Barrier and guardrail detection using a single camera

• US 10,115,027 B2
• Filed: 03/06/2017
• Issued: 10/30/2018
• Est. Priority Date: 09/21/2010
• Status: Active Grant

• Current Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Original Assignee: Mibileye Vision Technologies Limited
• Inventors: Stein, Gideon P.
• Primary Examiner(s): Rahman, Mohammad J
• Application Number:
  US15/451,146
• Publication Number:
  US 20170177953A1
• Time in Patent Office: 603 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 3/18 Image warping, e.g. rearranging pixels individually
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06T 7/74 involving reference images or patches
• 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
• 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: H04N 7/183 for receiving images from a single remote source

Abstract

Driver assistance systems for detecting a structural barrier extending along a road. The driver assistance system may be mountable in a host vehicle. The camera may capture multiple image frames in the forward field of view of the camera. A processor may process motion of images of the barrier in the image frames. The camera may be a single camera. The motion of the images may be responsive to forward motion of the host vehicle and/or the motion of the images may be responsive to lateral motion of the host vehicle.

Claims

1. An image processing method, comprising:

obtaining, via a camera located in a moving vehicle, a first image frame;

locating, in the first image frame, a first image patch comprising an image line intersecting a vanishing point in the first image frame;

obtaining, via the camera located in the moving vehicle, a second image frame;

locating, in the second image frame, a second image patch corresponding to the first image patch;

warping the first image patch based on a vertical surface model and known vehicle motion to provide a first warped image patch; and

identifying a match between the second image patch and the first warped image patch.

2. The method according to claim 1, wherein identifying a match between the second image patch and the first warped image patch comprises:

identifying, in the first image frame or in the second frame image, image data corresponding to a vertical structure.

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

determining a lateral distance between the vehicle and the vertical structure.

4. The method according to claim 1, further comprising:

warping the first image patch based on a horizontal surface model to provide a second warped image patch, and

wherein identifying a match between the second image patch and the first warped image patch comprises;

identifying, in the first image frame or in the second frame image, image data corresponding to a horizontal structure.

5. The method according to claim 4, wherein identifying a match between the second image patch and the first warped image patch comprises:

determining a matching score of the vertical surface model and the image data, and

determining a matching score of the horizontal surface model and the image data.

6. The method according to claim 4, further comprising:

determining a longitudinal distance between the vehicle and the vertical structure.

7. The method according to claim 1, wherein the first image patch is on or bounded by an image line intersecting a vanishing point in the first image frame, and the second image patch is on or bounded by an image line intersecting a vanishing point in the second image frame.

8. The method according to claim 7, wherein the image line intersecting the vanishing point in the first image frame is associated with a barrier lacking substantial vertical image texture, and the image line intersecting the vanishing point in the second image frame is associated with a barrier lacking substantial vertical image texture.

9. An image processing system, comprising:

a camera configured to be placed in a moving vehicle and obtain a first image frame; and

a processor operatively connected to the camera, the processor being operable to;

locate, in the first image frame, a first image patch comprising an image line intersecting a vanishing point in the first image frame;

obtain, via the camera located in the moving vehicle, a second image frame;

locate, in the second image frame, a second image patch corresponding to the first image patch in the first image frame;

warp the first image patch based on a vertical surface model and known vehicle motion to provide a first warped image patch; and

identify a match between the second image patch and the first warped image patch.

10. The image processing system according to claim 9, wherein the processor is operable to identify, in the first image frame or in the second frame image, image data corresponding to a vertical structure.

11. The image processing system according to claim 10, wherein the processor is operable to determine a lateral distance between the vehicle and the vertical structure.

12. The image processing system according to claim 9, wherein the processor is operable to warp the first image patch based on a horizontal surface model to provide a second warped image patch, and to identify, in the first image frame or in the second frame image, image data corresponding to a horizontal structure.

13. The image processing system according to claim 12, wherein the processor is operable to determine a matching score of the vertical surface model and the image data, and to determine a matching score of the horizontal surface model and the image data.

14. The image processing system according to claim 12, wherein the processor is operable to determine a longitudinal distance between the vehicle and the vertical structure.

15. The image processing system according to claim 9, wherein the first image patch is on or bounded by an image line intersecting a vanishing point in the first image frame, and the second image patch is on or bounded by an image line intersecting a vanishing point in the second image frame.

16. The image processing system according to claim 15, wherein the image line intersecting the vanishing point in the first image frame is associated with a barrier lacking substantial vertical image texture, and the image line intersecting the vanishing point in the second image frame is associated with a barrier lacking substantial vertical image texture.