Break-Segment Detection and Recognition in Broadcasting Video/Audio Based on C/S Architecture
Abstract
A novel scheme for break-segment detection and recognition in broadcasting video/audio based on client/server architecture is proposed, where breaksegments are referred to as segments inserted between or within main programs such as commercials, upcoming program announcements, head leader and closing credits of programs, etc. At the server-end, a break-segment database is initially generated and thereafter updated by results of repetition detection. The clients get the latest break-segment database from the server through network and recognize the break-segments in the database. For both repetition detection and recognition, only the audio signal is processed using the feature EEUPC and corresponding similarity measurement and matching algorithm, achieving much higher efficiency than current methods. Experimental results demonstrate high accuracy and efficiency of the proposed framework.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Li, Y., Kuo, C.-C.J.: Detecting Commercial Breaks in Real TV Program based on Audiovisual Information. In: SPIE Proc. on IMMS, vol. 421 (2000)Google Scholar
- 2.Duan, L., Wang, J., et al.: Segmentation, Categorization, and Identification of Commercials from TV Streams Using Multimodal Analysis. In: Proc. ACM MM 2006, Santa Barbara (2006)Google Scholar
- 3.Hua, X., et al.: Robust Learning-Based TV Commercial Detection. In: Proc. ICME (2005)Google Scholar
- 4.Duygulu, P., Chen, M., Hauptmann, A.: Comparison and Combination of Two Novel Commercial Detection Methods. In: Proc. ICME 2004, pp. 1267–1270 (2004)Google Scholar
- 5.Gauch, J.M., Shivadas, A.: Identification of New Commercials Using Repeated Video Sequence Detection. In: Proc. ICIP, pp. 1252–1255 (2005)Google Scholar
- 6.Covell, M., Baluja, S., et al.: Advertisement Detection and Replacement using Acoustic and Visual Repetition. In: Proc. International Workshop on Multimedia Signal Processing (2006)Google Scholar
- 7.Zhao, D., Wang, X., et al.: Fast Commercial Detection based on Audio Retrieval. In: Proc. ICME 2008, Hannover (2008)Google Scholar