SALIENCY-WEIGHTED VIDEO QUALITY ASSESSMENT

Number: 20180158184
Published: 2018-06-07
Filed: 2018-02-01
Assignee: Disney Enterprises, Inc.
Inventors: Aydin; Tunc Ozan et al.
CPC: G06T7/0002; H04N19/85; H04N19/00; H04N17/004
Verdict: Set aside video quality assessment metric (PGPUB dup)
Source: Google Patents · FreePatentsOnline

Abstract

Systems and methods are disclosed for weighting the image quality prediction of any visual-attention-agnostic quality metric with a saliency map. By accounting for the salient regions of an image or video frame, the disclosed systems and methods may dramatically improve the precision of the visual-attention-agnostic quality metric during image or video quality assessment. In one implementation, a method of saliency-weighted video quality assessment includes: determining a per-pixel image quality vector of an encoded video frame; determining per-pixel saliency values of the encoded video frame or a reference video frame corresponding to the encoded video frame; and computing a saliency-weighted image quality metric of the encoded video frame by weighting the per-pixel image quality vector using the per-pixel saliency values.

Background

TECHNICAL FIELD

The present disclosure relates generally to video quality assessment techniques, and more particularly, some embodiments relate to systems and methods for providing saliency-weighted video quality assessment.DESCRIPTION OF THE RELATED ART

The goal of automated video quality assessment is obtaining a quantitative measure that is highly correlated with the perceived quality of the input visual content. Currently, video quality assessment and control is mostly done interactively by quality experts, who have to inspect the produced (e.g., transcoded) versions of the evaluated content and make sure that they conform to corresponding quality requirements. Automated video quality assessment tools are highly desired in content distribution workflows due to their potential to significantly reduce the amount of manual work required during the quality control process. However, automated methods can only be trusted if they consistently provide quality predictions that are correlated with the subjectively perceived content quality.BRIEF SUMMARY OF THE DISCLOSURE

According to various embodiments of the technology disclosed herein, systems and methods are disclosed for providing saliency-weighted video quality assessment. In one embodiment, an assessed image is received at a non-transitory computer readable medium. In this embodiment, one or more processors: determine a per-pixel image quality vector of the assessed image; determine per-pixel saliency value

Claims

1. A method comprising: receiving an encoded video; determining a saliency-weighted image quality metric for each video frame of the encoded video; determining video frames of the encoded video with a saliency-weighted image quality metric that is below a threshold; and assembling a playlist including the video frames of the encoded video with a saliency-weighted image quality metric that is below the threshold. 11. A system, comprising: a non-transitory computer-readable medium operatively coupled to a processor and having instructions stored thereon that, when executed by the processor, cause the system to: receive an encoded video; determine a saliency-weighted image quality metric for each video frame of the encoded video; determine video frames of the encoded video with a saliency-weighted image quality metric that is below a threshold; and assemble a playlist including the video frames of the encoded video with a saliency-weighted image quality metric that is below the threshold.