Pedestrian face detection

• US 10,082,796 B2
• Filed: 10/27/2016
• Issued: 09/25/2018
• Est. Priority Date: 10/27/2016
• 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): Tissot, Adam D
• Application Number:
  US15/335,749
• Publication Number:
  US 20180120858A1
• Time in Patent Office: 698 Days
• Field of Search: None
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• 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 40/161 Detection; Localisation; Normalisation

Abstract

A controller for a vehicle is programmed to detect a pedestrian in an image received from a camera, determine whether a face of the pedestrian is present in the image, and cause the vehicle to change lanes based on the absence of the face.

Claims

1. A controller for a vehicle, comprising a processor and a memory storing processor-executable instructions, the processor programmed to:

detect a pedestrian in a camera image;

determine whether a face of the pedestrian is present in the image;

detect a lane adjacent the vehicle and on an opposite side of the vehicle from the pedestrian;

determine that the adjacent lane has sufficient space free of obstacles;

cause the vehicle to change lanes based on an absence of the face and on the adjacent lane having sufficient space free of obstacles;

maintain the vehicle in a present lane based on a lack of the adjacent lane, the adjacent lane having insufficient space free of obstacles, or the presence of the face;

determine whether the vehicle contains occupants; and

actuate brakes to brake based on the absence of the face and an absence of occupants.

2. The controller of claim 1, further programmed to determine whether the pedestrian is located in an area in front of and outside a forward-projected width of the vehicle.

3. The controller of claim 2, wherein the programming to determine whether a face of the pedestrian is present in the image includes programming to determine whether a face of the pedestrian is present in the image if the pedestrian is located in the area.

4. The controller of claim 1, wherein the programming to determine whether a face of the pedestrian is present in the image includes programming to determine whether two eyes of the pedestrian are present in the image.

5. The controller of claim 1, further programmed to detect a head of the pedestrian based on detecting the pedestrian.

6. The controller of claim 1, further programmed to actuate a horn to sound based on the absence of the face.

7. The controller of claim 1, further programmed to actuate a headlamp to illuminate based on the absence of the face.

8. The controller of claim 1, further programmed to actuate a propulsion to cease accelerating based on the absence of the face.

9. The controller of claim 1, further programmed to actuate brakes to brake based on the absence of the face.

10. A control system comprising:

a camera having a field of vision including an area in front of and outside a forward-projected width of a vehicle; and

a controller programmed to;

detect a pedestrian in the area based on an image received from the camera;

determine whether a face of the pedestrian is present in the image;

detect a lane adjacent the vehicle and on an opposite side of the vehicle from the pedestrian;

determine that the adjacent lane has sufficient space free of obstacles;

cause the vehicle to change lanes based on an absence of the face and on the adjacent lane having sufficient space free of obstacles;

maintain the vehicle in a present lane based on a lack of the adjacent lane, the adjacent lane having insufficient space free of obstacles, or the presence of the face;

determine whether the vehicle contains occupants; and

actuate brakes to brake based on the absence of the face and an absence of occupants.

11. The control system of claim 10, wherein the programming to determine whether a face of the pedestrian is present in the image includes programming to determine whether two eyes of the pedestrian are present in the image.

12. The control system of claim 10, wherein the controller is further programmed to detect a head of the pedestrian based on detecting the pedestrian.

13. The control system of claim 10, wherein the controller is further programmed to actuate a horn to sound based on the absence of the face.

14. The control system of claim 10, wherein the controller is further programmed to actuate a headlamp to illuminate based on the absence of the face.

15. The control system of claim 10, wherein the controller is further programmed to actuate a propulsion to cease accelerating based on the absence of the face.

16. The control system of claim 10, wherein the controller is further programmed to actuate brakes to brake based on the absence of the face.

17. A method comprising:

detecting a pedestrian in a camera image;

determining whether a face of the pedestrian is present in the image;

detecting a lane adjacent the vehicle and on an opposite side of the vehicle from the pedestrian;

determining that the adjacent lane has sufficient space free of obstacles;

causing a vehicle to change lanes based on an absence of the face and on the adjacent lane having sufficient space free of obstacles;

maintaining the vehicle in a present lane based on a lack of the adjacent lane, the adjacent lane having insufficient space free of obstacles, or the presence of the face;

determining whether the vehicle contains occupants; and

actuating brakes to brake based on the absence of the face and an absence of occupants.

18. The method of claim 17, further comprising determining whether the pedestrian is located in an area in front of and outside a forward-projected width of the vehicle.