Title :
Task-specific utility in a general Bayes net vision system
Author :
Rimey, Raymond D. ; Brown, Christopher M.
Author_Institution :
Dept. of Comput. Sci., Rochester Univ., NY, USA
Abstract :
TEA is a task-oriented computer vision system that uses Bayes nets and a maximum expected-utility decision rule to choose a sequence of task-dependent and opportunistic visual operations on the basis of their cost and (present and future) benefit. The authors discuss technical problems regarding utilities, present TEA-1´s utility function (which approximates a two-step lookahead), and compare it to various simpler utility functions in experiments with real and simulated scenes
Keywords :
Bayes methods; computer vision; inference mechanisms; probabilistic logic; Bayes nets; maximum expected-utility decision rule; opportunistic visual operations; simpler utility functions; task-oriented computer vision system; two-step lookahead; utility function; Application software; Cameras; Computational modeling; Computer science; Computer vision; Costs; Decision theory; Decision trees; Layout; Machine vision;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223214
