Intelligent Electronic Navigational Aids: A New Approach

摘要

The smart management of clutter is a key component in designing intelligent, next-generation user interfaces and electronic displays. Intelligent devices can enhance a user's situational awareness under adverse conditions. In this paper we present two approaches to assist a user with target detection and clutter analysis, and we suggest how these tools could be integrated with an electronic chart system. The first tool, an information fusion technique, is a multiple-view generalization of AdaBoost, which can assist a user in finding a target partially obscured by display clutter. The second technique clusters geospatial features on an electronic display and determines a meaningful measure of display clutter. The clutter metric correlates with preliminary, subjective, clutter rankings. The metric can be used to warn a user if display clutter is a potential hazard for his performance. We compare the performance of the proposed techniques with recent classifier fusion strategies on synthetic and real data.