• Contact
• SMPTE.org

• About
• Attend
• Exhibit
• Schedule
• Sessions
• Sponsors
• Media
• Partners

Exhibit Hall Open

Grand Ballroom Salons 3-6

Tuesday 1:00 pm- 7:00 pm
Wednesday 10:00 am- 5:00 pm
Thursday 10:00 am- 2:00 pm

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

Peter Schallauer (JOANNEUM RESEARCH Forschungs Ges.m.b.H., Austria); Hannes Fassold (JOANNEUM RESEARCH Forschungs Ges.m.b.H., Austria); Martin Winter (JOANNEUM RESEARCH Forschungsgesellschaft mbH, Austria); Werner Bailer (Joanneum Research, Austria); Georg Thallinger (JOANNEUM RESEARCH, Austria); Werner Haas (Joanneum Research, Austria)

Automatic quality control for audiovisual media is an important tool in several steps of the media production, delivery and archiving process. Broadcasters are checking quality at ingest, after editing and before play-out to various delivery services. Archives are checking for content integrity at archive ingest and delivery. Content providers are checking their content for correct encoding and conformance to the required format standard before dispatching to customers. These use cases have in common that mainly technical properties of the material are checked, e.g. stream compliance, playtime, aspect ratio, resolution or MXF compliance. Today 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 mainly checked by human exploration of the audiovisual content. In this work we focus on challenges and recent results in automatic visual quality analysis of video content. We first give an overview on which visual impairments are relevant in which media production, archiving and delivery process. A set of requirements for impairment detection algorithms, tools and systems is presented for software and file based environments. We show how impairment detection algorithms need to be designed in order to meet these requirements. We show our recent algorithmic research results for different impairment detectors developed, e.g. freeze frame, flicker and video breakup. 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 developed which allows a user to quickly grasp the frequency and strengths of visual impairments in the content.

Thursday, Oct 29
2:00 PM - 6:00 PM

Sponsors