Red-eye determination device

Patent metadata

Field	Value
Publication number	US-9298995-B2
Application number	US-201114232161-A
Country	US
Kind code	B2
Filing date	Jul 11, 2011
Priority date	Jul 11, 2011
Publication date	Mar 29, 2016
Grant date	Mar 29, 2016

Abstract

A black eye position existence probability density distribution learning unit that records a black eye position which is detected in the daytime to a black eye position existence probability density distribution, a red-eye candidate detection unit that detects red-eye candidates from the image of the driver at night, and a red-eye determination unit that determines the red eye from the red-eye candidates. The red-eye determination unit determines the red eye on the basis of the relationship between a change in the direction of the face and the behavior of the red-eye candidate and determines, as the red eye, the red-eye candidate disposed at the position of high black eye position existence probability density with reference to the black eye position existence probability density distribution.

First claim

The invention claimed is:

1. A red-eye determination device that determines a red eye from a red-eye candidate which is detected from image information of a captured image of a vehicle occupant, comprising:
circuitry configured to:
learn a black eye position existence probability density distribution from the image information acquired while the vehicle is being driven;
detect the red-eye candidate from the image information; and
determine a red-eye candidate, disposed at a position of high black eye position existence probability density in the learned black eye position existence probability density distribution, as the red-eye when two or more red-eye candidates are detected.

2. The red-eye determination device according to claim 1 , wherein the circuitry is further configured to:
detect a change in a direction of a face of the occupant;
detect a behavior of each detected red-eye candidate; and
determine the red eye on the basis of a relationship between the change in the direction of the face and the behavior of each detected red-eye candidate.

3. The red-eye determination device according to claim 1 , wherein the circuitry is further configured to:
calculate the amount of light outside the vehicle,
learn the existence probability density distribution at a time when the amount of light outside the vehicle is large, and
determine the red eye using the existence probability density distribution at a time when the amount of light outside the vehicle is small.

4. The red-eye determination device according to claim 1 , wherein the black eye position existence probability density distribution includes black eye positions over a predetermined period.

5. The red-eye determination device according to claim 4 , wherein the black eye position existence probability density distribution represents frequency of the black eye positions over the predetermined period.

Assignees

• HANITA Kiyoto
• Takemae Yoshinao
• Toyota Motor Co Ltd

Inventors

• HANITA Kiyoto
• Takemae Yoshinao

Classifications

• G06T2207/30201

  Face · CPC title

• G06T7/408

  Physics · mapped topic

• G06T7/0046

  Physics · mapped topic

• G06T2207/30041

  Eye; Retina; Ophthalmic · CPC title

• G06K9/0061

  Physics · mapped topic