Automatic Content Based Video Quality Analysis for Media Production and Delivery Processes

Automatic quality control for audiovisual media is an important tool in several steps of the media production, delivery and archiving processes. Today, mainly technical properties of the material are checked, e.g. stream compliance, playtime, aspect ratio, and resolution or MXF compliance. Only some content properties can be checked automatically, e.g. blocking or luma/chroma violation. Other relevant content properties and impairments like noise level, sharpness, large dropouts, flickering or instability are checked by manually exploring the audiovisual content. In this work we focus on challenges and recent results in automatic content based visual quality analysis of video. We first give an overview on which visual impairments are relevant in which stages of the media production, archiving and delivery process. A set of requirements for impairment detection algorithms, tools and systems is presented. We show how impairment detection algorithms need to be designed in order to meet these requirements. Furthermore we show our recent algorithmic research results for two content based impairment detectors (freeze frame and video breakup detection). In order to facilitate interoperability and exchange of impairment metadata between different tools and systems, a standardized way of description is needed. We give an overview on our framework proposed for the description of visual impairments based on MPEG-7. In order to enable efficient human interaction with quality analysis results we present the “Quality Summary Viewer” application which allows a user to quickly grasp the frequency and strengths of visual impairments in the content.

Published

2009-10

Content type

Original Research

DOI

10.5594/M001346

ISBN

978-1-61482-943-0