System and method for detecting an eye

• US 20070014431A1
• Filed: 06/10/2005
• Published: 01/18/2007
• Est. Priority Date: 06/10/2005
• Status: Active Grant

• Current Assignee: Aptiv Technologies AG
• Original Assignee: Delphi Technologies, Inc. (BorgWarner Incorporated)
• Inventors: Wilhelm, Andrew, Hammoud, Riad
• Granted Patent: US 7,689,008 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 40/19 Sensors therefor

Abstract

A system and method are provided for detecting one or both eyes of the driver of a vehicle. The system includes a video imaging camera oriented to generate images of the driver'"'"'s face. The system also includes a video processor for processing the images generated with the video imaging camera. Filters are applied to each of potential eye candidates to determine which candidates represent an eye, weighted values are assigned to the filtered eye candidates, and an eye is detected based on the weighting of each eye candidate. According to one aspect, different size patches of potential eye candidates are processed and compared to models.

Claims

1. A system for detecting an eye, said system comprising:

a video imaging camera oriented to generate images of a face of a subject; and

a video processor for processing the images generated with the video imaging camera, said video processor comprising a salient feature detector for detecting potential eye candidates and filters for filtering the potential eye candidates based on appearance, spatial-geometrical constraint, and physiological skin property, said video processor further comprising weighting logic for weighting each potential candidate based on the appearance, spatial-geometrical constraint, and physiological skin property and generating a weighted value for each potential eye candidate, said video processor further comprising detecting logic for detecting an eye based on the weighted value of each eye candidate.

2. The system as defined in claim 1, wherein said detecting logic detects the eye based on the weighted value of each eye candidate by comparing the weighted values of each of the eye candidates and detecting the eye based on the maximum weighted value.

3. The system as defined in claim 2, wherein said filters comprise a pattern recognition filter for filtering the potential eye candidates based on appearance.

4. The system as defined in claim 3, wherein the filters comprise a spatial-geometrical constraint filter for weighting the potential eye candidates based on one or more spatial-geometrical constraints which compare horizontal eye candidates.

5. The system as defined in claim 3, wherein the filters comprise a spatial-geometrical constraint filter for weighting the potential eye candidates based on one or more spatial-geometrical constraints which compare vertical eye candidates.

6. The system as defined in claim 1, wherein said filters comprise a physiological skin property filter for weighting the potential eye candidates based on one or more physiological skin properties for comparing physiological properties of eye candidates to physiological properties of a skin region.

7. The system as defined in claim 1, wherein the video processor further includes a multi-resolution filter that compares a first patch of an eye candidate having a first size to one or more first models based on image recognition, and further compares a second patch of the eye candidate having a different second size to one or more second models based on pattern recognition

8. The system as defined in claim 1, wherein the video imaging camera is located on a vehicle to monitor the eye of the driver of the vehicle.

9. An eye detecting system for detecting an eye of a subject, said system comprising:

a video imaging camera oriented to generate images of a face of a subject; and

a video processor for processing the images generated with the video imaging camera, said video processor comprising a first image recognition filter for filtering potential eye candidates based on appearance, wherein the first image recognition filter compares a first patch of the image having a first size to a first model based on pattern recognition, said video processor further comprising a second image recognition filter for processing a second patch of the image having a different second size and comparing the image to a second model based on pattern recognition, wherein the video processor detects an eye based on the first and second image recognition filters.

10. The system as defined in claim 9, wherein said video processor further comprises weighting logic for assigning a weighted value to the filter outputs, said video processor further comprising detecting logic for detecting an eye based on the weighted value of each eye candidate.

11. The system as defined in claim 10, wherein said detecting logic detects the eye based on the weighted value of each eye candidate by comparing the weighted values of each eye candidates and detecting the eye based on the maximum weighted value.

12. The system as defined in claim 9, wherein the video processor further comprises a spatial-geometric constraint filter for weighting each potential candidate based on one or more spatial-geometric constraints.

13. The system as defined in claim 9, wherein said video processor further comprises a physiological skin property filter for weighting each candidate based on one or more physiological skin properties for comparing physiological properties of eye candidates to physiological properties of a skin region.

14. The system as defined in claim 9, wherein said video imaging camera is located on a vehicle to monitor the eye of a driver of the vehicle.

15. A method of detecting an eye, said method comprising the steps of:

arranging a video imaging camera to generate images of a face of a subject;

generating an image of the face;

detecting salient features in the image as potential eye candidates;

filtering the potential eye candidates based on appearance;

assigning a weighted value to each eye candidate based on the appearance;

filtering the potential eye candidates based on one or more spatial-geometrical constraints;

assigning a weighted value to each eye candidate based on the spatial-geometrical constraints;

filtering the potential eye candidates based on one or more physiological skin properties;

assigning a weighted value to each eye candidate based on the physiological skin properties; and

detecting an eye based on the weighted values of the eye candidates.

16. The method as defined in claim 15, wherein the step of detecting an eye comprises comparing the weighted values of each of the eye candidates and detecting the eye based on the maximum weighted value.

17. The method as defined in claim 15, wherein the step of filtering the potential eye candidates based on appearance comprises applying a pattern recognition filter to the generated image.

18. The method as defined in claim 15, wherein the step of filtering the potential eye candidates based on spatial-geometrical constraints comprises comparing pairs of horizontal eye candidates.

19. The method as defined in claim 15, wherein the step of filtering the potential eye candidates based on spatial-geometrical constrains further comprises comparing pairs of vertical eye candidates.

20. The method as defined in claim 15, wherein the step of filtering the potential eye candidates based on physiological skin properties comprises comparing brightness of eye candidates to brightness of one or more skin regions.

21. The method as defined in claim 15 further comprising the step of comparing a first patch of the eye candidate having a first size to a first model based on pattern recognition and generating a first output, comparing a second patch of the eye candidate having a different second size to a second model based on pattern recognition and generating a second output, and assigning a weighted value to each eye candidate based on the comparison of the first and second patches.

22. The method as defined in claim 15, wherein said step of arranging a video camera comprises arranging the video camera in a vehicle to monitor the eye of the driver of the vehicle.

23. A method of detecting an eye, said method comprising the steps of:

arranging a video imaging camera to generate images of a face of a subject;

generating an image of the subject;

detecting potential eye candidates in the image;

comparing a first patch of a first size to a first model based on pattern recognition and generating a first output;

assigning a weighted value to each eye candidate based on the first output;

comparing a second patch of the image having a different second size to a second model based on pattern recognition and generating a second output;

assigning a weighted value to each eye candidate based on the second output; and

detecting an eye based on the weighted value of the eye candidates.

24. The method as defined in claim 23, wherein the step of detecting potential eye candidates comprises detecting salient features in the image of the face of the subject.

25. The method as defined in claim 23, wherein the step of arranging an imaging camera comprises arranging the image camera in a vehicle to monitor the eye of the driver of the vehicle.