Fast Learning of Sprites using Invariant Features
Moray Allan, Michalis Titsias and Christopher Williams
In: British Machine Vision Conference 2005, 5-8 September 2005, Oxford, UK.
A popular framework for the interpretation of image sequences is the layers
or sprite model of e.g. Wang and Adelson (1994), Irani et al. (1994). Jojic
and Frey (2001) provide a generative probabilistic model framework for this
task, but their algorithm is slow as it needs to search over discretized trans-
formations (e.g. translations, or affines) for each layer. In this paper we show
that by using invariant features (e.g. Lowe's SIFT features) and clustering
their motions we can reduce or eliminate the search and thus learn the sprites
much faster. We demonstrate our algorithm on two image sequences.