Multisource data classification with dependence trees

Abstract

In order to apply a statistical approach to the classification of multisource remote-sensing data, one of the main problems to face lies in the estimation of probability distribution functions. This problem arises out of the difficulty of defining a common statistical model for such heterogeneous data. A possible solution is to adopt nonparametric approaches, which rely on the availability of training samples without any assumption about the related statistical distributions. The purpose of this paper is to investigate the suitability of the concept of dependence trees for the integration of multisource information through estimation of probability distributions. First, this concept, introduced by Chow and Liu, is used to provide an approximation of a probability distribution defined in an-dimensional space by a product of 1 probability distributions defined in two-dimensional (2-D) spaces; this approximation corresponds, in terms of graph theoretical interpretation, to a tree of dependence. For each land cover class, a dependence tree is generated by minimizing an appropriate closeness measure. Then, a nonparametric estimation of the second-order probability distributions is carried out through the Parzen window approach, based on the implementation of 2-D Gaussian kernels. In this way, it is possible to reduce the complexity of the estimation, while capturing a significant part of the interdependence among variables. A comparison with other multisource data fusion methods, namely, the multilayer perceptron (MLP) method, the-nearest neighbor (-NN) method, and a Bayesian hierarchical classifier (BHC), is made. Experimental results obtained on multisensor [airborne thematic mapper (ATM) and synthetic aperture radar (SAR)] and multisource (experimental synthetic aperture radar (E-SAR) and a textural feature) data sets show that the proposed fusion method based on dependence trees is able to provide a classification accuracy similar to those of the other methods considered, but with the advantage of a reduced computational load.

Classification of hyperspectral remote sensing images with support vector machines

“…Tree-based classifiers have represented an interesting and effective way to structure and solve complex classification problems [44]- [47]. The organization of information into a hierarchical tree allows to achieve a faster processing capability and, at times, a higher accuracy of analysis.…”

Region-Based Classification of Multisensor Optical-SAR Images

“…(1)), the dependence tree approach is adopted, that nonparametrically approximates each class-conditional pdf by a product of bivariate pdfs of couples of features [4], i.e. (k = 1, 2, .…”

“…The method is based on two key ideas. First, a semiparametric probability density function (pdf) estimation approach, combining the nonparametric dependence-tree method [4] with a set of parametric bivariate distributions, is used to model the joint statistics of optical-SAR data. Then, a region-based classi cation approach, incorporating a segmentation technique [5,6], is adopted to integrate the contextual information in the classi cation process.…”

Land cover classification with multi-source data using evidential reasoning approach

“…For example, many landscape metrics are built on the land cover classification (Zhang et al, 2006;Zhang et al, 2009). It has been confirmed that multi-source data have the potential for improving image classification accuracy, since they can provide much more information compared to single satellite imagery for classification decisions (Kim and Swain, 1995;Chiuderi, 1997;Le Hegarat-Mascle et al, 1997;Datcu et al, 2002;Franklin et al, 2002;Ozesmi and Bauer, 2002;Chitroub, 2003;Tzeng et al, 2007;Camps-Valls et al, 2008;Na et al, 2009). Geospatial data used for image classification include four types: interval data, ratio data, nominal data and ordinal data (Franklin et al, 2002).…”