Eye gazing imaging for video communications

• US 8,154,583 B2
• Filed: 05/31/2007
• Issued: 04/10/2012
• Est. Priority Date: 05/31/2007
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Eastman Kodak Company
• Inventors: Kurtz, Andrew F., Luo, Jiebo
• Primary Examiner(s): Ramakrishnaiah, Melur
• Application Number:
  US11/756,575
• Publication Number:
  US 20080297589A1
• Time in Patent Office: 1,776 Days
• Field of Search: 348 1401- 1416
• US Class Current: 348/14.16
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

Video communication systems and methods for communicating between an individual in a local environment, and a remote viewer in a remote environment are provided. The system has an image display device; at least one image capture device which acquires video images for fields of view of a local environment, and any individuals therein; an audio system having an audio emission device and an audio capture device; a computer, which includes a contextual interface having a gaze adapting process, and image processor; and a communication controller which transmits and receives video images of the local environment and the remote environment, and data regarding video scene characteristics thereof across a network between the local environment and the remote environment; wherein the gaze adapting process identifies video scene characteristics of the local environment indicative of eye gaze image capture and altering the video images when the characteristics are indicative.

Claims

1. A method for providing eye contact video images of an individual in a local environment to a remote individual during a communication event using a video communication system, comprising:

initiating a communication event by establishing a video communication link with a video communication system at a remote site;

initiating the capture of a video images of a video scene within a local environment including an individual therein;

determining a video context for the video scene, the associated eye-gaze context rules and the associated range of variation for gaze metrics indicative of eye gaze image capture;

analyzing current video images of the video scene to determine current gaze metrics relative to participating individual in the local environment;

comparing the current gaze metrics with the determined range of gaze metrics; and

when the current gaze metrics are within a range,

modifying the video capture or video processing of the video images in a manner that generates eye gaze corrected images of the local individual which provide eye contact to the remote individual.

2. The method as in claim 1, wherein the context rules determine the gaze metrics for a given video scene based upon the defined video context and the field of view encompassed by the captured video images.

3. The system according to claim 2 wherein the defined video context is determined from identified contextual cues that include event classifications, user classifications, user identity, user gestures, user behaviors, or user privacy settings.

4. The system according to claim 2 wherein the defined video context is determined with respect to defined automatic video capture modes that each specify a range of defined video capture settings, the automatic video capture modes including a fully automatic mode, a semi-automatic mode, a preview mode, a lock and follow mode, a hierarchical mode, a portable mode, a media space, or one of various modes based upon given event classifications.