Combat Identification with Sequential Observations, Rejection Option, and Out-of-Library Targets
Abstract
This research extends a mathematical framework to select the optimal sensor ensemble and fusion method across multiple decision thresholds subject to warfighter constraints for a combat identification (CID) system. The formulation includes treatment of exemplars from target classes on which the CID system classifiers are not trained (out-of-library classes) and enables the warfighter to optimize a CID system without explicit enumeration of classifier error costs. A time-series classifier design methodology is developed and applied, yielding a multi-variate Gaussian hidden Markov model (HMM). The extended CID framework is used to compete the HMM-based CID system against a template-based CID system. The framework evaluates competing classifier systems that have multiple fusion methods, varied prior probabilities of targets and non-targets, varied correlation between multiple sensor looks, and varied levels of target pose estimation error. Assessment using the extended framework reveals larger feasible operating regions for the HMM-based classifier across experimental settings. In some cases the HMM-based classifier yields a feasible region that is 25\% of the threshold operating space versus 1\% for the template-based classifier.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2005
- Accession Number
- ADA441989
Entities
People
- Timothy W. Albrecht
Organizations
- Air Force Institute of Technology