Automatic Detection and Recognition of TV Commercials

Abstract

TV commercials are interesting in many respects: advertisers and psychologists are interested in their influence on human purchasing habits, while parents might be interest in shielding their children from their influence. We propose two methods for detecting and extracting commercials in digital videos. The first method is based on statistics of measurable features and enables the detection of commercial blocks within TV broadcasts. The second method performs detection and recognition of known commercials with high accuracy. Finally, we show how both approaches can be combined into a self-learning system. Our experimental results underline the practicality of the methods.

Demo Video

Short Demo Video (MPEG-1: 28MB)

Publications

Rainer Lienhart, Christoph Kuhmünch and Wolfgang Effelsberg. Isolating and Identifying Commercials in TV Programs. In Handbook of Multimedia Computing, CRC Press, 1998. to appear.
Rainer Lienhart, Christoph Kuhmünch and Wolfgang Effelsberg. On the Detection and Recognition of Television Commercials, Proc. IEEE Conf. on Multimedia Computing and Systems, Ottawa, Canada, pp. 509 - 516, June 1997. [Abstract] [PS : 70KB]; also Technical Report TR-96-016, Dezember 1996.
Rainer Lienhart, Christoph Kuhmünch and Wolfgang Effelsberg. Aufspüren und Erkennen von Werbung in laufenden Fernsehsendungen. In: Mustererkennung 1997, 19. DAGM-Symposium, Braunschweig, 15.-17. September 1997, Erwin Paulus and Friedrich M. Wahl, Editors, pp. 435-445, September 1997. [Abstract] [PS : 104 KB]