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… 
Realtime Segmentation and Recognition of Gestures using Hierarchical Markov Models
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
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
TLDR
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
  • D. Herzog, V. Krüger
  • Computer Science
    Statistical and Geometrical Approaches to Visual Motion Analysis
  • 2008
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 64 REFERENCES
Recognition and interpretation of parametric gesture
TLDR
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
  • Andrew D. Wilson, A. Bobick
  • Computer Science
    Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)
  • 1998
TLDR
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
TLDR
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
  • A.D. Wilson, A. Bobick
  • Computer Science
    Proceedings of International Symposium on Computer Vision - ISCV
  • 1995
TLDR
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
  • M. Gales
  • Computer Science
    Comput. Speech Lang.
  • 1998
TLDR
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
  • J. Yamato, J. Ohya, K. Ishii
  • Computer Science
    Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1992
TLDR
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
TLDR
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.
TLDR
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
TLDR
A new approach for modeling and recognition of atomic activities that employs principal component analysis and analytical global transformations is proposed.
Space-time gestures
TLDR
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.
...
1
2
3
4
5
...