PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

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.

Abstract

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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Additional Information:Also available from http://www.dai.ed.ac.uk/homes/ckiw/online_pubs.html
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:84
Deposited By:Christopher Williams
Deposited On:14 May 2004