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 method is provided in one example embodiment and includes receiving a camera dynamic parameter; determining a reference transform parameter based on the camera dynamic parameter; applying the reference transform parameter to generate a video image; and encoding the reference transform parameter in a bitstream for transmission with the video image. In other more specific instances, the method may include decoding a particular video image; decoding a particular reference transform parameter; and applying a particular reference transform parameter to the particular video image. The entropy-decoded data can undergo inverse quantization and transformation such that reference transformed data is combined with the entropy-decoded data. Additionally, the entropy-decoded data can be subjected to filtering before decoded video images are rendered on a display.

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: Particular embodiments generally relate to video compression. In one embodiment, a store of reference frames is provided in memory. The reference frames may be classified based on a plurality of classifiers. The classifiers may correspond to features that are found in the reference frame. A frame to encode is then received. The frame is analyzed to determine features found in the frame. As macroblocks in the frame are encoded, a macroblock is analyzed to determine which feature may be included in the macroblock. The feature is used to determine a classifier, which is used to determine a subset of the reference frames. The subset is then searched to determine a reference frame for the macroblock.

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: A processing system can include an encoder to encode a real-time transmission of a presentation. A memory buffer can copy and store images of the presentation and convert the images into snapshot images. A transmitter can transmit the snapshot images to an external annotation device, and a receiver can receive annotation data of an annotation performed on the snapshot images at the external annotation device. The annotation can be encoded, in accordance with the annotation data, into the real-time transmission of the presentation to display the real-time transmission with the annotation.

Abstract: Video content is received at a computing device that camera views provided by video cameras that are aligned to capture images of participants within a defined space. Each camera view is at a first resolution and the video cameras are aligned such that a field of view (FOV) for each camera overlaps a portion of the FOV of at least one other adjacent camera. Positions of participants depicted within the video content are detected, where at least one participant is captured by overlapping FOVs of two adjacent camera views. A target view is generated from the first number of camera views, the target view having a second resolution that is lower than the first resolution, and the target view includes a view of the at least one participant captured within the overlapping FOVs of two adjacent camera views. The target view is displayed at a display device.

Abstract: Techniques are provided for receiving and decoding a sequence of video frames at a computing device, and analyzing a current video frame N to determine whether to skip or render the current video frame N for display by the computing device. The analyzing includes generating color histograms of the current video frame N and one or more previous video frames, determining a difference value representing a difference between the current video frame N and a previous video frame N?K, where K>0, the difference value being based upon the generated color histograms, in response to the difference value not exceeding a threshold value, rendering the current video frame N or a recently rendered video frame N?K using the current video frame, and in response to the difference value exceeding the threshold value, skipping the current video frame N from being rendered.

Abstract: A method that includes capturing depth information associated with a first field of view of a depth camera. The depth information is represented by a first plurality of depth pixels. The method also includes capturing color information associated with a second field of view of a video camera that substantially overlaps with the first field of view of the depth camera. The color information is represented by a second plurality of color pixels. The method further includes enhancing color information represented by at least one color pixel of the second plurality of color pixels to generate an enhanced image. The enhanced image adjusts an exposure characteristic of the color information captured by the video camera. The at least one color pixel is enhanced based on depth information represented by at least one corresponding depth pixel of the first plurality of depth pixels.

Abstract: A coding method, apparatus, and medium with software encoded thereon to implement a coding method. The coding method includes encoding the position of non-zero-valued coefficients in an ordered series of quantized transform coefficients of a block of image data, including encoding events using variable length coding using a plurality of variable length code mappings that each maps events to codewords, the position encoding including switching between the code mappings based on the context. The coding method further includes encoding amplitudes of the non-zero-valued coefficients using variable dimensional amplitude coding in the reverse order of the original ordering of the series.

Abstract: A method is provided in one example embodiment that includes generating a depth map that corresponds to a video image and filtering the depth map with the video image to create a filtered depth map. The video image can be filtered with the filtered depth map to create an image. In one example implementation, the video image is filtered using extended depth-guided filtering that is incorporated into a video encoding-decoding loop.

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: 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: A method is provided in one example embodiment that includes receiving a plurality of depth values corresponding to pixels of an image; and filtering the image as a function of a plurality of variations in the depth values between adjacent pixels of a window associated with the image. In more detailed embodiments, the method may include encoding the image into a bit stream for transmission over a network. The filtering can account for a bit rate associated with the encoding of the image.

Abstract: A coding method, apparatus, and medium with software encoded thereon to implement a coding method. The coding method includes encoding the position of non-zero-valued coefficients in an ordered series of quantized transform coefficients of a block of image data, including encoding events using variable length coding using a plurality of variable length code mappings that each maps events to codewords, the position encoding including switching between the code mappings based on the context. The coding method further includes encoding amplitudes of the non-zero-valued coefficients using variable dimensional amplitude coding in the reverse order of the original ordering of the series.

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: Techniques are provided for image-based real-time gesture recognition. Video data of a person is obtained. Pixels are classified in the video stream at a given time instance during a time period as a foreground or a background pixel. A data entry is generated comprising data indicating foreground history values for each of a plurality of time instances of the video stream and data indicating a time period value. When the classifying indicates that a first pixel is a foreground pixel, the data structure associated with the first pixel is evaluated to determine whether or not to update a foreground history value associated with the first pixel at the given time instance. A motion gradient vector is generated for the video stream based on the foreground history value associated with the first pixel and foreground history values associated with other pixels.

Abstract: A method is provided in one example and includes receiving an input video, and identifying values of pixels from noise associated with a current video image within the video input. The method also includes creating a skip-reference video image associated with the identified pixel values, and comparing a portion of the current video image to the skip-reference video image. The method also includes determining a macroblock associated with the current video image to be skipped before an encoding operation occurs.

Abstract: Particular embodiments include a method, an apparatus, and logic embodied in tangible computer-readable medium that when executed carries out a method of encoding an ordered sequence of quantized transform coefficients of a block of image data. One embodiment is a context adaptive variable length coding method that includes position coding the positions of zero-valued and non-zero valued coefficients by either a mixed method that encodes either the run length of zeroes preceding a non-zero coefficient or the run length of nonzero-valued coefficients preceding a zero-valued coefficients. Another includes position coding that uses a variable length code for two parameters respectively indicating the number of zero-valued coefficient positions and nonzero-valued coefficient positions still to be coded.