THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
Goal-Orianted Dynamic Vision
UR > CS > Research > Vision > Publications > Goal-Orianted Dynamic Vision
pdf 694 KB
ps.gz 253 KB
ps 1.27 MB
@TechReport{von Kaenel:TR93,
  author = 	 {Peter A. von Kaenel and Christopher M. Brown and Raymond D. Rimey},
  title = 	 {Goal-Orianted Dynamic Vision},
  institution =  {Comp. Sci. Dept. Rochester NY},
  year = 	 {1993},
  number = 	 {466},
  address = 	 {Rochester NY},
  month = 	 {August},
  abstract  =    {#
TEA-1 is a selective vision system that uses Bayes nets for representation and benefit-
cost analysis for control of visual and nonvisual actions. TEA-1 solves T-world problems,
a class of problems involving static two-dimensional scenes. For example, TEA-1 has been
demonstrated to answer questions about scenes of dinner tables.

This paper presents dTEA-1, an extension to TEA-1 that allows tasks to be performed on 
dynamic scenes. Currently, dTEA-1 successfully performs a task on a simulated train scene.
The objects in the scene include a train on a track and a herd of cows, but the domain 
may be extended to include static objects and other classifications of moving objects. The
task is to keep track of the locations of objects, and the system intelligently allocates
its effort to keep uncertainty and cost to a minimum.  }
}