ABSTRACT
Automatic quality assessment for audiovisual media is an important task for several steps of the media production, delivery and archiving processes. In this paper we focus on the semi-automatic quality inspection of videos and propose a novel algorithm for the detection of severe visual distortions, commonly termed as 'Video Breakup'. In order to enable the efficient human interaction with quality analysis results we present the extended 'Quality Summary Viewer' application, which enables the user to efficiently verify the detected events. Moreover it allows the user to quickly grasp the frequency and strengths of these visual impairments in the content and allows for its overall quality appraisal. Evaluation on a huge, challenging dataset shows, that our algorithm is able to detect up to 97.3% of the events annotated by domain experts. Depending on the application specific needs, we can reach a false detection rate of only 0.1-1.5 per minute.
- Audiovisual Defect and Quality Description. http://mpeg7.joanneum.at.Google Scholar
- ISO/IEC. Multimedia content description interface. ISO/IEC 15938:2001.Google Scholar
- P. Schallauer, W. Bailer, R. Mörzinger, H. Fürntratt, and G. Thallinger. Automatic quality analysis for film and video restoration. In IEEE ICIP, San Antonio, USA, October 2007.Google ScholarCross Ref
- D. Van der Weken, M. Nachtegael, and E. Kerre. Using similarity measures for histogram comparison. Lecture Notes in Computer Science, 2715:1--9, 2003. Google ScholarDigital Library
- Z. Wang and Q. Li. Statistics of natural image sequences: temporal motion smoothness by local phase correlations. Human Vision and Electronic Imaging XIV, 7240:72400W, 2009.Google ScholarCross Ref
- C. Zach, Thomas Pock, and H. Bischof. A duality based approach for realtime tv-l1 optical flow. In Proceedings of the 29th DAGM Symposium on Pattern Recognition, pages 214--223, 2007. Google ScholarDigital Library
Index Terms
- Efficient video breakup detection and verification
Recommendations
Digital Preservation, Archival Science and Methodological Foundations for Digital Libraries
Digital libraries, whether commercial, public, or personal, lie at the heart of the information society. Yet, research into their long-term viability and the meaningful accessibility of their contents remains in its infancy. In general, as we have ...
Automatic freeze frame detection for video preservation
ICIP'09: Proceedings of the 16th IEEE international conference on Image processingA significant amount of work in film and video preservation is dedicated to quality assessment of the content to be archived or reused out of the archive. This paper proposes automatic content analysis algorithms which reduce manual inspection time in ...
Representing software project vision by means of video: A quality model for vision videos
Highlights- Based on literature, we elaborate ten video and five vision quality characteristics.
AbstractEstablishing a shared software project vision is a key challenge in Requirements Engineering (RE). Several approaches use videos to represent visions. However, these approaches omit how to produce a good video. This missing guidance is ...
Comments