Fast Learning of Sprites using Invariant

Moray Allan, Michalis K Titsias, Christopher K I Williams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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 transformations (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.
Original languageEnglish
Title of host publicationProceedings of the British Machine Vision Conference 2005
PublisherBMVA Press
Number of pages10
ISBN (Print)1 901725 29 4
Publication statusPublished - 2005
EventBritish Machine Vision Conference 2005 (BMVC) - Oxford Brookes Univeristy, Oxford, United Kingdom
Duration: 5 Sept 20058 Sept 2005


ConferenceBritish Machine Vision Conference 2005 (BMVC)
Country/TerritoryUnited Kingdom


Dive into the research topics of 'Fast Learning of Sprites using Invariant'. Together they form a unique fingerprint.

Cite this