# Parametric Hidden Markov Models for Gesture Recognition

@article{Wilson1999ParametricHM, title={Parametric Hidden Markov Models for Gesture Recognition}, author={Andrew D. Wilson and Aaron F. Bobick}, journal={IEEE Trans. Pattern Anal. Mach. Intell.}, year={1999}, volume={21}, pages={884-900} }

A method for the representation, recognition, and interpretation of parameterized gesture is presented. By parameterized gesture we mean gestures that exhibit a systematic spatial variation; one example is a point gesture where the relevant parameter is the two-dimensional direction. Our approach is to extend the standard hidden Markov model method of gesture recognition by including a global parametric variation in the output probabilities of the HMM states. Using a linear model of dependence…

## Figures, Tables, and Topics from this paper

## 674 Citations

Realtime Segmentation and Recognition of Gestures using Hierarchical Markov Models

- 2011

In this work, we present a realtime system for continuous gesture segmentation and recognition. The model is an extension of the system called Gesture Follower developed at Ircam, which is an hybrid…

Recognizing Everyday Human Movements through Human Anatomy Based Coupled Hidden Markov Models

- 2005

Gesture recognition has been an active research area for several decades. Pose-driven Hidden Markov Models (HMMs), in which each state corresponds to a single pose, have been the most popular…

Two-stage Hidden Markov Model in Gesture Recognition for Human Robot Interaction

- Computer Science
- 2012

An approach for HRI is introduced in which not only the human can naturally control the robot by hand gesture, but also the robot can recognize what kind of task it is executing and improve the recognition of whole gesture meaning recognition.

Recognition and Synthesis of Human Movements by Parametric HMMs

- Computer ScienceStatistical and Geometrical Approaches to Visual Motion Analysis
- 2008

This work argues that many human movements are parametric, i.e., a parametric variation of the movements in dependence of, e.g., a position a person is pointing at, and uses parametric HMMs (PHMMs) to model the parametric variability of human movements explicitly.

Untethered gesture acquisition and recognition for virtual world manipulation

- Computer ScienceVirtual Reality
- 2005

A vision-based method for tracking the pose of a user in real time and a technique that provides parameterized gesture recognition are described that are performed using rank-order fusion to merge speech and vision hypotheses.

Learning dynamics for exemplar-based gesture recognition

- Computer Science2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
- 2003

A non-parametric HMM approach that uses a discrete HMM with arbitrary states (decoupled from exemplars) to capture the dynamics over a large exemplar space where a nonparametric estimation approach is used to model the exemplar distribution.

Neural Networks with Hidden Markov Models in Skeleton-Based Gesture Recognition

- Computer ScienceKSE
- 2014

By carefully tailoring NNs to a traditional HMM-based GR system, this study can improve significantly the performance, hence, achieving very competitive results on a skeleton-basedGR task which is defined by using Microsoft Research Cambridge 12 (MSRC-12) data.

Dynamic Gesture Recognition Based on Dynamic Bayesian Networks

- Computer Science
- 2007

Hierarchical Dynamic Vision System (HDVS), which based on dynamic Bayesian networks (DBNs) is proposed for automatically identifying human gestures in this paper, is used as the underlying topology in the proposed dynamic system to recognize human gestures with motion trajectories in an indoor scene.

Contextual Markovian Models

- Computer Science
- 2014

A generative framework of Contextual Hidden Markov Models (CHMM) to model directly the influence of contextual information on observation sequences by parameterizing the probability distributions of HMMs with static or dynamic contextual variables and a Transfer Learning approach to learn Contextual HMMs from fewer examples.

Gesture Modeling by Hanklet-Based Hidden Markov Model

- Computer ScienceACCV
- 2014

This paper aims at decomposing a gesture into sub-trajectories that are the output of a sequence of atomic linear time invariant systems, and uses a Hidden Markov Model to model the transitions from the LTI system to another.

## References

SHOWING 1-10 OF 64 REFERENCES

Recognition and interpretation of parametric gesture

- Computer ScienceSixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)
- 1998

The approach is to extend the standard hidden Markov model method of gesture recognition by including a global parametric variation in the output probabilities of the states of the HMM.

Nonlinear PHMMs for the interpretation of parameterized gesture

- Computer ScienceProceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)
- 1998

A generalized expectation-maximization (GEM) algorithm for training the PHMM and a GEM algorithm to simultaneously recognize the gesture and estimate the value of the parameter, and results on a pointing gesture are presented.

Vision based hand gesture interpretation using recursive estimation

- Computer ScienceProceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers
- 1994

The concept of recursive estimation of the gesture state is introduced, modeling the gestures as a sequence of static hand poses as a hidden Markov model where the unobservable state is the spatio-temporal gesture and the hand poses are the observations.

Learning visual behavior for gesture analysis

- Computer ScienceProceedings of International Symposium on Computer Vision - ISCV
- 1995

A state-based method for learning visual behavior from image sequences that exploits two constraints allowing application of the technique to view-based gesture recognition: gestures are modal in the space of possible human motion, and gestures are viewpoint-dependent.

Maximum likelihood linear transformations for HMM-based speech recognition

- Computer ScienceComput. Speech Lang.
- 1998

The paper compares the two possible forms of model-based transforms: unconstrained, where any combination of mean and variance transform may be used, and constrained, which requires the variance transform to have the same form as the mean transform.

Recognizing human action in time-sequential images using hidden Markov model

- Computer ScienceProceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- 1992

The recognition rate is improved by increasing the number of people used to generate the training data, indicating the possibility of establishing a person-independent action recognizer.

A State-Based Approach to the Representation and Recognition of Gesture

- Computer ScienceIEEE Trans. Pattern Anal. Mach. Intell.
- 1997

A state-based technique for the representation and recognition of gesture is presented, using techniques for computing a prototype trajectory of an ensemble of trajectories and for defining configuration states along the prototype and for recognizing gestures from an unsegmented, continuous stream of sensor data.

Visual Recognition of American Sign Language Using Hidden Markov Models.

- Computer Science
- 1995

Using hidden Markov models (HMM's), an unobstrusive single view camera system is developed that can recognize hand gestures, namely, a subset of American Sign Language (ASL), achieving high recognition rates for full sentence ASL using only visual cues.

Parameterized Modeling and Recognition of Activities

- Mathematics, Computer ScienceComput. Vis. Image Underst.
- 1999

A new approach for modeling and recognition of atomic activities that employs principal component analysis and analytical global transformations is proposed.

Space-time gestures

- Computer ScienceProceedings of IEEE Conference on Computer Vision and Pattern Recognition
- 1993

A method for learning, tracking, and recognizing human gestures using a view-based approach to model articulated objects is presented and results showing tracking and recognition of human hand gestures at over 10 Hz are presented.