Multisensor fusion classification with a multilayer perceptron

Abstract

The problem of fusing information from multiple sensors to perform pattern recognition is addressed. A technique is proposed for performing target/nontarget discrimination using information from absolute range and forward looking infrared (FLIR) sensors. A multilayer perceptron is used to perform the feature-level fusion and is compared to a <e1 xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</e1> -nearest-neighbor classifier as well as a nonparametric Bayesian classifier using Parzen windows. All three classifiers show statistically significant improvement from the fusion process; however, the multilayer perceptron uses far fewer free parameters, which should improve generalization capability. Also, the multilayer perceptron requires much less computation than the traditional classifiers