Thomson Licensing

Ditto Technologies, Inc.

Dialogic (us) Inc.

Dialogic Corporation

Thomson Licensing Dtv

Sitaram Bhagavathy

Joan Llach

Dong-Qing Zhang

Jeffrey Adam Bloom

Dekun Zou

Sergey Surkov

Dmitry Kornilov

Ran Ding

Beibei Wang

Tao Liu

Niranjan Narvekar

Jesus Barcons-Palau

Yu Huang

Shan He

Glenn Lawrence Cash

Zhai Jie Fu

Wen Chen

Malavika Bhaskaranand

Jie Fu Zhai

Methods and apparatuses for data pruning for video compression using example-based super resolution are provided. A method and apparatus for encoding is provided in which patches of video are extracted from input video, grouped together using a clustering method, and representative patches are packed into patch frames. The original video is downsized and sent either along with, or in addition to, the patch frames. At a decoder, the method and apparatus provided extract patches from the patch frames and create a patch library. The regular video frames are upsized and the low resolution patches are replaced by patches from the patch library by searching the library using the patches in the decoded regular frames as keywords. If there are no appropriate patches, no replacement is made. A post processing procedure is used to enhance the spatiotemporal smoothness of the recovered video.

Data pruning for video compression using example-based super-resolution

Methods and apparatus are provided for sampling-based super resolution video encoding and decoding. The encoding method receives high resolution pictures and generates low resolution pictures and metadata there from, the metadata for guiding post-decoding post-processing of the low resolution pictures and the metadata; and then encodes the low resolution pictures and the metadata using at least one encoder. The corresponding decoding method receives a bitstream and decodes low resolution pictures and metadata there from using a decoder; and then reconstructs high resolution pictures respectively corresponding to the low resolution pictures using the low resolution pictures and the metadata.

Methods and apparatus for sampling-based super resolution video encoding and decoding

Methods and apparatus are provided for reducing vector quantization error through patch shifting. A method generates, from an input video sequence, one of more high resolution replacement patches, the one or more high resolution replacement patches for replacing one or more low resolution patches during a reconstruction of the input video sequence. This generating step generates the one or more high resolution replacement patches using data corresponding to a patch spatial shifting process, the patch spatial shifting process for reducing jittery artifacts caused by a motion-induced vector quantization error in the one or more high resolution replacement patches, the data for at least deriving a patch size of the one or more high resolution replacement patches such that the one or more high resolution replacement patches are generated to have the patch size greater than a patch size of the one or more low resolution patches in order to be suitable for use in the patch spatial shifting process.

Methods and apparatus for reducing vector quantization error through patch shifting

Method and apparatus for recovering a pruned version of a picture in a video sequence are disclosed. The apparatus includes a divider for dividing the pruned version of the picture into a plurality of non-overlapping blocks. The apparatus also includes a metadata decoder for decoding metadata for use in recovering the pruned version of the picture. The apparatus further includes a patch library creator for creating a patch library from a reconstructed version of the picture. The patch library includes a plurality of high resolution replacement patches for replacing the one or more pruned blocks during a recovery of the pruned version of the picture. The apparatus additionally includes a search and replacement device for performing a searching process using the metadata to find a corresponding patch for a respective one of the one or more pruned blocks from among the plurality of non-overlapping blocks and replace the respective one of the one or more pruned blocks with the corresponding patch. The signature is respectively created for each of the one or more pruned blocks, and the pruned version of the picture is recovered by comparing respective distance metrics from signatures for each of the plurality of high resolution patches to signatures for each of the one or more pruned blocks, sorting the respective distance metrics to obtain a rank list for each of the one or more pruned blocks, wherein a rank number in the rank list for a particular one of the one or more pruned blocks is used to retrieve a corresponding one of the plurality of high resolution patches in the patch library to be used to replace the particular one of the one or more pruned blocks. A patch dependency graph having a plurality of nodes and a plurality of edges is used to recover the pruned version of the picture. Each of the plurality of nodes represents a respective one of the plurality of overlapping blocks, and each of the plurality of edges represents a respective dependency of at least the respective one of the plurality of overlapping blocks.

Recovering a pruned version of a picture in a video sequence for example-based data pruning using intra-frame patch similarity

A system for fitting glasses frames to a user is disclosed. The system includes an interface for receiving images of a user's head at different angles. A processor compares user head measurements determined from the images with a database of glasses frame information that includes glasses frame measurements. One or more glasses frames are selected based on the comparison and the selected glasses frames are output.

Fitting glasses frames to a user

A method of object-aware video coding is provided that comprises the steps of: receiving a video sequence having a plurality of frames; selecting at least two frames; determing total area of at least one object of interest in each of the at least two frames; comparing the total area to a threshold area; classifying each of the at least two frames as being a low object weighted frame or a high object weighted frame, low object weighted frames being frames having the total area exceeding the threshold area and high object weighted frames being frame having the total area not exceeding the threshold area; and encoding each low object weighted frame according to one encoding mode and encoding each high object weighted frame according to a different encoding mode.

Object-aware video encoding strategies

A method is disclosed for analyzing video to detect far-view scenes in sports video to determine when certain image processing algorithms should be applied. The method comprises analyzing and classifying the fields of view of images from a video signal, creating and classifying the fields of view of sets of sequential images, and selectively applying image processing algorithms to sets of sequential images representing a particular type of field of view.

Method for detecting and adapting video processing for far-view scenes in sports video

A method and associated apparatus for using a trajectory-based technique to detect a moving object in a video sequence at incorporates human interaction through a user interface. The method comprises steps of identifying and evaluating sets of connected components in a video frame, filtering the list of connected components by comparing features of the connected components to predetermined criteria, identifying candidate trajectories across multiple frames, evaluating the candidate trajectories to determine a selected trajectory, eliminating incorrect trajectories through use of the interface and processing images in said video sequence responsive to the evaluating and eliminating steps.

Human interaction trajectory-based system

Systems and methods of perceptual quality monitoring of video information, communications, and entertainment that can estimate the perceptual quality of video with high accuracy, and can be used to produce quality scores that better correlate with subjective quality scores of an end user. The systems and methods of perceptual quality monitoring of video can generate, from an encoded input video bitstream, estimates of one or more quality parameters relating to the video, such as the coding bit rate parameter, the video frame rate parameter, and the packet loss rate parameter, and provide these video quality parameter estimates to a predetermined video quality estimation model. Because the estimates of the video quality parameters are generated from the encoded input video bitstream as it is being received, the systems and methods are suitable for use as QoE monitoring tools.

Video quality monitoring

Systems and methods of identifying media content, such as video content, that employ fingerprint matching at the level of video frames. The presently disclosed systems and methods of identifying media content can extract one or more fingerprints from a plurality of video frames included in query video content, and, for each of the plurality of video frames from the query video content, perform frame-level fingerprint matching of the extracted fingerprints against fingerprints extracted from video frames included in a plurality of reference video content. Using the results of such frame-level fingerprint matching, the presently disclosed systems and methods of identifying media content can identify the query content in relation to an overall sequence of video frames from at least one of the plurality of reference content, and/or in relation to respective video frames included in a sequence of video frames from the reference content.

Content identification using fingerprint matching

Methods and apparatus for video object segmentation are provided, suitable for use in a super-resolution system. The method comprises alignment of frames of a video sequence, pixel alignment to generate initial foreground masks using a similarity metric, consensus filtering to generate an intermediate foreground mask, and refinement of the mask using spatio-temporal information from the video sequence. In various embodiments, the similarity metric is computed using a sum of squared differences approach, a correlation, or a modified normalized correlation metric. Soft thresholding of the similarity metric is also used in one embodiment of the present principles. Weighting factors are also applied to certain critical frames in the consensus filtering stage in one embodiment using the present principles.

Method and apparatus for video object segmentation

A method for propagating user-provided foreground-background constraint information for a first video frame to subsequent frames allows extraction of moving foreground objects with minimal user interaction. Video matting is performed wherein constraints derived from user input with respect to a first frame are propagated to subsequent frames using the estimated alpha matte of each frame. The matte of a frame is processed in order to arrive at a rough foreground-background segmentation which is then used for estimating the matte of the next frame. At each frame, the propagated constraints are used by an image matting method for estimating the corresponding matte which is in turn used for propagating the constraints to the next frame, and so on.

Video matting based on foreground-background constraint propagation

One or more implementations access a digital image and determine whether at least one portion of the digital image includes one or more bands having a difference in color. The determination is based on at least two candidate scales. One or more implementations access a digital image and assess at least a portion of the digital image for the existence of one or more bands having a difference in color. The assessing includes determining a fraction of pixels in the portion having a color value offset by an offset value from a color value of a particular pixel in the portion.

Identifying banding in digital images

Systems and methods of objective video quality measurement that employ a reduced-reference approach to video quality measurement. Such systems and methods of objective video quality measurement can extract information pertaining to one or more features of a target video whose perceptual quality is to be measured, extract information pertaining to one or more features of a reference video, and employ one or more prediction functions involving the target features and the reference features to provide a measurement of the perceptual quality of the target video.

Growing community of inventors

Plainsboro, NJ, United States of America

Sitaram Bhagavathy