Abstract Disclosed is a low bit rate audio and video communication system which employs an integrated encoding system that dynamically allocates available bits among the audio and video signals to be encoded based on the content of the audio and video information and the manner in which the audio and video information will be perceived by a viewer. A dynamic bit allocation and encoding process will evaluate the current content of the audio and video information and allocate the available bits among the audio and video signals to be encoded. In addition, an appropriate audio encoding technique is dynamically selected based on the current content of the audio signal. A face location detection subroutine will detect and model the location of faces in each video frame, in order that the facial regions may be more accurately encoded than other portions of the video frame. A lip motion detection subroutine will detect the location and movement of the lips of a person present in a video scene, in order to determine when a person is speaking and to encode the lip regions more accurately. The audio and video signals generated by a second party to a communication are monitored to determine if the second party is paying attention to the audio and video information transmitted by the first party to the communication.
A method for determining if a person in front of a camera is looking in the direction of said camera at a given time, said camera generating a video signal representing a view of said person, said person having a face and lips, said method comprising the steps of: performing a face location detection subroutine at a reference time when said person is known to be looking in the direction of said camera in order to detect and model said face, said face being modelled with an ellipse defined by parametric values including a major axis and a minor axis, said major axis divided by said minor axis resulting in a reference aspect ratio; performing said face location detection subroutine on said video signal at said given time to measure said major axis and said minor axis of said modelled face ellipse at said given time, said measured major axis divided by said measured minor axis resulting in a current measured aspect ratio; and concluding that said person is not looking in said general direction of said camera at said given time if one of said following conditions occur: said face location detection subroutine performed at said given time has determined that there is no face in said video signal; or the difference between said current measured aspect ratio and said reference aspect ratio exceeds a predefined threshold.
Claim 2
Independent Claim
228 words
A method for determining if a person in front of a camera is looking in the direction of said camera at a given time, said camera generating a video signal representing a view of said person, said person having a face and lips, said method comprising the steps of: performing a face location detection subroutine at a reference time when said person is known to be looking in the direction of said camera in order to detect and model said face, said face being modelled with an ellipse defined by parametric values including a major axis and a minor axis, said major axis divided by said minor axis resulting in a reference aspect ratio; performing said face location detection subroutine on said video signal at said given time to measure said major axis and said minor axis of said modelled face ellipse at said given time, said measured major axis divided by said measured minor axis resulting in a current measured aspect ratio; and concluding that said person is not looking in said general direction of said camera at said given time if one of said following conditions occur: said face location detection subroutine performed at said given time has determined that there is no face in said video signal; or the difference between said current measured aspect ratio and said reference aspect ratio exceeds a predefined threshold.
Claim 3
Dependent Claim
105 words
The method for determining if a person is looking at a camera according to claim 1, further including the steps of: performing a lip motion detection subroutine on said video signal at said given time in order to detect and model said lips, said lips being modelled with an ellipse defined by parametric values including a major axis and a minor axis; and concluding that said person is not looking in said general direction of said camera at said given time if the distance between said minor axis of said lip ellipse and said measured major axis of said face ellipse exceed a predefined threshold.