Journal article
Hidden Markov Model on a unit hypersphere space for gesture trajectory recognition
Pattern recognition letters, v 36(1), pp 144-153
15 Jan 2014
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
•Gesture trajectory is modeled on a unit-hypersphere for scale-invariancy.•A Mixture of von Mises-Fisher (MvMF) distribution is incorporated into an HMM.•The parameter estimation formulae for MvMF-HMM are derived in a closed form.
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.
Metrics
Details
- Title
- Hidden Markov Model on a unit hypersphere space for gesture trajectory recognition
- Creators
- Jounghoon Beh - Research Institute for Advanced Computer ScienceDavid K. Han - Office of Naval ResearchRamani Durasiwami - Research Institute for Advanced Computer ScienceHanseok Ko - Research Institute for Advanced Computer Science
- Publication Details
- Pattern recognition letters, v 36(1), pp 144-153
- Publisher
- Elsevier
- Number of pages
- 10
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000329145400018
- Scopus ID
- 2-s2.0-84893049119
- Other Identifier
- 991021930828104721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence