Grant: Idea to Innovation
Centre de recherche informatique de Montréal
$120,000.00
TV and radio advertisement detection (Phase 1 application)
EF 2009-10
Résumé
The objective is to leverage the TV and Radio advertisement detection technology developed at CRIM to develop prototypes for advertisement detection products and services. These products and services have a very wide applicability. For example, they can be used by TV stations for monitoring ads and for indexing broadcasts, by CRTC for monitoring compliance of ads, by advertisement companies and other businesses for monitoring the airing of their ads on TV and radio broadcasts. We have developed advertisement detection system that accurately monitors specific ads using audio only. It can also detect arbitrary ads with over 96% recall and over 92% precision. The same algorithms can be used to detect copying of copyrighted audio (songs etc.) in peer-to-peer transfer over the internet.
Currently, this technology works off-line on recorded audio of the broadcasts. The algorithms are completely automated, and can be applied to both TV and radio broadcasts. We need to test the algorithms on much larger data from all over US and Canada to verify the performance. We will also optimize the computing speed of the algorithms for searching both known ads and new ads. The algorithms that find new ads are novel, but we need to show that they perform well for all kinds of programs with reasonable computing requirements. Evaluating the robustness of the algorithms on data from all over North America is necessary in order to attract funding for technology transfer from potential companies in this business.
Programme
Idea to Innovation
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Not-for-profit organization or charity
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
380721-2009
Name nom
Kenny, Patrick
Department département
Head Office
Organization id
71
Institution établissement
Centre de recherche informatique de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2009
Competition year année de concours
2009
Award amount
120000
Program id
I2IPJ
Program nane en
Idea to Innovation
Program name fr
De l'idée à l'innovation
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2514
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Digital signal processing
Research subject fr
Traitement des signaux numériques
Partie
1
Nb partie
1
Application title
TV and radio advertisement detection (Phase 1 application)
Keyword
NA
Application summary
The objective is to leverage the TV and Radio advertisement detection technology developed at CRIM to develop prototypes for advertisement detection products and services. These products and services have a very wide applicability. For example, they can be used by TV stations for monitoring ads and for indexing broadcasts, by CRTC for monitoring compliance of ads, by advertisement companies and other businesses for monitoring the airing of their ads on TV and radio broadcasts. We have developed advertisement detection system that accurately monitors specific ads using audio only. It can also detect arbitrary ads with over 96% recall and over 92% precision. The same algorithms can be used to detect copying of copyrighted audio (songs etc.) in peer-to-peer transfer over the internet.
Currently, this technology works off-line on recorded audio of the broadcasts. The algorithms are completely automated, and can be applied to both TV and radio broadcasts. We need to test the algorithms on much larger data from all over US and Canada to verify the performance. We will also optimize the computing speed of the algorithms for searching both known ads and new ads. The algorithms that find new ads are novel, but we need to show that they perform well for all kinds of programs with reasonable computing requirements. Evaluating the robustness of the algorithms on data from all over North America is necessary in order to attract funding for technology transfer from potential companies in this business.