Representability of human motions by Factorial Hidden Markov Models

Dana Kulić, Wataru Takano, Yoshihiko Nakamura

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

35 Citations (Scopus)

Abstract

This paper describes an improved methodology for human motion recognition and imitation based on Factorial Hidden Markov Models (FHMM). Unlike conventional Hidden Markov Models (HMMs), FHMMs use a distributed state representation, which allows for more efficient representation of each time sequence. Once the FHMMs are trained with exemplar motion data, they can be used to generate sample trajectories for motion production, and produce significantly more accurate trajectories compared to single Hidden Markov chain models. Due to the additional information encoded in FHMMs models, FHMM models have a higher Kullback-Leibler distance compared to single Markov chain models, making it easier to distinguish between similar models. The efficacy of using FHMMs is tested on a database of human motions obtained through motion capture. The results show that FHMMs provide better generalization to new data when compared to conventional HMMs during motion recognition, as well as providing a better fit for generated data.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages2388-2393
Number of pages6
ISBN (Print)1424409128, 9781424409129
DOIs
Publication statusPublished - 1 Dec 2007
Externally publishedYes
Event2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007 - San Diego, CA, United States of America
Duration: 29 Oct 20072 Nov 2007

Publication series

NameIEEE International Conference on Intelligent Robots and Systems

Conference

Conference2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
CountryUnited States of America
CitySan Diego, CA
Period29/10/072/11/07

Cite this