Learning structured behaviour models using variable length Markov models

Aphrodite Galata, Neil Johnson, David Hogg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In recent years there has been an increased interest in the modelling and recognition of human activities involving highly structured and semantically rich behaviour such as dance, aerobics, and sign language. A novel approach is presented for automatically acquiring stochastic models of the high-level structure of an activity without the assumption of any prior knowledge. The process involves temporal segmentation into plausible atomic behaviour components and the use of variable length Markov models for the efficient representation of behaviours. Experimental results are presented which demonstrate the generation of realistic sample behaviours and evaluate the performance of models for long-term temporal prediction.

Original languageEnglish
Title of host publicationProceedings - IEEE International Workshop on Modelling People, MPeople 1999
PublisherIEEE
Pages95-102
Number of pages8
ISBN (Electronic)0769503624, 9780769503622
DOIs
Publication statusPublished - 1999
Event1999 IEEE International Workshop on Modelling People, MPeople 1999 - Kerkyra, Greece
Duration: 20 Sept 1999 → …

Publication series

NameProceedings - IEEE International Workshop on Modelling People, MPeople 1999

Conference

Conference1999 IEEE International Workshop on Modelling People, MPeople 1999
Country/TerritoryGreece
CityKerkyra
Period20/09/99 → …

Fingerprint

Dive into the research topics of 'Learning structured behaviour models using variable length Markov models'. Together they form a unique fingerprint.

Cite this