Statistical Foreground Modelling for Object Localisation
2000 (English)Conference paper (Refereed)
A Bayesian approach to object localisation is feasible given suitable likelihood models for image observations. Such a likelihood involves statistical modelling - and learning - both of the object foreground and of the scene background. Statistical background models are already quite well understood. Here we propose a “conditioned likelihood” model for the foreground, conditioned on variations both in object appearance and illumination. Its effectiveness in localising a variety of objects is demonstrated.
Place, publisher, year, edition, pages
2000. 307-323 p.
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-69635DOI: 10.1007/3-540-45053-X_20OAI: oai:DiVA.org:kth-69635DiVA: diva2:485657
Proceedings of the European Conference on Computer Vision (ECCV 2000)
NR 201408052012-01-292012-01-29Bibliographically approved