Active gesture recognition using partially observable Markov decision processes
نویسندگان
چکیده
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 or expressions. A hiddenstate 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 distractor gestures, our system can learn where to foveate to maximally discriminate a particular gesture.
منابع مشابه
Reinforcement Learning of Active Recognition Behaviors
We show how a concise representation of active recognition behavior– what observations to make to detect a given object– can be derived from hidden-state reinforcement learning techniques. These learning techniques can solve decision process tasks which include perceptual observations, defined formally as Partially Observable Markov Decision Processes (POMDP). We define recognition within a POM...
متن کاملSupervised Training of Conversive Hidden Non-markovian Models: Increasing Usability for Gesture Recognition
Hidden non-Markovian Models (HnMMs) were introduced and formalized as an extension of Hidden Markov Models for the analysis of partially observable stochastic processes. Their main advantage over HMM is the possibility to model arbitrary distributions for state transition duration, so that the unobservable stochastic process needs not to be Markovian. Besides academic examples, HnMMs were appli...
متن کاملPerformance of a Single Action Partially Observable Markov Decision Process in a Recognition Task
Partially Observable Markov Decision Processes (POMDPs) have been applied extensively to planning in environments where knowledge of an underlying process is confounded by unknown factors[3, 4, 7]. By applying the POMDP architecture to basic recognition tasks, we introduce a novel pattern recognizer that operates under partially observable conditions. This Single Action Partially Observable Mar...
متن کاملPerformance of a Single Action POMDP in a Recognition Task
Partially Observable Markov Decision Processes (POMDPs) have been applied extensively to planning in environments where knowledge of an underlying process is confounded by unknown factors[3, 4, 7]. By applying the POMDP architecture to a basic recognition task, we introduce a novel pattern recognizer that operates under partially observable conditions. This Single Action Partially Observable Ma...
متن کاملMonte Carlo Hidden Markov Models: Learning Non-Parametric Models of Partially Observable Stochastic Processes
We present a learning algorithm for non-parametric hidden Markov models with continuous state and observation spaces. All necessary probability densities are approximated using samples, along with density trees generated from such samples. A Monte Carlo version of Baum-Welch (EM) is employed to learn models from data. Regularization during learning is achieved using an exponential shrinking tec...
متن کامل