SYSTEM AND METHOD FOR DETECTING DROWSY FACIAL EXPRESSIONS OF VEHICLE DRIVERS UNDER CHANGING ILLUMINATION CONDITIONS
First Claim
1. A method of detecting drowsy facial expressions of vehicle drivers under changing illumination conditions comprising:
- capturing an image of a person'"'"'s face using an image sensor;
detecting a face region of the image using a pattern classification algorithm;
performing, using an active appearance model algorithm, local pattern matching to identify a plurality of landmark points on the face region of the image;
generating a 3D face model with facial muscles of the face region;
determining photometric flows from the 3D face model using an extract photometric flow module;
determining geometric flows from the 3D face model using a compute geometric flow module;
determining a noise component generated by varying illuminations by comparing the geometric flows to the photometric flows; and
removing the noise component by subtracting two photometric flows.
3 Assignments
0 Petitions
Accused Products
Abstract
The present invention includes a method of detecting drowsy facial expressions of vehicle drivers under changing illumination conditions. The method includes capturing an image of a person'"'"'s face using an image sensor, detecting a face region of the image using a pattern classification algorithm, and performing, using an active appearance model algorithm, local pattern matching to identify a plurality of landmark points on the face region of the image. The method also includes generating a 3D face model with facial muscles of the face region, determining photometric flows from the 3D face model using an extract photometric flow module, determining geometric flows from the 3D face model using a compute geometric flow module, determining a noise component generated by varying illuminations by comparing the geometric flows to the photometric flows, and removing the noise component by subtracting two photometric flows.
-
Citations
20 Claims
-
1. A method of detecting drowsy facial expressions of vehicle drivers under changing illumination conditions comprising:
-
capturing an image of a person'"'"'s face using an image sensor; detecting a face region of the image using a pattern classification algorithm; performing, using an active appearance model algorithm, local pattern matching to identify a plurality of landmark points on the face region of the image; generating a 3D face model with facial muscles of the face region; determining photometric flows from the 3D face model using an extract photometric flow module; determining geometric flows from the 3D face model using a compute geometric flow module; determining a noise component generated by varying illuminations by comparing the geometric flows to the photometric flows; and removing the noise component by subtracting two photometric flows. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A method of detecting facial expressions of a person under changing illumination conditions comprising:
-
capturing an image of a person'"'"'s face using an image sensor; detecting a face region of the image using a pattern classification algorithm; performing, using an active appearance model algorithm, local pattern matching to identify a plurality of landmark points on the face region of the image; generating a 3D face model with facial muscles of the face region; categorizing the facial muscles into action units; determining photometric flows from the 3D face model using an extract photometric flow module; determining geometric flows from the 3D face model using a compute geometric flow module; comparing the geometric flows with stored geometric flows for a match; retrieving the stored geometric flows that match the geometric flows; and determining whether a facial deformation of the face region exists using the retrieved geometric flows. - View Dependent Claims (7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17)
-
-
18. A method of detecting facial expressions of a person under changing illumination conditions comprising:
-
capturing an image of a person'"'"'s face using an image sensor; detecting a face region of the image using a pattern classification algorithm; performing, using an active appearance model algorithm, local pattern matching to identify a plurality of landmark points on the face region of the image; generating a 3D face model with facial muscles of the face region; determining photometric flows from the 3D face model using an extract photometric flow module; determining geometric flows from the 3D face model using a compute geometric flow module; and determining whether a facial deformation of the face region exists using the photometric flows or the geometric flows. - View Dependent Claims (19, 20)
-
Specification