Fast Unsupervised Greedy Learning of Multiple Objects and Parts from Video
Michalis Titsias and Christopher Williams
In: Generative-Model Based Vision 2004, 2 July 2004, Washington DC, USA.
Williams and Titsias (2004) have shown how to carry out unsupervised
greedy learning of multiple objects from images (GLOMO), building on
the work of Jojic and Frey (2001). In this paper we show that the
earlier work on GLOMO can be greatly speeded up for video sequence
data by carrying out approximate tracking of the multiple objects in
the scene. Our method is applied to raw image sequence data and
extracts the objects one at a time. First, the moving background is
learned, and moving objects are found at later stages. The algorithm
recursively updates an appearance model of the tracked object
so that possible occlusion of the object is taken into account
which makes tracking stable.
We apply this method to learn multiple objects in image sequences
as well as articulated parts of the human body.