Collision avoidance for vehicle control

• US 9,121,717 B1
• Filed: 12/11/2013
• Issued: 09/01/2015
• Est. Priority Date: 10/20/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhu, Jiajun
• Primary Examiner(s): Cheung, Mary
• Assistant Examiner(s): BERNS, MICHAEL ANDREW
• Application Number:
  US14/103,280
• Time in Patent Office: 629 Days
• Field of Search: 701/523, 701/408
• US Class Current: 1/1
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2520/16 Pitch
• CPC Class Codes: B60W 2552/15 Road slope, i.e. the inclination of a road segment in the longitudinal direction
• CPC Class Codes: B60W 2554/801 Lateral distance
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01S 11/12 using electromagnetic waves other than radio waves
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G05D 1/0251 extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision stereoscopic image analysis H04N13/00; depth recovery from images G06T7/593
• 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: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 9/02 Anti-collision systems

Abstract

A method is provided for processing an image in which only parts of the image that appear above a point on a horizon line are analyzed to identify an object. In one embodiment, the distance between the object and a vehicle is determined, and at least one of the speed and direction of the vehicle is changed when it is determined that the distance is less than the range of a sensor. The method for processing images is not limited to vehicular applications only and it may be used in all applications where computer vision is used to identify objects in an image.

Claims

1. A system comprising:

memory storing a range value of an object detection sensor of a vehicle; and

one or more processors configured to;

determine, based on a pitch of the vehicle, a point P on a visual horizon;

determine a distance between the vehicle and an object that is located above and beyond the point P;

compare the distance to the range value; and

when the distance is less than the range value, change at least one of a speed of the vehicle and a heading of the vehicle in order to reduce a likelihood of collision with an object not currently detectable by the object detection sensor.

2. The system of claim 1, wherein the one or more processors are further configured to change at least one of the speed and heading of the vehicle based on at least a grade of a surface on which the vehicle is standing or driving exceeding a threshold grade value.

3. The system of claim 1, wherein the one or more processors are further configured to change at least one of the speed and heading of the vehicle based on at least the pitch of the vehicle exceeding a threshold pitch value.

4. The system of claim 1, further comprising a camera configured to capture a plurality of images, and wherein the plurality of images are used to determine the distance.

5. The system of claim 4, wherein the one or more processors are further configured to determine the point P further based on a signal received from a sensor that senses the pitch of the camera.

6. The system of claim 4, wherein the camera is a stereo camera.

7. The system of claim 4, wherein the one or more processors are further configured to identify the object by extracting a template of the object from a first image of the plurality of images and comparing the template against a plurality of object representations.

8. The system of claim 1, wherein the one or more processors are further configured to identify the object based on a comparison to a representation of a type of the object.

9. The system of claim 1, wherein the one or more processors are further configured to identify the object based on proximity to the point P.

10. The system of claim 1, wherein the one or more processors are further configured to:

receive a first image of a scene at least part of the vehicle'"'"'s surroundings and a second image overlapping at least a part of the scene of the first image; and

process the first image and the second image in order to determine the point P.

11. A method comprising:

determining, by one or more processors, based on a pitch of a vehicle, a point P on a visual horizon;

determining, by the one or more processors, a distance between the vehicle and an object that is located above and beyond the point P;

comparing, by the one or more processors, the distance to a range value of an object detection sensor of the vehicle; and

when the distance is less than the range value, changing, by the one or more processors, at least one of a speed of the vehicle and a heading of the vehicle in order to reduce a likelihood of collision with an object not currently detectable by the object detection sensor.

12. The method of claim 11, wherein the at least one of the speed and heading of the vehicle are changed further based on at least a grade of a surface on which the vehicle is standing or driving exceeding a threshold grade value.

13. The method of claim 11, wherein the at least one of the speed and heading of the vehicle are changed further based on at least the pitch of the vehicle exceeding a threshold pitch value.

14. The method of claim 11, further comprising receiving a plurality of images from a camera, and wherein the distance is determined further based on the plurality of images.

15. The method of claim 14, wherein the point P is determined further based on a signal received from a sensor that senses the pitch of the camera.

16. The method of claim 14, wherein the camera is a stereo camera.

17. The method of claim 14, further comprising identifying the object by extracting a template of the object from a first image of the plurality of images and comparing the template against a plurality of object representations.

18. The method of claim 11, further comprising identifying the object based on a comparison to a representation of a type of the object.

19. The method of claim 11, further comprising identifying the object based on proximity to the point P.

20. The method of claim 11, further comprising:

receiving a first image of a scene at least part of the vehicle'"'"'s surroundings and a second image overlapping at least a part of the scene of the first image; and

processing the first image and the second image in order to determine the point P.