RECOGNITION AND PREDICTION OF LANE CONSTRAINTS AND CONSTRUCTION AREAS IN NAVIGATION

• US 20160046290A1
• Filed: 08/17/2015
• Published: 02/18/2016
• Est. Priority Date: 08/18/2014
• Status: Active Grant

• Current Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Original Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Inventors: AHARONY, Hila, DYSHEL, Maria, HAREL, Amir, RABANI, Meital, SHAMAH, Shaked, HORN, Kobi
• Granted Patent: US 10,150,473 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60W 10/04 including control of propulsion units
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 10/20 including control of steering systems
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2710/18 Braking system
• CPC Class Codes: B60W 2710/20 Steering systems
• CPC Class Codes: B60W 2720/10 Longitudinal speed
• CPC Class Codes: B60W 30/0953 the prediction being responsive to vehicle dynamic parameters
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• 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 1/09623 Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle G08G1/0967 takes precedence

Abstract

Systems and methods use cameras to provide autonomous and/or driver-assist navigation features. In some implementations, techniques for predicting the location of first roadway lane constraints are provided. The system may receive multiple images of a roadway in a vicinity of a vehicle, recognize a first roadway lane constraint, and, when lane prediction conditions are determined to be satisfied, predict a location of a second roadway lane constraint. In some implementations, techniques for detecting and responding to construction zones are provided. The system may receive multiple images of a roadway in a vicinity of a vehicle, recognize indicators of a construction zone in the images, determine that the vehicle is proximate to a construction zone, and output a signal indicating that the vehicle is proximate to a construction zone.

Claims

1. A device mountable on a vehicle, comprising:

a camera adapted to capture, when mounted on the vehicle, and while the vehicle is in motion, multiple images of a roadway within a field of view of the camera;

a processor configured to;

obtain the multiple images from the camera;

apply image processing to the multiple images to recognize a first roadway lane constraint appearing in at least one of the multiple images;

determine, based on the multiple images, that one or more defined lane prediction conditions are satisfied;

in accordance with a determination that one or more defined lane prediction conditions are satisfied, predict a location of a second roadway lane constraint;

issue a notification or a control signal to control a motion of the vehicle according to the predicted location of the second roadway lane constraint.

2. The device according to claim 1, wherein the processor is configured to issue a notification or a control signal to direct a motion of the vehicle according to a location of the first roadway lane constraint.

3. The device according to claim 1, wherein the processor is configured to issue a notification or a control signal to direct a motion of the vehicle along a lane or an area between the first roadway lane constraint and the second roadway lane constraint.

4. The device according to claim 1, wherein the processor is configured to issue a notification or a control signal for moving the vehicle issue a notification or a control signal to direct a motion of the vehicle to avoid the first roadway lane constraint and the second roadway lane constraint.

5. The device of claim 1, wherein the one or more defined lane prediction conditions comprise that the second roadway lane constraint ceases to be recognized, based on the multiple images, as the vehicle moves on the roadway.

6. The device of claim 1, wherein the one or more defined lane prediction conditions comprise that the first roadway lane constraint has been recognized for at least a threshold time or a threshold distance.

7. The device of claim 1, wherein the one or more defined lane prediction conditions comprise that a guard rail is present in the vicinity of the vehicle.

8. The device of claim 7, wherein determining that a guard rail is present in the vicinity of the vehicle comprises detecting, in the one or more images, a pattern created by posts supporting the guard rail.

9. The device of claim 7, wherein the one or more defined lane prediction conditions comprise that the guard rail is casting a shadow onto the roadway.

10. The device of claim 1, wherein the one or more defined lane prediction conditions comprise that multiple substantially parallel edges are detected, in the multiple images, on one side of a lane on the roadway.

11. The device of claim 1, wherein predicting the location of the second roadway lane constraint comprises accounting for a location of the first roadway lane constraint.

12. The device of claim 1, wherein predicting the location of the second roadway lane constraint comprises predicting a width of a lane based on information about a previously determined width of the lane.

13. The device of claim 1, wherein the processor is configured to:

determine whether one or more defined lane prediction cancellation conditions are satisfied, and

in accordance with a determination that one or more defined lane prediction cancellation conditions are satisfied, cease to predict the location of the second roadway lane constraint.

14. The device of claim 13, wherein the one or more defined lane prediction cancellation conditions comprise that, after ceasing to be recognized, the second roadway lane constraint is recognized based on the one or more images.

15. The device of claim 13, wherein the one or more defined lane prediction cancellation conditions comprise that a driver is moving the vehicle between lanes.

16. The device of claim 13, wherein the one or more defined lane prediction cancellation conditions comprise that the vehicle is traversing a curve that exceeds a predefined sharpness threshold.

17. The device of claim 13, wherein determining whether one or more defined lane prediction cancellation conditions are satisfied comprises:

selecting a maximum lane prediction distance setting, and

determining whether a distance traveled by the vehicle while predicting the location of the second roadway lane constraint is greater than a maximum lane prediction distance associated with the maximum lane prediction distance setting.

18. The device of claim 17, wherein selecting a maximum lane prediction distance setting comprises, in accordance with a determination that a first lane is merging with a second lane in the vicinity of the vehicle, selecting a maximum lane prediction distance setting such that the maximum lane prediction distance is greater than a default maximum lane prediction distance.

19. The device of claim 17, wherein selecting a maximum lane prediction distance setting comprises, in accordance with a determination that defined guard-rail conditions are satisfied, selecting a maximum lane prediction distance setting having no maximum lane prediction distance.

20. The device of claim 17, wherein selecting a maximum lane prediction distance setting comprises, in accordance with a determination that defined guard-rail conditions are satisfied, selecting a maximum lane prediction distance setting such that the maximum lane prediction distance is greater than a default maximum lane prediction distance.

21. A computer system comprising:

a memory that stores instructions, and

a processor that executes the instructions to cause the system to;

obtain multiple images from a camera, the camera being adapted to capture, when mounted on the vehicle, and while the vehicle is in motion, images of the roadway within a field of view of the camera;

apply image processing to the multiple images to recognize a first roadway lane constraint appearing in at least one of the multiple images;

determine, based on the multiple images, that one or more defined lane prediction conditions are satisfied;

in accordance with a determination that one or more defined lane prediction conditions are satisfied, predict a location of a second roadway lane constraint;

issue a notification or a control signal to direct a motion of the vehicle according to the predicted location of the second roadway lane constraint.

22. A method comprising:

at a system comprising a memory that stores instructions and a processor that executes the instructions;

obtaining multiple images from a camera, the camera being adapted to capture, when mounted on a vehicle, and while the vehicle is in motion, images of a roadway within a field of view of the camera;

applying image processing to the multiple images to recognize a first roadway lane constraint appearing in at least one of the multiple images;

determining, based on the multiple images, that one or more defined lane prediction conditions are satisfied;

in accordance with a determination that one or more defined lane prediction conditions are satisfied, predicting a location of a second roadway lane constraint;

issuing a notification or a control signal to direct a motion of the vehicle according to the predicted location of the second roadway lane constraint.

23. A vehicle comprising:

a body;

a camera adapted to capture, when mounted on the vehicle, and while the vehicle is in motion, multiple images of a roadway within a field of view of the camera;

a processor configured to;

obtain the multiple images from the camera;

apply image processing to the multiple images to recognize a first roadway lane constraint appearing in at least one of the multiple images;

determine, based on the multiple images, that one or more defined lane prediction conditions are satisfied;

in accordance with a determination that one or more defined lane prediction conditions are satisfied, predict a location of a second roadway lane constraint;

issue a notification or a control signal to control a motion of the vehicle according to the predicted location of the second roadway lane constraint.

24. A device mountable on a vehicle, comprising:

a camera adapted to capture, when mounted on the vehicle, and while the vehicle is in motion, multiple images of a roadway within a field of view of the camera, and

a processor configured to;

obtain the multiple images from the camera;

apply image processing to the multiple images to recognize, in the multiple images, one or more indicators of a construction zone, and

in accordance with recognizing the one or more indicators of a construction zone, output a signal indicating that the vehicle is proximate to a construction zone.

25. The device of claim 24, wherein the processor is configured to:

determine, based on the one or more indicators, that the vehicle is proximate to a construction zone, and

in accordance with the determination that the vehicle is proximate to a construction zone, output the signal indicating that the vehicle is proximate to a construction zone.

26. The device of claim 24, wherein the output signal is perceptible by a driver of the vehicle.

27. The device of claim 24, wherein the output signal is a control signal that controls a motion of the vehicle.

28. The device of claim 24, wherein the one or more indicators of a construction zone comprise one of:

cones present in the vicinity of the roadway, barrels present in the vicinity of the roadway, poles present in the vicinity of the roadway, and barriers present in the roadway.

29. The device of claim 24, wherein the one or more indicators of a construction zone comprise predefined traffic signs.

30. The device of claim 24, wherein the one or more indicators of a construction zone comprise construction zone lane lines.

31. The device of claim 24, wherein the instructions cause the system to:

in accordance with the determination that the vehicle is proximate to a construction zone, cause the moving vehicle to move in accordance with the construction zone indicators.

32. The device of claim 31, wherein causing the moving vehicle to move in accordance with the construction zone indicators comprises one of:

causing reducing a speed of the vehicle;

causing changing a lane in which the vehicle is traveling;

enabling avoiding cones, barrels, poles, and/or barriers; and

causing following construction zone lane constraints rather than conventional lane constraints.

33. The device of claim 24, wherein the instructions cause the system to:

determine, based on the one or more indicators, that the construction zone is a complex construction zone, and

in accordance with a determination that the construction zone is a complex construction zone, disable automated vehicle control functionality.

34. The device of claim 33, wherein the determination that the construction zone is a complex construction zone comprises the recognition of one of:

cones present in a lane in which the vehicle is present, barrels present in a lane in which the vehicle is present, poles present in a lane in which the vehicle is present, and barriers present in a lane in which the vehicle is present.

35. The device of claim 33, wherein the determination that the construction zone is a complex construction zone comprises the recognition of a number of cones, barrels, poles, and/or barriers in the vicinity of the vehicle exceeding a predefined threshold number.

36. A computer system comprising:

a memory that stores instructions, and

a processor that executes the instructions to cause the system to;

obtain multiple images from a camera, the camera being adapted to capture, when mounted on the vehicle, and while the vehicle is in motion, images of the roadway within a field of view of the camera;

apply image processing to the multiple images to recognize, in the multiple images, one or more indicators of a construction zone, and

in accordance with recognizing the one or more indicators of a construction zone, output a signal indicating that the vehicle is proximate to a construction zone.

37. A method comprising:

at a system comprising a memory that stores instructions and a processor that executes the instructions;

obtaining multiple images from a camera, the camera being adapted to capture, when mounted on a vehicle, and while the vehicle is in motion, images of a roadway within a field of view of the camera;

applying image processing to the multiple images to recognize, in the multiple images, one or more indicators of a construction zone, and

in accordance with recognizing the one or more indicators of a construction zone, output a signal indicating that the vehicle is proximate to a construction zone.

38. A vehicle, comprising:

a body;

a camera adapted to capture, when mounted on the vehicle, and while the vehicle is in motion, multiple images of a roadway within a field of view of the camera, and

a processor configured to;

obtain the multiple images from the camera;

apply image processing to the multiple images to recognize, in the multiple images, one or more indicators of a construction zone, and

in accordance with recognizing the one or more indicators of a construction zone, output a signal indicating that the vehicle is proximate to a construction zone.