein

the classifier is configured to analyze multiple road locations in order to extract the course of multiple lanes or the overall road.

20. The system according to claim 12, wherein

the system comprises a human machine interface (HMI) that communicates the lane relative position of the expected future vehicle location to a driver of a vehicle in order to warn about a critical lateral position of the vehicle.

21. The system according to claim 12, wherein

the system comprises a human machine interface (HMI) that provides feedback to a driver about the lateral positioning within its lane in order to improve the driver'"'"'s driving skill.

22. The system according to claim 12, wherein

the system comprises a depth sensor that provides additional depth information.