Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Digital Object Identifier (DOI) 10.1007/s00530-004-0148-1 Multimedia Systems 10: 164179 (2004) Multimedia Systems
 

Summary: Digital Object Identifier (DOI) 10.1007/s00530-004-0148-1
Multimedia Systems 10: 164179 (2004) Multimedia Systems
A hierarchical Bayesian network for event recognition
of human actions and interactions
Sangho Park, J.K. Aggarwal
Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX 78712, USA
(e-mail: sangho@ece.utexas.edu, aggarwaljk@mail.utexas.edu)
Published online: 25 October 2004 c Springer-Verlag 2004
Abstract. Recognizing human interactions is a challenging
task due to the multiple body parts of interacting persons and
the concomitant occlusions. This paper presents a method for
the recognition of two-person interactions using a hierarchical
Bayesian network (BN). The poses of simultaneously tracked
body parts are estimated at the low level of the BN, and the
overall body pose is estimated at the high level of the BN.
The evolution of the poses of the multiple body parts are pro-
cessed by a dynamic Bayesian network (DBN). The recogni-
tion of two-person interactions is expressed in terms of seman-
tic verbal descriptions at multiple levels: individual body-part
motions at low level, single-person actions at middle level,

  

Source: Aggarwal, J. K. - Department of Electrical and Computer Engineering, University of Texas at Austin

 

Collections: Computer Technologies and Information Sciences; Engineering