Bayesian Inference in Model-Based Machine Vision
This work addresses the challenge of multi-sensor integration for model-based vision systems, but it appears incremental as it builds on existing Bayesian methods.
The paper tackles the problem of visual interpretation in machine vision by integrating hierarchical Bayesian inference with physical object representations and sensor models, resulting in a system that uses probabilities to rank hypotheses.
This is a preliminary version of visual interpretation integrating multiple sensors in SUCCESSOR, an intelligent, model-based vision system. We pursue a thorough integration of hierarchical Bayesian inference with comprehensive physical representation of objects and their relations in a system for reasoning with geometry, surface materials and sensor models in machine vision. Bayesian inference provides a framework for accruing_ probabilities to rank order hypotheses.