REAL TIME MONITORING OF RADIO AND TV BROADCASTS

This paper describes work being done in two European projects. While content based indexing and retrieval methods have initially mostly been applied to the audio and video archive area, both projects target the media monitoring market. This is motivated by the size, demand and structure of this market. On one hand, the yearly worldwide revenues are remarkably high, and on the other hand, also methods that are maybe not yet perfect for the absolute requirements of very large archives may be well suited to enhance or replace existing manual solutions in media monitoring. The project RAA provides an example for the recognition and monitoring of audio clips, based on digital fingerprinting technologies. In the project DETECT real time recognition of advertisements and company logos for producing comparative brand statistics is being developed. Approach and results, specific technical problems for this application area as well as applicability and market relevance of the developed solutions are discussed.

[1]  김동규,et al.  [서평]「Algorithms on Strings, Trees, and Sequences」 , 2000 .

[2]  D. Lipman,et al.  Improved tools for biological sequence comparison. , 1988, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Ton Kalker,et al.  A Highly Robust Audio Fingerprinting System , 2002, ISMIR.

[4]  Douglas Keislar,et al.  Content-Based Classification, Search, and Retrieval of Audio , 1996, IEEE Multim..

[5]  Helmut Neuschmied,et al.  Robust Sound Modelling for Song Identification in Broadcast Audio , 2002 .

[6]  Noel Murphy,et al.  Automatic TV advertisement detection from MPEG bitstream , 2002, Pattern Recognit..

[7]  Daniela Hall,et al.  Brand identification using Gaussian derivative histograms , 2003, Machine Vision and Applications.

[8]  Helmut Neuschmied,et al.  Identification of Audio Titles on Internet , 2001 .

[9]  Jürgen Herre,et al.  AudioID: Towards Content-Based Identification of Audio Material , 2001 .

[10]  Wolfgang Effelsberg,et al.  On the detection and recognition of television commercials , 1997, Proceedings of IEEE International Conference on Multimedia Computing and Systems.