Active gesture recognition using partially observable Markov decision processes
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (10514651) , 984-988 vol.3
- https://doi.org/10.1109/icpr.1996.547315
Abstract
We present a foveated gesture recognition system that guides an active camera to foveate salient features based on a reinforcement learning paradigm. Using vision routines previously implemented for an interactive environment, we determine the spatial location of salient body parts of a user and guide an active camera to obtain images of gestures of expressions. A hidden-state reinforcement learning paradigm based on the partially observable Markov decision process (POMDP) is used to implement this visual attention. The attention module selects targets to foveate based on the goal of successful recognition, and uses a new multiple-model Q-learning formulation. Given a set of target and distracter gestures, our system can learn where to foveate to maximally discriminate a particular gesture.Keywords
This publication has 8 references indexed in Scilit:
- Space-time gesturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A novel environment for situated vision and behaviorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Active face tracking and pose estimation in an interactive roomPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Q-learningMachine Learning, 1992
- A survey of algorithmic methods for partially observed Markov decision processesAnnals of Operations Research, 1991
- Active Perception and Reinforcement LearningNeural Computation, 1990
- Learning to predict by the methods of temporal differencesMachine Learning, 1988
- The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted CostsOperations Research, 1978