Support Vector Machines for Crop Classification Using Hyperspectral Data

Abstract

In this communication, we propose the use of Support Vector Machines (SVM) for crop classification using hyperspectral images. SVM are benchmarked to well–known neural networks such as multilayer perceptrons (MLP), Radial Basis Functions (RBF) and Co-Active Neural Fuzzy Inference Systems (CANFIS). Models are analyzed in terms of efficiency and robustness, which is tested according to their suitability to real–time working conditions whenever a preprocessing stage is not possible. This can be simulated by considering models with and without a preprocessing stage. Four scenarios (128, 6, 3 and 2 bands) are thus evaluated. Several conclusions are drawn: (1) SVM yield better outcomes than neural networks; (2) training neural models is unfeasible when working with high dimensional input spaces and (3) SVM perform similarly in the four classification scenarios, which indicates that noisy bands are successfully detected.

This research has been partially supported by the Information Society Technologies (IST) programme of the European Community. The results of this work will be applied in the “Smart Multispectral System for Commercial Applications” project (SmartSpectra, www.smartspectra.com). All the data used were acquired in the Scientific Analysis of the European Space Agency (ESA) Airborne Multi-Annual Imaging Spectrometer Campaign DAISEX (Contract #15343/01/NL/MM).