Arris Enterprises LLC

Gautam Babbar

Pierre A Brice

Olga Malysheva

Daniel Hillegass

Wayne D Woodruff

Dan Hillegass

The automatic video comparison system for measuring the quality of decoded data described herein provides a method for measuring the quality of decoded data at the level of sub-units of a unit of data, for instance at the level of sub-blocks of a video frame. The system can therefore locate defects that may not otherwise be detected by an automated system that measures quality at the level of the entire frame. Processing encoded media is computationally intensive, thus the automatic video comparison system uses a distributed computing system in order to distribute the computations across many compute resources that are capable of operating in parallel.

Automatic video comparison of the output of a video decoder

A method is presented for detecting visual artifacts such as macroblocking artifacts appearing in a rendering of a video stream. A decoded video stream that includes a plurality of frames is received. Edges appearing in the plurality of frames are detected and data characterizing the edges is directed to a neural network. The neural network determines a likelihood that a macroblocking artifact occurs in the video stream using the neural network. The neural network is trained using training data that includes (i) one or more video sequences having known macroblocking artifacts whose size and duration are known and (ii) user ratings indicating a likelihood that users visually perceived macroblocking in each of the one or more video sequences when each of the one or more video sequences are rendered.

Visual artifact detector

A computer implemented method for hashing an image is provided that includes: receiving a reference image frame; deriving an array of reference hash values to represent the reference image frame, wherein the array of reference hash values includes a first reference hash value, a second reference hash value, and a third reference hash value; receiving an test image frame; deriving an array of hash values to represent the test image frame, wherein the array of hash values includes a first test hash value, a second test hash value, and a third test hash value; subtracting the array of test hash values representing the test image frame from the array of reference hash values representing the reference image frame to produce a delta array, wherein the delta array is indicative of an area where the test image frame differs from the reference image frame.

Creating hash values indicative of differences in images

A test system is provided for analyzing a video frame received from a device under test such as a video rendering device includes a video capture device, a matrix code reader and a video quality analyzer. The video capture device receives a video stream from a video rendering device that includes a plurality of video frames. At least one of the video frames includes a matrix code overlaid thereon. The matrix code encodes one or more test parameters specifying one or more quality tests that are to be performed on the video frame on which the matrix code is overlaid. The matrix code reader scans and decodes the matrix code. The video quality analyzer analyzes the quality of the video frame based on the one or more quality tests embodied in the matrix code and decoded by the matrix code decoding device.

Growing community of inventors

Philadelphia, PA, United States of America

Gautam Babbar