Paper Info
Title
Tracking the visual focus of attention for a varying number of wandering people.
Abstract
We define and address the problem of finding the visual focus of attention for a varying number of wandering people (VFOA-W), determining where the people's movement is unconstrained. VFOA-W estimation is a new and important problem with mplications for behavior understanding and cognitive science, as well as real-world applications. One such application, which we present in this article, monitors the attention passers-by pay to an outdoor advertisement. Our approach to the VFOA-W problem proposes a multi-person tracking solution based on a dynamic Bayesian network that simultaneously infers the (variable) number of people in a scene, their body locations, their head locations, and their head pose. For efficient inference in the resulting large variable-dimensional state-space we propose a Reversible Jump Markov Chain Monte Carlo (RJMCMC) sampling scheme, as well as a novel global observation model which determines the number of people in the scene and localizes them. We propose a Gaussian Mixture Model (GMM) and Hidden Markov Model (HMM)-based VFOA-W model which use head pose and location information to determine people's focus state. Our models are evaluated for tracking performance and ability to recognize people looking at an outdoor advertisement, with results indicating good performance on sequences where a moderate number of people pass in front of an advertisement.
Year
DOI
Venue
2008
10.1109/TPAMI.2007.70773
IEEE Trans. Pattern Anal. Mach. Intell.
Keywords
Field
DocType
gaussian mixture model,video analysis,head location,vfoa-w estimation,index terms— computer vision,vfoa-w model,outdoor advertisement,tracking,hidden markov model,moderate number,wandering people,important problem,varying number,vfoa-w problem,con- sumer products.,visual focus,advertising,pose estimation,movement,marketing,cognition,cognitive science,attention,sampling methods,computer vision,algorithms,monte carlo methods,consumer products,bayesian methods,hidden markov models,layout,artificial intelligence,gaussian processes,visual fields,human factors,displays,tv,visual perception,state space,indexing terms,dynamic bayesian network
Computer vision,Markov chain Monte Carlo,Computer science,Markov model,Markov chain,Pose,Bayesian network,Artificial intelligence,Hidden Markov model,Mixture model,Dynamic Bayesian network
Journal
Volume
Issue
ISSN
30
7
0162-8828
Citations 
PageRank 
References 
62
1.90
28
Authors
4
Name
Order
Citations
PageRank
Kevin Smith1243088.78
Sileye O. Ba238123.08
Jean-marc Odobez31641110.52
Daniel Gatica-Perez44182276.74