Hidden Markov Model on a unit hypersphere space for gesture trajectory recognition

Jounghoon Beh, David K. Han, Ramani Durasiwami, Hanseok Ko

Research output: Contribution to journalArticlepeer-review

38 Citations (Scopus)

Abstract

In this paper, a Mixture of von Mises-Fisher (MvMF) Probability Density Function (PDF) is incorporated into a Hidden Markov Model (HMM) in order to model spatio-temporal data in a unit-hypersphere space. The parameter estimation formulae for MvMF-HMM are derived in a closed form. As an application for the proposed MvMF-HMM, hands gesture trajectory recognition task is considered. Modeling gesture trajectory on a unit-hypersphere inherently removes bias from a subject's arm length or distance between a subject and camera. In experiments with public datasets, InteractPlay and UCF Kinect, the proposed MvMF-HMM showed superior recognition performance compared to current state-of-the-art techniques.

Original languageEnglish
Pages (from-to)144-153
Number of pages10
JournalPattern Recognition Letters
Volume36
Issue number1
DOIs
Publication statusPublished - 2014 Jan 15

Keywords

  • Directional statistics
  • Gesture recognition
  • Hidden Markov model
  • Von Mises-Fisher distribution

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Hidden Markov Model on a unit hypersphere space for gesture trajectory recognition'. Together they form a unique fingerprint.

Cite this