The objective of this project is to develop human intelligence-inspired algorithms that exploit multi-modal sources of low and high quality data to achieve a series of objectives such as detection, localization, tracking, and classification. We propose to develop a rigorous hierarchical adaptive decision making (HADM) algorithm will be developed that includes multiple levels of decision making organized in a hierarchical manner, a confidence factor associated with each decision, and a feedback mechanism used to trigger the need for higher quality data or to go back and correct erroneous intermediary decisions. In Phase I, we developed and illustrated an approach to HADM for anomaly detection and localization using a random dot paradigm which is representative of human decision making under uncertainty. The methodology was applied to a radar sensing model to illustrate the application to surveillance systems. We also developed an experimental demonstration using simulated data from The Ohio State Universitys Cognitive Radar Engineering Workspace (CREW) testbed. In Phase II, we propose to extend and refine the HADM algorithms developed in Phase I, apply the techniques to models of realistic single and/or multi-sensor surveillance systems, and demonstrate performance on simulated data and in experimental demonstrations using the CREW system.
