Method and apparatus for estimating face position in 3 dimensions

A method comprising:

• storing reference face sizes according to subject information including age, sex and race information in advance;
• acquiring two-dimensional image information from a single camera, the two-dimensional image information including a face of a subject;
• detecting a face region of the subject from the two-dimensional image information;
• calculating, by a computer, a size of the detected face region;
• judging, by a computer, the subject information in the detected face region and selecting a reference face size corresponding to the judged subject information from the reference face sizes;
• estimating, by a computer, a distance between the single camera and the face of the subject using the calculated size of the face region and the selected reference face size;
• and
• obtaining, by a computer, positional information of the face of the subject in a three-dimensional coordinate system using the estimated distance between the single camera and the face of the subject,
• wherein the obtaining of the positional information of the face of the subject in the three-dimensional coordinate system includes:
• calculating a central position of the detected face region in a two-dimensional image coordinate system;
• and
• converting the central position of the face region in the image coordinate system into a position in the three-dimensional coordinate system using the estimated distance between the single camera and the face of the subject and camera specifications including field of view (FOV) and resolution of the single camera.

An apparatus comprising:

• a camera including a single camera configured to acquire two-dimensional image information, the two-dimensional image information including a face of a subject;
• a face extractor configured to detect a face region of the subject from the two-dimensional image information acquired by the camera;
• a face size calculator configured to calculate a size of the face region detected by the face extractor;
• a distance estimator configured to estimate a distance between the single camera and the face of the subject using the size of the face region calculated by the face size calculator;
• and
• a three-dimensional position calculator configured to obtain positional information of the face of the subject in a three-dimensional coordinate system using the distance between the camera and the face of the subject estimated by the distance estimator,
• wherein the three-dimensional position calculator calculates a central position of the detected face region in an image coordinate system, and converts the calculated central position of the face region into a position in the three-dimensional coordinate system using the estimated distance between the camera and the face of the subject and camera specifications including field of view (FOV) and resolution of the camera.