Vehicle vision

• US 10,325,163 B2
• Filed: 11/22/2016
• Issued: 06/18/2019
• Est. Priority Date: 11/22/2016
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Perez Barrera, Oswaldo, Jimenez Hernandez, Alvaro
• Primary Examiner(s): Mistry, Oneal R
• Application Number:
  US15/358,402
• Publication Number:
  US 20180144199A1
• Time in Patent Office: 938 Days
• 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 computer is programmed to detect an object based on vehicle camera image data. The computer determines a light source and determines, based in part on a light source position, that the detected object is a shadow. The computer then navigates the vehicle without avoiding the object upon determining that the detected object is a shadow.

Claims

1. A computer for a vehicle, programmed to:

detect a first and a second object based on an image from a camera in the vehicle;

identify a third object including a light source;

identify a projected path of the vehicle;

determine that the first object is on the projected path of the vehicle based on the vehicle camera image by calculating a set of coordinates of the first object relative to the vehicle and determining whether the coordinates of the first object are within an area covered by the projected path, and further determine, based on a moving speed and a position of the third object including the light source and a speed of the second object, that the first object is a shadow of the second object; and

navigate the vehicle without avoiding the detected shadow of the second object.

2. The computer of claim 1, wherein the third object is a second vehicle.

3. The computer of claim 1, further programmed to determine that the first object is the shadow based on a first luminance of the first object being less than a second luminance of an area surrounding the first object in the image.

4. The computer of claim 1, further programmed to identify the projected path based on a vehicle position, a vehicle orientation, and at least two of a vehicle yaw rate, a vehicle steering angle, and a vehicle speed.

5. The computer of claim 1, further programmed to determine that the first object is the shadow by determining whether the object is located on a line between the light source and a second object casting the shadow.

6. The computer of claim 1, further programmed to determine whether the first object is the shadow by:

determining a first shape of the first object;

determining a second shape of the second object; and

determining whether the first shape is a projection of the second shape caused by the light source.

7. The computer of claim 1, further programmed to navigate the vehicle without avoiding the first object in response to determining a lack of a second object, wherein the first object is the shadow of the second object.

8. The computer of claim 1, further programmed to receive the position of the light source by:

detecting the third object based on vehicle camera image data; and

determining the position of the detected third object.

9. A method carried out in a vehicle, comprising:

detecting a first and a second object based on an image from a camera in the vehicle;

identifying a third object including a light source;

identifying a projected path of the vehicle;

determining that the first object is on the projected path of the vehicle based on the vehicle camera image by calculating a set of coordinates of the first object relative to the vehicle and determining whether the coordinates of the first object are within an area covered by the projected path, and further determining, based on a moving speed and a position of the third object including the light source and a speed of the second object, that the first object is a shadow of the second object; and

navigating the vehicle without avoiding the detected shadow of the second object.

10. The method of claim 9, wherein the third object is a second vehicle.

11. The method of claim 9, further comprising determining that the first object is the shadow based on a first luminance of the first object being less than a second luminance of an area surrounding the first object in the image.

12. The method of claim 9, further comprising identifying the projected path based on a vehicle position, a vehicle orientation, and at least two of a vehicle yaw rate, a vehicle steering angle, and a vehicle speed.

13. The method of claim 9, further comprising determining that the second object casts the shadow based on a speed of a second vehicle.

14. The method of claim 9, further comprising determining whether the first object is the shadow by:

determining a first shape of the first object;

determining a second shape of the second object; and

determining whether the first shape is a projection of the second shape caused by the light source.

15. The method of claim 9, further comprising navigating the vehicle without avoiding the first object in response to determining a lack of a second object, wherein the first object is the shadow of the second object.

16. The method of claim 9, further programmed to receive the position of the light source by:

detecting the third object based on vehicle camera image data; and

determining the position of the detected third object.