Sadlier, David A., Marlow, Seán, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 and Murphy, Noel (2002) Automatic TV advertisement detection from MPEG bitstream. Pattern Recognition, 35 (12). pp. 2719-2726. ISSN 0031-3203
Abstract
The Centre for Digital Video Processing at Dublin City University conducts concentrated research and development in the area of digital video management. The current stage of development is demonstrated on our Web-based digital video system called Físchlár (Proceedings of the Content based Multimedia Information Access, RIAO 2000, Vol. 2, Paris, France, 12–14 April 2000, p. 1390), which provides for efficient recording, analysing, browsing and viewing of digitally captured television programmes.
Advertisement breaks during or between television programmes are typically recognised by a series of ‘black’ video frames simultaneously accompanying a depression in audio volume which separate each advertisement from one another by recurrently occurring before and after each individual advertisement. It is the regular prevalence of these flags that enables automatic differentiation between what is programme and what is a commercial break. This paper reports on the progress made in the development of this idea into an advertisement detector system that automatically detects the commercial breaks from the bitstream of digitally captured television broadcasts.
Metadata
Item Type: | Article (Published) |
---|---|
Refereed: | Yes |
Uncontrolled Keywords: | MPEG-1; Black/Silent Frames; DC coefficients; Subband scalefactors |
Subjects: | Computer Science > Digital video Computer Science > Information retrieval |
DCU Faculties and Centres: | Research Initiatives and Centres > Centre for Digital Video Processing (CDVP) |
Publisher: | Elsevier |
Official URL: | http://dx.doi.org/10.1016/S0031-3203(01)00251-5 |
Use License: | This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License |
ID Code: | 385 |
Deposited On: | 01 Apr 2008 by DORAS Administrator . Last Modified 09 Nov 2018 09:58 |
Documents
Full text available as:
Preview |
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
130kB |
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record