Videoconferencing method with tracking of face and dynamic...

Television – Two-way video and voice communication – User positioning

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C348S014080, C348S169000

Reexamination Certificate

active

06680745

ABSTRACT:

FIELD OF THE INVENTION
The present invention relates generally to videoconferencing and, more particularly, to the use of image recognition technology to track the faces of conference participants, thereby freeing them to move about, yet stay within camera range, and facilitating preferential allocation of bandwidth to a face portion of each video frame.
BACKGROUND
Most prior art videoconferencing systems transmit video images from a single camera, e.g. mounted on top of a computer monitor of each participant. These cameras use a “landscape” format (i.e. width dimension greater than height dimension), similar to a television set, and the system transmits the entire image. Due to the fact that typically only a limited amount of bandwidth is available, only a low-resolution image, e.g. 160 by 120 pixels, is transmitted. As a result, the user must sit relatively still, and in a position fairly close to the camera to be able to transmit a good face image. Furthermore, the automatic gain control (AGC) of the camera, which controls brightness and contrast of the image, is often controlled by simple averaging methods that do not account for the location of the face in the image.
SUMMARY OF THE INVENTION
Therefore, it is an object of the present invention to use automatic face recognition algorithms to distinguish a face portion of an image from other portions of the image, and to track any movement of the face around the room or other space in which the participant is located. This tracking can be used to automatically focus, zoom and pan the camera or, in case multiple cameras are available, to automatically switch from one camera to another, as appropriate. The camera parameter adjustments such as color balance or automatic gain control can be programmed to satisfy predetermined criteria, e.g. best lighting for reading facial expressions, or enhancement of the transmitting person's appearance by simulating a suntan. For applications requiring identification of a person, the camera can be directed to zoom in on known distinguishing characteristics of each particular person until identification has been made. If the number of persons in a room varies during a conference, the image can be adjusted to show all who are present at a particular time or, if desired, to omit observers who do not wish to be seen.


REFERENCES:
patent: 5434617 (1995-07-01), Bianchi
patent: 6091777 (2000-07-01), Guetz et al.
patent: 6297846 (2001-10-01), Edanami
patent: 409284791 (1997-10-01), None

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Videoconferencing method with tracking of face and dynamic... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Videoconferencing method with tracking of face and dynamic..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Videoconferencing method with tracking of face and dynamic... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3194693

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.