BMVC 2004, Kingston, 7th-9th Sept, 2004

Wavelet-based holistic sequence descriptor for generating video summaries
A. Graves and S. Gong (Queen Mary, University of London)

We propose a video representation, the Video Scene Trajectory, computed
from localised temporal-change in order to capture the holistic action content
in a sequence. Such a representation is critical for action based genres such
as surveillance. We show that an analysis of the trajectory shape is able to
produce a temporal segmentation. Furthermore, we build an action based
video summary using the Top Discriminative Active Pixels in the segments.
Experiments are presented on real-world outdoor surveillance scenes.
(pdf article)