A repeated video clip identification system

Identifying short repeated video clips, such as news program logo, station logo, TV commercials, etc., from broadcasting video databases or streams is important for video content indexing, personalization as well as monitoring. In this demo system we present the following two functions: 1) automatically identifying variable length unknown repeated clips and known reference clips from video collections or steams; 2) visualize temporal distribution of repeated short video clips and analyze video structure based them. Experiment has been conducted on 12 hour CNN and ABC news videos, and excellent results have been achieved in both short repeated video clip identification and news video structure analysis.

[1]  Jonathan Foote,et al.  Scene boundary detection via video self-similarity analysis , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[2]  John M. Gauch,et al.  Real time repeated video sequence identification , 2004, Comput. Vis. Image Underst..

[3]  Ton Kalker,et al.  Visual hashing of digital video: applications and techniques , 2001, Optics + Photonics.

[4]  Qi Tian,et al.  Fast and robust short video clip search using an index structure , 2004, MIR '04.

[5]  Qi Tian,et al.  A color fingerprint of video shot for content identification , 2004, MULTIMEDIA '04.