Abstract: A method is provided in one example and includes receiving a video input from a camera element; using change detection statistics to identify background image data; using the background image data as a temporal reference to determine foreground image data of a particular video frame within the video input; using a selected foreground image for a background registration of a subsequent video frame; and providing at least a portion of the subsequent video frame to a next destination.

Abstract: Clock synchronization for an acoustic echo canceller (AEC) with a speaker and a microphone connected over a digital link may be provided. A clock difference may be estimated by analyzing the speaker signal and the microphone signal in the digital domain. The clock synchronization may be combined in both hardware and software. This synchronization may be performed in two stages, first with coarse synchronization in hardware, then fine synchronization in software with, for example, a re-sampler.

Abstract: A method for transition control in a videoconference comprises receiving a plurality of video streams from a plurality of cameras, displaying a first video stream of the plurality of video streams, detecting a stream selection event for display of a second video stream of the plurality of video streams, determining a transition category for a transition from the first video stream to the second video stream, and selecting a display transition based on the transition category for displaying the transition from the first video stream to the second video stream.

Abstract: Video frames are captured at one or more cameras during a video conference session, where each video frame includes a digital image with a plurality of pixels. Depth values associated with each pixel are determined in at least one video frame, where each depth value represents a distance of a portion of the digital image represented by at least one corresponding pixel from the one or more cameras that capture the at least one video frame. Luminance values of pixels are adjusted within captured video frames based upon the depth values determined for the pixels so as to achieve relighting of the video frames as the video frames are displayed during the video conference session.

Abstract: Techniques are provided for establishing a videoconference session between participants at different endpoints, where each endpoint includes at least one computing device and one or more displays. A plurality of video streams is received at an endpoint, and each video stream is classified as at least one of a people view and a data view. The classified views are analyzed to determine one or more regions of interest for each of the classified views, where at least one region of interest has a size smaller than a size of the classified view. Synthesized views of at least some of the video streams are generated, wherein the synthesized views include at least one view including a region of interest, and views including the synthesized views are rendered at one or more displays of an endpoint device.

Abstract: A video coder includes a forward coder and a reconstruction module determining a motion compensated predicted picture from one or more previously decoded pictures in a multi-picture store. The reconstruction module includes a reference picture predictor that uses only previously decoded pictures to determine one or more predicted reference pictures. The predicted reference picture(s) are used for motion compensated prediction. The reference picture predictor may include optical flow analysis that uses a current decoded picture and that may use one or more previously decoded pictures together with affine motion analysis and image warping to determine at least a portion of at least one of the reference pictures.

Abstract: A system and method for reducing blurred video caused by intra-coded IDR-frames sent in response to when a destination endpoint in a multipoint videoconference switches to a new video source. An embodiment according to the invention comprises using inter-coded temporal predictive referencing a long term reference frame (LTRF) instead of IDR-frames in a multipoint videoconference system.

Abstract: Techniques are provided for dynamically adapting the view from a conference endpoint that includes a presentation apparatus, such as a whiteboard. A first signal is received that includes a video signal derived from a video camera that is viewing a room during a conference session in which a person is presenting information on a presentation apparatus. During the video conference, switching is performed between the first signal and a second signal representing content being displayed on the presentation apparatus during the conference session for output and transmission to other conference endpoints of the conference session. The determination as to whether to supply the first signal (for a normal view of the conference room) or the second signal may be based on a position determination of the presenter or may be instead be based on an external view selection command received from another conference endpoint participating in the conference session.

Abstract: An apparatus, software encoded in tangible media, and a method at an encoder. The method includes sending compressed video data including a reference frame message to create a long term reference frame to a plurality of decoders at one or more destination points, receiving feedback from the decoders indicative of whether or not the decoders successfully received the reference frame message, and in the case that the received feedback is such that at least one of the decoders did not successfully receive the reference frame message or does not have the indicated recent frame, repeating sending a reference frame message to create the long term reference frame. Using the method can replaces I-frame error recovery with long term reference frames, even in the case where the reference frame management messages are lost to at least one decoder.

Abstract: An apparatus, a method, and a computer-readable medium having instructions encoded thereon that when executed cause a method to be carried out. The method includes dividing at least a portion of a picture of a video stream into parts of blocks, and processing the parts in parallel by a plurality of interconnected processors. The processing of a respective part by its respective processor includes edge detection and color segmentation to determine block-level edge features including block-level color-segmented edge features. Each processor also performs coding functions on its respective part of the picture. The method also includes block-level processing using the block-level edge features to determine which blocks in the picture are likely to be that of a face, the block-level processing being at the granularity of at least a block.

Abstract: In one embodiment, a method of lighting is disclosed which includes apportioning a video display screen into a content portion and at least one light portion. The content portion displays video content and the light portion provides auxiliary lighting when energized to illuminate a subject adjacent the video display screen.

Abstract: A system and method for alerting participants in a videoconference that one or more participants are improperly framed by the videoconference camera is provided. An embodiment comprises a temporary self-view picture-in-picture image appearing when the number of faces detected by the videoconference camera changes. A face detection algorithm is used to determine when the number of faces being detected by the videoconference camera has changed. The self-view picture-in-picture image displays, for a duration of time, a representation of the image being captured by the videoconference camera, allowing participants who are not properly framed by the videoconference camera to adjust their position to that their faces are captured by the videoconference camera.

Abstract: In one embodiment, a method includes receiving audio at a plurality of microphones, identifying a sound source to be muted, processing the audio to remove sound received from the sound source at each of the microphones, and transmitting the processed audio. An apparatus is also disclosed.

Abstract: A video coder includes a forward coder and a reconstruction module determining a motion compensated predicted picture from one or more previously decoded pictures in a multi-picture store. The reconstruction module includes a reference picture predictor that uses only previously decoded pictures to determine one or more predicted reference pictures. The predicted reference picture(s) are used for motion compensated prediction. The reference picture predictor may include optical flow analysis that uses a current decoded picture and that may use one or more previously decoded pictures together with affine motion analysis and image warping to determine at least a portion of at least one of the reference pictures.

Abstract: A method, an apparatus, and a storage medium with executable code to execute a method including accepting camera views of at least some participants of a teleconference, each view from a corresponding video camera, with the camera views together including at least one view of each participant. The method includes accepting audio from a plurality of microphones, and processing the audio from the plurality of microphones to generate audio data and direction information indicative of the direction of sound received at the microphones. The method further includes generating one or more candidate people views, with each people view being of an area enclosing a head and shoulders view of at least one participant. The method also includes making a selection, according to the direction information, of which at least one of the candidate people views are to be transmitted to one or more remote endpoints.

Abstract: In one embodiment, a method includes obtaining a first image of a party that is stored in a first structure in response to an instruction to enroll the user in a system, and using information associated with the first image to identify a second image stored in a second structure. The second image has a relatively high likelihood of depicting the party. Finally, the method includes enrolling the party in the system, wherein enrolling the party in the system includes associating the second image with the party.

Abstract: Techniques are provided for managing long-term reference frames (LTRFs) for two or more video sources. A first video source is selected from a plurality of video sources. The first video source is encoded to produce an encoded video stream, where a reference frame message identifies a recent video frame as long-term reference frame (LTRF) associated with the first video stream. The process is repeated for other video streams. The LTRF associated with the first video stream is used as a reference for temporal predictive coding upon receiving a signal that the first video source has been re-selected.

Abstract: A system and method for creating a virtual round table videoconference is described. An embodiment of the system comprises a plurality of displays arranged in an arc configuration with a table to create a virtual round table. Cameras are arranged around the plurality of displays such that when a participant looks at a display with an image of a remote participant, the camera associated with the display captures an image of the participant's gaze, making eye contact with the camera. The image is displayed at the remote participant's endpoint creating the effect of eye contact between the participants. In another embodiment, audio speakers are arranged to provide directional sound such that the video source for a display and the audio source for the associated speaker are from the same endpoint.

Abstract: A network-adaptive error recovery method for real-time video transmission based on sending repair frames preemptively with a frequency that is based on observed run-length of good frames and round trip time.

Abstract: Techniques are provided to analyze video frames of a video signal in order to distinguish regions containing a face (and body torso) from regions that contain a relatively static background. The region containing the face is referred to as a foreground region. A current video frame is divided into a plurality of elements and the foreground regions and background regions are detected. The background regions of a subsequent video frame are detected/registered using the foreground regions of the current video frame. The foreground regions of the subsequent video frame are determined using the background regions of the current video frame as a temporal reference.