Chapter

Optical Remote Sensing

Volume 3 of the series Augmented Vision and Reality pp 99-122

Date:

A Divide-and-Conquer Paradigm for Hyperspectral Classification and Target Recognition

  • Saurabh PrasadAffiliated withGeosystems Research Institute and Electrical and Computer Engineering Department, Mississippi State University Email author 
  • , Lori M. BruceAffiliated withGeosystems Research Institute and Electrical and Computer Engineering Department, Mississippi State University

* Final gross prices may vary according to local VAT.

Get Access

Abstract

In this chapter, a multi-classifier, decision fusion framework is proposed for robust classification of high dimensional hyperspectral data in small-sample-size conditions. Such datasets present two key challenges. (1) The high dimensional feature spaces compromise the classifiers’ generalization ability in that the classifier tends to over-fit decision boundaries to the training data. This phenomenon is commonly known as the Hughes phenomenon in the pattern classification community. (2) The small-sample-size of the training data results in ill-conditioned estimates of its statistics. Most classifiers rely on accurate estimation of these statistics for modeling training data and labeling test data, and hence ill-conditioned statistical estimates result in poorer classification performance. Conventional approaches, such as Stepwise Linear Discriminant Analysis (S-LDA) are sub-optimal, in that they utilize a small subset of the rich spectral information provided by hyperspectral data for classification. In contrast, the approach proposed in this chapter utilizes the entire high dimensional feature space for classification by identifying a suitable partition of this space, employing a bank-of-classifiers to perform “local” classification over this partition, and then merging these local decisions using an appropriate decision fusion mechanism. Adaptive classifier weight assignment and nonlinear pre-processing (in kernel induced spaces) are also proposed within this framework to improve its robustness over a wide range of fidelity conditions. This chapter demonstrates the efficacy of the proposed algorithms to classify remotely sensed hyperspectral data, since these applications naturally result in very high dimensional feature spaces and often do not have sufficiently large training datasets to support the dimensionality of the feature space. Experimental results demonstrate that the proposed framework results in significant improvements in classification accuracies over conventional approaches.

Keywords

Decision Fusion Hyperspectral Imagery Kernel Discriminant Analysis Multi-Classifiers Small-Sample-Size Conditions Statistical Pattern Recognition