Rule-based scene extraction from video

Instead of clustering video shots into scenes using low level image features, in this paper, we propose a rule-based model to extract simple dialog or action scenes. Through analyzing video editing rules and observing temporal appearance patterns of shots in dialog scenes of movies, we deduce a set of rules to recognize dialog or action scenes. Based on these rides, a finite state machine is designed to extract dialog or action scenes from videos automatically.

[1]  Thomas S. Huang,et al.  Exploring video structure beyond the shots , 1998, Proceedings. IEEE International Conference on Multimedia Computing and Systems (Cat. No.98TB100241).

[2]  Boon-Lock Yeo,et al.  Time-constrained clustering for segmentation of video into story units , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[3]  Wolfgang Effelsberg,et al.  Scene Determination Based on Video and Audio Features , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[4]  Alan Hanjalic,et al.  Automatically Segmenting Movies into Logical Story Units , 1999, VISUAL.

[5]  Derick Wood,et al.  Theory of computation , 1986 .

[6]  Steven D. Katz.  Film directing, shot by shot : visualizing from concept to screen , 1991 .

[7]  Masahito Hirakawa,et al.  Content-based retrieval of video data by the grammar of film , 1997, Proceedings. 1997 IEEE Symposium on Visual Languages (Cat. No.97TB100180).

[8]  Rainer Lienhart,et al.  Scene Determination Based on Video and Audio Features , 2004, Multimedia Tools and Applications.

[9]  James L. Hein.  Theory of computation: an introduction , 1996 .

[10]  D. Arijon,et al.  Grammar of Film Language , 1976 .