Drowsiness detector

• US 8,433,095 B2
• Filed: 01/12/2010
• Issued: 04/30/2013
• Est. Priority Date: 02/09/2009
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Ishida, Kenji, Hachisuka, Satori
• Primary Examiner(s): BHATNAGAR, ANAND P
• Application Number:
  US12/654,976
• Publication Number:
  US 20100202658A1
• Time in Patent Office: 1,204 Days
• Field of Search: 382/100, 382/103, 382/107, 382/181, 382/190, 382/195, 382/203, 348/135, 348/143, 348169-172, 701/400
• US Class Current: 382/103
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: B60N 2/5621 by air
• CPC Class Codes: B60N 2/5657 blown towards the seat surface
• CPC Class Codes: B60N 2/5671 forming a windbreak, e.g. warm air blown on the neck of the passenger of an open vehicle
• CPC Class Codes: G06V 20/597 Recognising the driver's state or behaviour, e.g. attention or drowsiness
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G08B 21/06 indicating a condition of sleep, e.g. anti-dozing alarms

Abstract

A drowsiness detector detects the drowsiness by measuring a distance of an eyebrow at three points from a reference line defined by an inner eye corner and an outer eye corner. The three distances of the eyebrow from the reference line are respectively standardized by an inter-eye distance between the inner eye corners of the left and right eyes, and are respectively compared with thresholds for determining the rise of the eyebrow. The rise of the eyebrow is then translated as the start of the drowsiness, and is associated with an operation such as a doze prevention operation or the like.

Claims

1. A drowsiness detector comprising:

an eyebrow positioning unit for determining a position of each of at least two horizontally-separate measurement points set on at least one of right and left eyebrows, the at least two horizontally-separate measurement points being on the same one of right and left eyebrows; and

a detection unit for detecting drowsiness based on a vertical movement of the measurement points, wherein the detection unit detects drowsiness when an upward movement of the measurement points is detected.

2. The drowsiness detector of claim 1, wherein

the detection unit detects drowsiness based on the vertical movement of at least one of the measurement points.

3. The drowsiness detector of claim 1, wherein

the detection unit compares the positions of the measurement points at a wakeful time with the positions of the respective measurement points at a drowsiness detection time for detecting the vertical movement of measurement points.

4. The drowsiness detector of claim 1, wherein

three measurement points are set at an inner corner, an outer corner, and a substantial-center point of the eyebrow.

5. The drowsiness detector of claim 1, wherein

the detection unit measures the vertical movement of the position of the measurement point relative to a static reference point or a static reference line.

6. The drowsiness detector of claim 5, wherein

the static reference line is a straight line defined by an inner corner and an outer corner of an eye, and

the static reference point is a position of at least one of the inner corner of the eye, the outer corner of the eye, and a nasal cavity.

7. The drowsiness detector of claim 6, wherein

the eyebrow positioning unit measures the position of the measurement point based on image data of a face image, and

the detection unit measures the position of at least one of the inner and outer eye corners and the nasal cavity.

8. The drowsiness detector of claim 1, wherein

the detection unit detects the vertical movement of the position of at least one of the measurement points based on an area size of a polygon, and

the polygon is defined by at least one of an inner and outer eye corners and a nasal cavity, together with at least two of the measurement points.

9. The drowsiness detector of claim 1, wherein

the detection unit detects the vertical movement of the position of at least one of the measurement points based on an area size of a polygon, and the polygon is defined by an eye top point and a nasal cavity, together with at least two of the measurement points.

10. The drowsiness detector of claim 9, wherein

the eyebrow positioning unit measures the position of the measurement point based on image data of a face image, and

the detection unit measures the position of the eye top point based on image data of a face image.

11. The drowsiness detector of claim 1, wherein

the eyebrow positioning unit measures the position of the measurement point based on image data of a face image.

12. The drowsiness detector of claim 11 further comprising:

an image unit for generating the image data of the face image in a vehicle.

13. A non-transitory computer readable storage medium storing an instruction for causing a computer to provide the eyebrow positioning unit and the detection unit of claim 1.

14. A method of detecting drowsiness comprising steps of:

determining a position of each of at least two horizontally-separate measurement points that define at least one of right and left eyebrows, the at least two horizontally-separate measurement points being set on the same one of right and left eyebrows; and

detecting drowsiness based on an upward movement of the measurement points.