Abstract:
This paper investigates the utilization of game theory models for automated analysis of hyperspectral imagery fused with other remotely sensed and/or in situ data. The au...Show MoreMetadata
Abstract:
This paper investigates the utilization of game theory models for automated analysis of hyperspectral imagery fused with other remotely sensed and/or in situ data. The author analyzes two approaches to using strategic, competitive game theory models for groundcover classification, including the application of game theory models to (i) feature-level fusion and (ii) decision fusion for hypertemporal-hyperspectral datasets. Proposed model (i) uses conflict data filtering based on mutual entropy along with the Nash equilibrium as the means to find a steady state solution. Proposed model (ii) utilizes a strategic coalition game, specifically the weighted majority game (WMG). Both models are implemented under the assumption that all players are rational. The author incorporates each of the proposed approaches, (i) and (ii), into a multi-classifier decision fusion (MCDF) system for automated ground cover classification of hyperspectral imagery collected via an unmanned airborne system (UAS) over multiple dates. The paper provides experimental results demonstrating the efficacy of the proposed game theoretic approaches, presenting significant improvements over existing methods.
Date of Conference: 10-15 July 2016
Date Added to IEEE Xplore: 03 November 2016
ISBN Information:
Electronic ISSN: 2153-7003