Application of human facial features recognition to automobile security and convenience

• US 7,110,570 B1
• Filed: 07/21/2000
• Issued: 09/19/2006
• Est. Priority Date: 07/21/2000
• Status: Expired due to Fees

• Current Assignee: TRW Limited (Zeppelin - Stiftung der Stadt Friedrichshafen)
• Original Assignee: TRW Limited (Zeppelin - Stiftung der Stadt Friedrichshafen)
• Inventors: Dunbridge, Barry, McIver, George W., Shreve, Gregory A., Niesen, Joseph W., Berenz, John J.
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): NAKHJAVAN, SHERVIN K
• Application Number:
  US09/621,772
• Time in Patent Office: 2,251 Days
• Field of Search: 382/102, 382 1- 2, 382/103, 382/104, 382/115, 382/117, 382/118, 382/190, 382/209, 382/218, 382/224, 340/426.1, 340/426.28, 340/426.12, 340/426.26, 340/146.2, 340/541, 340/542, 340/565, 340/5.2, 340/5.3, 340/5.53, 340/5.81, 340/5.83, 367/136, 348/148, 348/152, 348/153
• US Class Current: 382/104
• CPC Class Codes: B60R 21/01534 using electromagneticwaves, e.g. infrared
• CPC Class Codes: B60R 21/01538 for image processing, e.g. cameras or sensor arrays
• CPC Class Codes: B60R 21/01542 detecting passenger motion
• CPC Class Codes: B60R 21/01552 detecting position of specific human body parts, e.g. face, eyes or hands
• CPC Class Codes: B60R 25/25 using biometry
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G08B 13/19608 Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
• CPC Class Codes: G08B 13/19645 Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
• CPC Class Codes: G08B 13/19647 Systems specially adapted for intrusion detection in or around a vehicle
• CPC Class Codes: G08B 21/06 indicating a condition of sleep, e.g. anti-dozing alarms

Abstract

An imaging system (50) for providing vehicle security and convenience features that employs face recognition software to identify and track a person. The system (50) employs infrared emitters (30) that emit an infrared signal along a predetermined field-of-view, and an infrared sensor (34), such as a CMOS sensor used as a video signal array, that receives reflected infrared illumination from objects in the field-of-view. A processor (52) including the face recognition software, is employed to detect human faces to identify and track the person. Once a face is detected, it can be compared to a data base to identify the person. Various applications for the imaging system (50) to provide driver convenience and security include determining driver identification as the driver approaches the vehicle, determining if a potential thief is in the vehicle by face recognition, providing driver seat adjustment, rear and side mirror adjustment and steering wheel adjustment, providing vehicle speed control, automatically starting the vehicle, etc.

Claims

1. An imaging system for a vehicle, the imaging system comprising:

an illuminator for illuminating a predefined field located outside of the vehicle and adjacent an entryway to an interior of the vehicle;

a detector for detecting radiation reflected from a person located in the predefined field, the detector being responsive to the detected radiation for providing image signals; and

a processor that is responsive to the image signals from the detector, the processor including face recognition software for analyzing the image signals for facial features of the person located in the predefined field, the processor comparing facial features of the person to known facial features of authorized vehicle occupants to determine whether the person is an authorized vehicle occupant, the processor causing the entryway to automatically become unlocked in response to a determination that the person is an authorized vehicle occupant,

wherein the illuminator is also adapted to illuminate a predefined interior vehicle field and the detector is adapted to detect radiation reflected from an occupant of the vehicle that is located in the predefined vehicle interior field and to providing occupant image signals, the processor comparing facial features of the occupant image signals to the known facial features of authorized vehicle occupants and causing a vehicle operation to be performed in response to a facial feature match.

2. The imaging system of claim 1 wherein the illuminator is an infrared source and wherein the detector is an infrared detector for receiving reflected infrared radiation.

3. The imaging system of claim 2 further comprising an infrared filter positioned between the detector and the predefined field.

4. The imaging system of claim 2 wherein the infrared source includes a cluster of infrared light emitting diodes.

5. The imaging system of claim 1 wherein the known facial features of the authorized vehicle occupants are facial images of the authorized occupants that are stored in a memory associated with the processor.

6. The imaging system of claim 1 wherein the illuminator is pulsed on and off, the detector obtaining a first image when the illuminator is on and obtaining a second image when the illuminator is off, the processor determining a difference between the first and second images to mitigate effects of ambient light.

7. The imaging system of claim 1 wherein the system monitors gestures of the occupant and performs vehicle functions in response to detected gestures.

8. The imaging system of claim 1 wherein the vehicle is started in response to the facial feature match between the occupant image signals and the known facial features.

9. The imaging system of claim 1 wherein the processor, in response to a facial feature match, identifies the occupant and limits operation of the vehicle to a maximum driving speed associated with the identified occupant.

10. The imaging system of claim 1 further including an intrusion alarm, the processor actuating the intrusion alarm in response to determining that the facial features of the occupant image signals do not match the known facial features of authorized vehicle occupants.

11. The imaging system of claim 10 wherein the processor records an image of the occupant in a memory in response to determining that the facial features of the occupant image signals do not match the known facial features of authorized vehicle occupants.

12. An intruder detection system for a vehicle, the intruder detection system comprising:

an illuminator for illuminating an interior portion of the vehicle;

a detector for detecting radiation reflected from a person located in the interior portion, the detector being responsive to the detected radiation for providing image signals indicative of an image of the person; and

a processor that is responsive to the image signals from the detector, the processor including face recognition software for analyzing the image signals for facial features of the person, the processor comparing facial features of the person to known facial features of authorized vehicle occupants to determine whether the person is an authorized vehicle occupant, the processor sounding an alarm and recording the image of the person in a memory when the processor determines that the person is not an authorized vehicle occupant.

13. The intruder detection system of claim 12 wherein the illuminator is an infrared source and wherein the detector is an infrared detector for receiving reflected infrared radiation.

14. The intruder detection system of claim 13 further comprising an infrared filter positioned between the detector and the predetermined field.

15. The intruder detection system of claim 13 wherein the infrared source includes a cluster of infrared light emitting diodes.

16. The imaging system of claim 12 wherein the illuminator is pulsed on and off, the detector obtaining a first image when the illuminator is on and obtaining a second image when the illuminator is off, the processor determining a difference between the first and second images to mitigate effects of ambient light.