A video stream consists of a number of shots
each of which has different boundary types such as
cut, fade, and dissolve. Many previous approaches
can find the cut boundary without difficulty. Ho wever,
most of them often produce false alarms for
the videos with large motions of camera and objects.
In this paper, we demonstrate that the shape
of the histogram difference between two successive
color images, called the structural information,
provides an important cue to distinguish fade and
dissolve effects from cut effect. Our shot detection
method uses an optimal Bayesian classifier
weighted by the structural information to model
the gradual transitions such as fades and dissolves.
The proposed method has been tested for a few
golf video segments and shown good performances
in detecting fade and dissolve effects as well as cut.
each of which has different boundary types such as
cut, fade, and dissolve. Many previous approaches
can find the cut boundary without difficulty. Ho wever,
most of them often produce false alarms for
the videos with large motions of camera and objects.
In this paper, we demonstrate that the shape
of the histogram difference between two successive
color images, called the structural information,
provides an important cue to distinguish fade and
dissolve effects from cut effect. Our shot detection
method uses an optimal Bayesian classifier
weighted by the structural information to model
the gradual transitions such as fades and dissolves.
The proposed method has been tested for a few
golf video segments and shown good performances
in detecting fade and dissolve effects as well as cut.