Method and apparatus for providing eye-contact function to multiple points of attendance using stereo image in video conference system
AssigneeElectronics and Telecommunications Research Institute
InventorsIn Ki Hwang, Mi Suk Lee
Life of this patent
Estimating the term…
Abstract
The present invention relates to a new eye-contact function providing method which provides a natural eye-contact function to attendances by using a stereo image and a depth image to estimate a precise depth value of the occlusion region and improve a quality of a composite eye-contact image when there are two or more remote attendances in one site at the time of a video conference using a video conference system and an apparatus therefor.
Claims14
An image processing method in an apparatus which supports video conference, the method comprising:
- generating an object mask for an image using stereo image information from a first camera and a second camera and depth image information from a depth camera and calculating an occlusion region in the object mask with respect to a depth;
- calculating an edge coordinate between objects of the image using the object mask and the occlusion region and determining a depth value of the edge coordinate of the depth image information through stereo image matching using the depth image information;
- and
- correcting such that there are depth values of the occlusion region to an end of the occlusion region toward the occlusion region in the edge coordinate.
An image processing apparatus which supports a video conference, the apparatus comprising:
- an occlusion region calculating unit which generates an object mask for an image using stereo image information from a first camera and a second camera and depth image information from a depth camera and calculates an occlusion region in the object mask with respect to a depth;
- a stereo matching unit which calculates an edge coordinate between objects of the image using the object mask and the occlusion region and determines a depth value of the edge coordinate of the depth image information through the stereo image matching using the depth image information;
- and
- a spread correcting unit which corrects such that there are depth values of the occlusion region to an end of the occlusion region toward the occlusion region in the edge coordinate.
Dependencies are inferred from the claim text.