1 February 1992 Bayesian inference for model-based vision
Author Affiliations +
In order to achieve successful recognition in practical model-based vision applications, many diverse sources of knowledge need to be exploited. By incorporating such information sources as sensor phenomenology, viewing geometry, model part geometry, scene environment, and external situational constraints, we can better recognize parameterized and obscured objects, resolve conflicting hypotheses, and derive the scene interpretation in an efficient manner. A Bayesian modeling and reasoning approach is well-suited for solving this problem by satisfying these goals: integration of diverse evidence sources in an order-independent manner; efficient manipulation of the system for opportunistic control; rational reasoning behavior in terms of graceful degradation as uncertainty increases; and explanation of results in terms of domain properties. We have developed a general model-based recognition Bayesian modeling and reasoning paradigm and tested it by applying it to two model-based recognition problems: military battlefield scene analysis and vehicle classification. The capabilities of this modeling representation include: hierarchical reasoning (coarse to fine, sub-part to whole) for favorable combinatorics; multiple belief propagation strategies for adapting to complex feature interactions; incorporation of static and dynamic constraints; and probabilistic reasoning over both discrete and continuous variables.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gil Ettinger, Gil Ettinger, Douglas R. Morgan, Douglas R. Morgan, Paul A. Reinholdsten, Paul A. Reinholdsten, } "Bayesian inference for model-based vision", Proc. SPIE 1609, Model-Based Vision Development and Tools, (1 February 1992); doi: 10.1117/12.57117; https://doi.org/10.1117/12.57117


Non-monotonic model-based system for scene interpretation
Proceedings of SPIE (December 31 1989)
SAR ATR via pose-tagged partial evidence fusion
Proceedings of SPIE (June 09 1996)
Computationally intelligent approach to ATR
Proceedings of SPIE (August 12 1999)
A Model-Based System For Force Structure Analysis
Proceedings of SPIE (April 04 1985)

Back to Top