Paper Info
Title
Control in a 3D Reconstruction System using Selective Perception
Abstract
This paper presents a control structure for general purpose image understanding that addresses both the high level of uncertainty in local hypotheses and the computational complexity of image interpretation. The control of vision algorithms is performed by an independent subsystem that uses Bayesian networks and utility theory to compute the marginal value of information provided by alternative operators and selects the ones with the highest value.We have implemented and tested this control structure with several aerial image data-sets. The results show that the knowledge base used by the system can be acquired using standard learning techniques and that the value-driven approach to the selection of vision algorithms leads to performance gains. Moreover, the modular system architecture simplifies the addition of both control knowledge and new vision algorithms.
Year
DOI
Venue
1999
10.1109/ICCV.1999.790421
ICCV
Keywords
Field
DocType
control structure,reconstruction system,control knowledge,image interpretation,new vision algorithm,aerial image data-sets,knowledge base,selective perception,marginal value,general purpose image understanding,vision algorithm,highest value,bayesian networks,bayesian methods,utility theory,bayesian network,uncertainty,computational complexity,testing,computer networks,image reconstruction,knowledge based systems,control systems,high performance computing,3d reconstruction,computer vision
Computer vision,Computer science,Knowledge-based systems,Aerial image,Bayesian network,Artificial intelligence,Knowledge base,Control system,Systems architecture,Machine learning,3D reconstruction,Computational complexity theory
Conference
Volume
Issue
ISBN
2
1
0-7695-0164-8
Citations 
PageRank 
References 
3
0.49
7
Authors
4
Name
Order
Citations
PageRank
Maurício Marengoni19619.02
Allen Hanson221133.75
Shlomo Zilberstein33419255.70
E. M. Riseman41402458.95