Summary: Scene-cut Detection in Image Sequences Using
Multiresolutional Information Features
Farid Ahmed' and Gregory J. Powerb
apennsylvanja State University, The Behrend College
School of Engineering & Engineering Technology, Erie, PA 16563
b Air Force Research Laboratory AFRL/SNAT Target Recognition Branch
Building 620, 2241 Avionics Circle, WPAFB, OH 45433-7321
This paper proposes to use a multiresolutional spatio-temporal metric for the segmentation of an image sequence.
In particular, scene-cut detection performance from an image sequence will be furnished. Wavelet decomposition is
used for the multiresolutional analysis. The segmentation results obtained here can be used in the video browsing
and indexing in multimedia applications.
Keywords: Spatio-temporal metric, multiresolutional feature, scene-cut, image sequence
Processing of large databases of image and video sequences is becoming increasingly more challenging with the
rapid growth of multimedia applications. Efficient storage and retrieval techniques necessitate the smart detection
of dynamic changes in an image sequence, which may be used to form an index database. A video sequence usually
consists of many scenes. Each scene is a combination of some frames that has continuous spatio-temporal property.
A scene change is usually associated with the dynamic changes in image content, motion, and audio information
among the frames. The change could be abrupt or gradual. Dissolve, fade in/out, and wiping are examples of