Deakin University
Browse

Incremental learning of temporally-coherent Gaussian mixture models

Download (514.71 kB)
journal contribution
posted on 2006-01-01, 00:00 authored by Ognjen Arandjelovic, R Cipolla
In this paper we address the problem of learning Gaussian Mixture Models (GMMs) incrementally. Unlike previous approaches which universally assume that new data comes in blocks representable by GMMs which are then merged with the current model estimate, our method works for the case when novel data points arrive one- by-one, while requiring little additional memory. We keep only two GMMs in the memory and no historical data. The current fit is updated with the assumption that the number of components is fixed which is increased (or reduced) when enough evidence for a new component is seen. This is deducedfrom the change from the oldest fit of the same complexity, termed the Historical GMM, the concept of which is central to our method. The performance of the proposed method is demonstrated qualitatively and quantitatively on several synthetic data sets and video sequences of faces acquired in realistic imaging conditions.

History

Journal

Society of Manufacturing Engineers (SME) Technical Papers

Volume

TP06PUB22

Pagination

1 - 1

Location

Piscataway, New Jersey

Open access

  • Yes

ISSN

0361-8765

Language

eng

Publication classification

C1.1 Refereed article in a scholarly journal

Copyright notice

2006, IEEE

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC