Paper Info
Title
Real-time estimation of human visual attention with dynamic bayesian network and MCMC-based particle filter
Abstract
Recent studies in signal detection theory suggest that the human responses to the stimuli on a visual display are nondeterministic. People may attend to different locations on the same visual input at the same time. Constructing a stochastic model of human visual attention would be promising to tackle the above problem. This paper proposes a new method to achieve a quick and precise estimation of human visual attention based on our previous stochastic model with a dynamic Bayesian network. A particle filter with Markov chain Monte-Carlo (MCMC) sampling make it possible to achieve a quick and precise estimation through stream processing. Experimental results indicate that the proposed method can estimate human visual attention in real time and more precisely than previous methods.
Year
DOI
Venue
2009
10.1109/ICME.2009.5202483
ICME
Keywords
Field
DocType
real-time estimation,mcmc-based particle filter,precise estimation,visual input,dynamic bayesian network,previous method,previous stochastic model,visual display,new method,human visual attention,real time,human response,monte carlo methods,markov processes,hidden markov models,stream processing,stochastic model,probability density function,particle filter,visualization,signal detection theory,stochastic processes,computer vision,markov chain monte carlo
Markov process,Markov chain Monte Carlo,Human visual system model,Computer science,Particle filter,Artificial intelligence,Computer vision,Pattern recognition,Nondeterministic algorithm,Markov chain,Hidden Markov model,Machine learning,Dynamic Bayesian network
Conference
ISSN
Citations 
PageRank 
1945-7871
10
0.77
References 
Authors
16
4
Name
Order
Citations
PageRank
Kouji Miyazato1652.58
Akisato Kimura224428.03
Shigeru Takagi3100.77
Junji Yamato41120165.72