Gradual Transition Detection in Video using Average Frame Similarity

Timo Volkmer

School of CS&IT, RMIT University

Date and time: 11.30am-12.30pm, Friday 25th June, 2004

Venue: 10.11.04

Chair: James Harland

Abstract:

Segmenting digital video into its constituent basic semantic entities, or shots, is an important step for effective management and retrieval of video data. Recent automated techniques for detecting transitions between shots are highly effective on abrupt transitions. However, automated detection of gradual transitions, and the precise determination of the corresponding start and end frames, remains problematic. This talk is divided into two parts: after a brief introduction into the field of content-based video retrieval, we present our gradual transition detection approach based on average frame similarity and adaptive thresholds. We report good detection results on the TREC video track collections -- particularly for dissolves and fades -- and very high accuracy in identifying transition boundaries. The approach described in the second part of this talk will be presented at the refereed Workshop for Multimedia Data and Document Engineering (MDDE) 2004, to be held on the 2nd July in Washington D.C.

About the speaker:

Timo Volkmer is a PhD student in the School of Computer Science and Information Technology at RMIT University. He is supervised by Saied Tahaghoghi & Hugh Williams.

Seminars are free and open to the general public. No booking is necessary.

If you are interested in giving a presentation in this seminar series, or to make suggestions for speakers, please contact James Harland, the seminar co-ordinator.