Next: Image features
Up: Video Representation
Previous: Video Representation
Given a video , we first slice it
into short segments:
. Ideally, each
segment would contain a single activity event. For
simplicity, we slice the video into fixed time duration (4 seconds)
with overlapping time window. The segmentation is not perfect,
but the video segments typically contain enough information for
determining the activity type, e.g. in the nursing home
video, in 4 seconds people can take a few steps or pick
up an object.
Mirko Visontai
2004-05-13