Saliency-weighted video quality assessment

Number: 9922411
Published: 2018-03-20
Filed: 2015-11-30
Assignee: Disney Enterprises, Inc.
Inventors: Aydin; Tunc Ozan et al.
CPC: H04N19/00; H04N19/85; G06T7/0002; H04N17/004
Verdict: Set aside video quality assessment metric, codec plumbing
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(1) 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(2) 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(3) 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 values of the

Claims

1. A method, comprising: receiving an assessed image at a non-transitory computer readable medium; one or more processors: determining a per-pixel image quality vector of the assessed image; determining per-pixel saliency values of the assessed image or a reference image corresponding to the assessed image; and computing a saliency-weighted image quality metric of the assessed image by weighting the per-pixel image quality vector using the per-pixel saliency values; and using at least the computed saliency-weighted image quality metric to perform image or video processing, wherein using at least the computed saliency-weighted image quality metric to perform image or video processing comprises monitoring and adjusting a quality of the assessed image. 9. A system, comprising: one or more processors; and one or more non-transitory computer-readable mediums operatively coupled to at least one of the one or more processors and having instructions stored thereon that, when executed by at least one of the one or more processors, cause the system to: receive an assessed image; determine a per-pixel image quality vector of the assessed image; determine per-pixel saliency values of the assessed image or a reference image; and compute a saliency-weighted image quality metric of the assessed image by weighting the per-pixel image quality vector using the per-pixel saliency values; and use at least the computed saliency-weighted image quality metric to perform image or video processing, wherein using at least the computed saliency-weighted image quality metric to perform image or video processing comprises monitoring and adjusting a quality of the assessed image.