PEDESTRIAN COLLISION WARNING SYSTEM

• US 20120314071A1
• Filed: 04/25/2012
• Published: 12/13/2012
• Est. Priority Date: 04/27/2011
• Status: Active Grant

• Current Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Original Assignee: Mobileye Technologies Limited (Intel Corporation)
• Inventors: Gurman, Amiad, Stein, Gideon P., Rosenbaum, Dan, Samet, Yonatan, Aloni, David
• Granted Patent: US 9,233,659 B2
• Time in Patent Office: Days
• US Class Current: 348/148
• 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 preventing a collision between a motor vehicle and a pedestrian using a camera and a processor mountable in a motor vehicle, wherein the processor is operably connectible 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 a pedestrian in the field of view of the camera;

validating detection of the candidate image by analyzing optical flow between the image frames of the image patch; and

providing a collision warning or a collision prevention control signal, when the analyzed optical flow is consistent with an upright pedestrian.

2. The method of claim 1, wherein said analyzing optical flow includes:

tracking optical flow between the image frames of a plurality of image points of said image patch;

fitting the image points to at least one model selected from the group consisting of a road surface model and a vertical surface model; and

based on the best fit of the image points to said at least one model, determining a time-to-collision (TTC) if a collision is expected.

3. The method of claim 2, further comprising:

verifying said candidate image as an image of said upright pedestrian and not an object in the road surface when the best fit model is the vertical surface model.

4. A method for preventing a collision between a motor vehicle and a pedestrian, the method using a camera and a processor mountable in the motor vehicle, wherein the processor is operably connectible to the camera and the processor is configured to capture image frames from the camera of the environment of the motor vehicle in the field of view of the camera, the method comprising:

detecting a candidate image, wherein the candidate image includes the pedestrian in the field of view of the camera;

based on a change of scale of the candidate image, determining that the motor vehicle and the pedestrian are expected to collide, thereby producing a potential collision warning;

using further information from the image frames, validating the potential collision warning; and

providing a collision warning signal or a collision control signal based upon said validating.

5. The method of claim 4, wherein said validating includes analyzing optical flow of the candidate image.

6. The method of claim 4, wherein said validating includes:

predicting at least two likely paths of the vehicle;

computing a region of intersection of said at least two paths;

determining whether the pedestrian is inside or moving towards said region of intersection; and

said providing said collision warning signal or said collision control signal when the pedestrian is inside or moving towards said region of intersection.

7. The method of claim 6, wherein said at least two likely paths are selected from the group consisting of:

a path of the present lane of travel of the vehicle as indicated by lane markings or curb, a path that follows current steering angle or yaw rate, a path of travel to follow a preceding vehicle, a path which is straight ahead and a path which avoids the vehicle going up on a curb.

8. The method of claim 4, wherein said validating includes determining that lane markings predict a straight road.

9. The method of claim 4, wherein said validating includes calculating lateral motion of the pedestrian.

10. The method of claim 4, wherein said validating includes determining if the pedestrian is crossing a lane mark or curb.

11. The method of claim 4, wherein said validating includes determining if the vehicle is changing lanes.

12. The method of claim 4, wherein said validating includes:

selecting an image patch in an image frame corresponding to where the motor vehicle will be in a predetermined time interval;

monitoring said image patch; and

if the pedestrian is imaged in said image patch, then providing said collision warning signal or said collision prevention control signal.

13. The method of claim 4 wherein said determining that the motor vehicle and the pedestrian are expected to collide includes calculating a first time-to-collision based on the change of scale.

14. The method of claim 13, wherein said validating includes:

calculating a second time-to-collision based on the further information from the image frames; and

comparing the first and second times to collision.

15. The method of claim 14, wherein said providing the collision warning signal or the collision control signal is performed when the absolute value difference between the first and second time-to-collision is less than a threshold.

16. A system operable to prevent a collision between a motor vehicle and a pedestrian, the system using a camera and a processor mountable in the motor vehicle, wherein the processor is operably connectible to the camera and the processor is configured to capture image frames from the camera of the environment of the motor vehicle in the field of view of the camera, the system operable to:

detect a candidate image, wherein the candidate image includes the pedestrian in the field of view of the camera;

based on a change of scale of the candidate image, determine that the motor vehicle and the pedestrian are expected to collide, thereby producing a potential collision warning;

use further information from the image frames to give a validation of the potential collision warning; and

provide a collision warning signal or a collision control signal upon said validation.

17. The system of claim 16, wherein said validation includes analyzing optical flow of the candidate image.

18. The system of claim 16, wherein said validation includes determining that lane markings predict a straight road.

19. The system of claim 16, wherein said validation includes calculating lateral motion of the pedestrian.

20. The system of claim 16, wherein said validation includes determining if the pedestrian is crossing a lane mark or curb.