Pedestrian collision warning system

• US 10,300,875 B2
• Filed: 03/23/2018
• Issued: 05/28/2019
• Est. Priority Date: 04/27/2011
• Status: Active Grant

• Current Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Original Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Inventors: Rosenbaum, Dan, Gurman, Amiad, Samet, Yonatan, Stein, Gideon P., Aloni, David
• Primary Examiner(s): Duley, Janese
• Application Number:
  US15/934,054
• Publication Number:
  US 20180215333A1
• Time in Patent Office: 431 Days
• CPC Class Codes: B60R 21/013 including means for detecting collisions, impending collisions or roll-over
• CPC Class Codes: B60R 2300/8033 for pedestrian protection
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/269 using gradient-based methods
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

A method is provided for preventing a collision between a motor vehicle and a pedestrian. The method uses a camera and a processor mountable in the motor vehicle. A candidate image is detected. Based on a change of scale of the candidate image, it may be determined that the motor vehicle and the pedestrian are expected to collide, thereby producing a potential collision warning. Further information from the image frames may be used to validate the potential collision warning. The validation may include an analysis of the optical flow of the candidate image, that lane markings prediction of a straight road, a calculation of the lateral motion of the pedestrian, if the pedestrian is crossing a lane mark or curb and/or if the vehicle is changing lanes.

Claims

1. A method for determining a risk of collision between a host motor vehicle and a pedestrian using a camera and a processor mountable in the host motor vehicle, wherein the processor is operably connectable to the camera and the processor is configured to capture a plurality of image frames from the camera of the environment of the motor vehicle in the field of view of the camera, the method comprising:

detecting an image patch in at least one of the image frames, wherein the image patch includes a candidate image of the pedestrian in the field of view of the camera;

determining if the pedestrian is on a far side of a curb or lane mark and determining whether the pedestrian is crossing the curb or the lane mark;

in accordance with a determination that the pedestrian is on the far side of the curb or lane mark and a determination that the pedestrian is not crossing the curb or the lane mark;

inhibiting a collision warning or a collision prevention control signal; and

in accordance with a determination that the pedestrian is on the far side of the curb or lane mark and a determination that the pedestrian is crossing the curb or the lane mark;

providing a collision warning or a collision prevention control signal.

2. The method according to claim 1, further comprising predicting at least a first and a second likely paths for the host vehicle.

3. The method according to claim 2, wherein at least the first likely path is predicted, at least in part, using image data.

4. The method according to claim 3, wherein predicting the first likely path comprises processing at least one image from the plurality of image frames.

5. The method according to claim 4, wherein the at least one image is processed to detect a curb, and wherein at least one of the first likely path is predicted using the detected curb.

6. The method according to claim 4, wherein the at least one image is processed to detect a lane marking, and wherein the first likely path is predicted using the detected lane marking.

7. The method according to claim 2, further comprising:

predicting a first intersection region for the host vehicle and the pedestrian based on the first likely path; and

predicting a second intersection region for the host vehicle and the pedestrian based on the second likely path.

8. The method according to claim 7, further comprising determining whether the pedestrian is inside or moving towards the first or the second regions of intersection.

9. A system for determining a risk of collision between a host motor vehicle and a pedestrian;

comprising;

a processor configured to receive a plurality of image frames from a camera mountable in the host motor vehicle, wherein the processor is further configured to;

detect an image patch in at least one of the image frames, wherein the image patch includes a candidate image of the pedestrian in the field of view of the camera;

determine if the pedestrian is on a far side of a curb or lane mark and determining whether the pedestrian is crossing the curb or the lane mark;

in accordance with a determination that the pedestrian is on the far side of the curb or lane mark and a determination that the pedestrian is not crossing the curb or the lane mark;

inhibit a collision warning or a collision prevention control signal; and

in accordance with a determination that the pedestrian is on the far side of the curb or lane mark and a determination that the pedestrian is crossing the curb or the lane mark;

provide a collision warning or a collision prevention control signal.

10. The system according to claim 9, wherein the processor is further configured to predict at least a first and a second likely path for the host vehicle.

11. The system according to claim 10, wherein at least the first likely path is predicted, at least in part, using image data.

12. The system according to claim 11, wherein predicting the first likely path comprises processing at least one image from the plurality of image frames.

13. The system according to claim 12, wherein the at least one image is processed to detect a curb, and wherein at least one of the first likely path is predicted using the detected curb.

14. The system according to claim 12, wherein the at least one image is processed to detect a lane marking, and wherein the first likely path is predicted using the detected lane marking.

15. The system according to claim 10, wherein the processor is further configured to:

predict a first intersection region for the host vehicle and the pedestrian based on the first likely path; and

predict a second intersection region for the host vehicle and the pedestrian based on the second likely path.

16. The system according to claim 15, wherein the processor is further configured to determine whether the pedestrian is inside or moving towards the first or the second regions of intersection.

17. A vehicle, comprising:

a body;

a camera;

one or more memories storing instructions, and

one or more processors configured to execute the instructions to cause the vehicle to;

capture a plurality of image frames from the camera of the environment of the vehicle in a field of view of the camera;

detect an image patch in at least one of the image frames, wherein the image patch includes a candidate image of a pedestrian in the field of view of the camera;

determine if the pedestrian is on a far side of a curb or lane mark and determining whether the pedestrian is crossing the curb or the lane mark;

in accordance with a determination that the pedestrian is on the far side of the curb or lane mark and a determination that the pedestrian is not crossing the curb or the lane mark;

inhibit a collision warning or a collision prevention control signal; and

in accordance with a determination that the pedestrian is on the far side of the curb or lane mark and a determination that the pedestrian is crossing the curb or the lane mark;

provide a collision warning or a navigation control signal.

18. The vehicle according to claim 17, wherein the processor is further configured to predict at least a first and a second likely paths for the host vehicle.

19. The vehicle according to claim 18, wherein at least the first likely path is predicted, at least in part, using image data.

20. The vehicle according to claim 19, wherein predicting the first likely path comprises processing at least one image from the plurality of image frames.

21. The vehicle according to claim 20, wherein the at least one image is processed to detect a curb, and wherein at least one of the first likely path is predicted using the detected curb.

22. The vehicle according to claim 20, wherein the at least one image is processed to detect a lane marking, and wherein the first likely path is predicted using the detected lane marking.

23. The vehicle according to claim 18, wherein the processor is further configured to:

predict a first intersection region for the host vehicle and the pedestrian based on the first likely path; and

predict a second intersection region for the host vehicle and the pedestrian based on the second likely path.

24. The vehicle according to claim 23, wherein the processor is further configured to determine whether the pedestrian is inside or moving towards the first or the second regions of intersection.

25. The vehicle of claim 17, wherein the navigation control command comprises a steering angle, an acceleration command, a deceleration command, or a combination thereof.