公开(公告)号：US20200380290A1

公开(公告)日：2020-12-03

申请号：US16428577

申请日：2019-05-31

Applicant: Apple Inc.

Inventor： Pranav SODHANI ,  Steven E. Saunders ,  Bjorn Hori ,  Rahul Gopalan ,  Krasimir Kolarov ,  Samira Tavakoli

IPC: G06K9/46 ,  H04N17/00 ,  H04N19/154 ,  G06K9/00 ,  G06N20/00

Abstract: Systems and Methods disclosed for measuring a similarity between the input and the output of computing systems and communications channels. Techniques disclosed provide for low complexity prediction method of a perceptual video quality (PVQ) score, which may be used to design and tune performance of the computing systems and communications channels.

公开(公告)号：US10185884B2

公开(公告)日：2019-01-22

申请号：US15258501

申请日：2016-09-07

Applicant: Apple, Inc.

Inventor： Krasimir D. Kolarov ,  Bjorn S. Hori ,  Rahul Gopalan ,  Steven E. Saunders

IPC: G06T7/77 ,  G06K9/03 ,  G06T7/00 ,  G06K9/62 ,  G06K9/00

Abstract: A video quality assessment method may include frame-by-frame analysis of a test video sequence (often compressed) with its original (reference) counterpart, pre-conditioning elements of the test and reference frames, defining a region of interest in the pre-conditioned test frame and estimating relative errors within the region of interest between the test and reference frame, filtering the estimated errors of the region of interest temporally across adjacent frames within a perpetually relevant time window, aggregating the filtered errors within the time window, ranking the aggregated errors, selecting a subset of the ranked errors, aggregating across the selected subset of errors, and inputting said aggregated error to a quality assessment system to determine a quality classification along with an estimated quality assessment.

公开(公告)号：US20180068195A1

公开(公告)日：2018-03-08

申请号：US15258501

申请日：2016-09-07

Applicant: Apple, Inc.

Inventor： Krasimir D. Kolarov ,  Bjorn S. Hori ,  Rahul Gopalan ,  Steven E. Saunders

IPC: G06K9/03 ,  G06T7/00 ,  G06T7/40 ,  G06T7/20 ,  G06K9/62 ,  G06K9/00

CPC classification number: G06K9/036 ,  G06K9/00577 ,  G06K9/6201 ,  G06K9/628 ,  G06K2009/6213 ,  G06T7/0002 ,  G06T7/11 ,  G06T7/80 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/30168

Abstract: A video quality assessment method may include frame-by-frame analysis of a test video sequence (often compressed) with its original (reference) counterpart, pre-conditioning elements of the test and reference frames, defining a region of interest in the pre-conditioned test frame and estimating relative errors within the region of interest between the test and reference frame, filtering the estimated errors of the region of interest temporally across adjacent frames within a perpetually relevant time window, aggregating the filtered errors within the time window, ranking the aggregated errors, selecting a subset of the ranked errors, aggregating across the selected subset of errors, and inputting said aggregated error to a quality assessment system to determine a quality classification along with an estimated quality assessment.