Hyperspectral Classification Fusion for Classifying Different Military Targets

Abstract

The objective of this paper is to develop novel classification structures for military targets detection and recognition by employing different fusion techniques. In real applications, the great diversity of materials in the background areas and the similarity between the background and target signatures result in high false alarm rates and large miss classification errors. In this paper, two novel target detection and recognition systems are proposed using different fusion techniques: decision fusion and classification fusion employing confidence vectors. These new systems are tested using an experimental data set to assess their effectiveness.