Drowsiness detection system and method

• US 7,202,792 B2
• Filed: 11/11/2002
• Issued: 04/10/2007
• Est. Priority Date: 11/11/2002
• Status: Expired due to Term

• Current Assignee: Aptiv Technologies Limited (Aptiv PLC)
• Original Assignee: Delphi Technologies, Inc. (BorgWarner Incorporated)
• Inventors: Witt, Gerald J., Zhang, Harry, Smith, Matthew R.
• Primary Examiner(s): NGUYEN, HUNG T
• Application Number:
  US10/291,913
• Publication Number:
  US 20040090334A1
• Time in Patent Office: 1,611 Days
• Field of Search: 340/575, 340/576, 340/573.1, 340/573.4, 340/691, 340/693, 340/436, 340/439, 340/937, 340/573.7, 382/117, 382/118, 382/203, 382/789, 382/103, 382/104, 351/206, 351/209, 351/246, 351/211, 351/221, 701/1, 701/10, 701/45, 701/70, 180/272, 180/273, 180/271, 348/77, 348/143, 348/148, 348/151
• US Class Current: 340/575
• CPC Class Codes: B60K 28/066 actuating a signalling device B60K28/063 takes precedence
• CPC Class Codes: G08B 21/06 indicating a condition of sleep, e.g. anti-dozing alarms

Abstract

A low-cost system for detecting a drowsy condition of a driver of a vehicle includes a video imaging camera located in the vehicle and oriented to generate images of a driver of the vehicle. The system also includes a processor for processing the images acquired by the video imaging camera. The processor monitors an eye and determines whether the eye is in an open position or a closed state. The processor further determines a time proportion of eye closure as the proportion of a time interval that the eye is in the closed position, and determines a driver drowsiness condition when the time proportion of eye closure exceeds a threshold value.

Claims

1. A system for monitoring an eye of a person and detecting drowsiness of the person, the system comprising:

a video imaging camera oriented to generate images of an eye of a person; and

a processor for processing the images generated by the video imaging camera, said processor monitoring the images of the eye and determining whether the eye is in one of an open position and a closed position, wherein the processor determines that the eye is in the closed position when at least one of a sclera and an iris of an eye is not visible in the image, said processor determining a time proportion of eye closure as a number of video image frames that the eye is determined to be in the closed position as compared to the total number of video frames within a time interval and further determining a drowsiness condition when the time proportion of eye closure exceeds a threshold value.

2. The system as defined in claim 1, wherein the system is located in a vehicle for detecting an eye of a driver of the vehicle and determining a drowsiness condition of the driver of the vehicle.

3. The system as defined in claim 1, wherein the time proportion of eye closure is calculated as a running average based on a fixed number of video frames within the time interval.

4. The system as defined in claim 1, wherein the processor generates an output signal when the processor determines that the time proportion of eye closure exceeds the threshold value.

5. A system for detecting driver drowsiness in a vehicle, said system comprising:

a video imaging camera located in the vehicle and oriented to generate a sequence of video image frames showing images of an eye of a driver of the vehicle; and

a processor for processing the images generated by the video imaging camera, said processor monitoring images of the eye and determining whether the eye is in one of an open position and a closed position, wherein the processor determines that the eye is in the closed position when at least one of a sclera and an iris of an eye is not visible in the image, said processor determining a time proportion of eye closure as the proportion of a number of video image frames that the eye is determined to be in the closed position as compared to the total number of video frames within a time interval, and further determining a driver drowsiness condition when the time proportion of eye closure exceeds a threshold value.

6. The system as defined in claim 5, wherein the processor generates an output signal to initiate a countermeasure when the processor determines that the time proportion exceeds the threshold value.

7. The system as defined in claim 6, wherein the countermeasure comprises an alarm warning to the driver.

8. The system as defined in claim 6, wherein the countermeasure comprises a change in one of heating and cooling in the vehicle.

9. The system as defined in claim 5, wherein the time proportion of eye closure is calculated as a running average based on a fixed number of video frames within the time interval.

10. A method for monitoring an eye of a person and detecting a drowsiness condition of the person, said method comprising the steps of:

generating a sequence of video image frames showing images of an eye of a person with a video imaging camera;

processing the images of the eye;

determining whether the eye is one of an open position and a closed position for each image, wherein the processor determines that the eye is in the closed position when at least one of a sclera and an iris of an eye is not visible in the image;

determining a time proportion of eye closure as a number of video image frames that the eye is determined to be in the closed position as compared to the total number of video frames within a time interval; and

determining a drowsiness condition of the person when the time proportion of eye closure exceeds a threshold value.

11. The method as defined in claim 10, wherein the method monitors an eye of a driver of a vehicle and detects a drowsiness condition of the driver of the vehicle.

12. The method as defined in claim 10 further comprising the step of generating an output signal to initiate a countermeasure when the determined time proportion of eye closure exceeds the threshold value.

13. The method as defined in claim 12, wherein the countermeasure comprises an alarm warning to the driver.

14. The method as defined in claim 12, wherein the countermeasure comprises a change in one of heating and cooling.

15. The method as defined in claim 10, further comprising the step of calculating a running average of the time proportion of eye closure based on a fixed number of video frames within the time interval.

16. A method for detecting driver drowsiness in a vehicle, said method comprising the steps of:

capturing a sequence of video image frames with a video imaging camera, each frame showing an image of a driver of the vehicle;

processing the images acquired to monitor an eye of the driver;

determining whether the monitored eye is in one of an open position and a closed position, wherein the processor determines that the eye is in the closed position when at least one of a sclera and an iris of an eye is not visible in the image;

determining a time proportion of eye closure as a number of video image frames that the eye is determined to be in the closed position as compared to the total number of video frames within a time interval; and

determining a driver drowsiness condition when the time proportion of eye closure exceeds a threshold value.

17. The method as defined in claim 16 further comprising the step of generating an output signal to initiate a countermeasure when the determined time proportion of eye closure exceeds the threshold value.

18. The method as defined in claim 17, wherein the countermeasure comprises an alarm warning to the driver.

19. The method as defined in claim 17, wherein the countermeasure comprises a change in one of heating and cooling in the vehicle.

20. The method as defined in claim 16, further comprising the step of calculating a running average of the time proportion of eye closure based on a fixed number of video frames within the time interval.