This paper presents new approaches in character-
izing and segmenting the content of video. These approaches are
developed based upon the pattern analysis of spatio-temporal
slices. While traditional approaches to motion sequence analysis
tend to formulate computational methodologies on two or three
adjacent frames, spatio-temporal slices provide rich visual pat-
terns along a larger temporal scale. In this paper, we first describe
a motion computation method based on a structure tensor for-
mulation. This method encodes visual patterns of spatio-temporal
slices in a tensor histogram, on one hand, characterizing the tem-
poral changes of motion over time, on the other hand, describing
the motion trajectories of different moving objects. By analyzing
the tensor histogram of an image sequence, we can temporally
segment the sequence into several motion coherent subunits, in ad-
dition, spatially segment the sequence into various motion layers.
The temporal segmentation of image sequences expeditiously
facilitates the motion annotation and content representation of a
video, while the spatial decomposition of image sequences leads to
a prominent way of reconstructing background panoramic images
and computing foreground objects
