Fusion of hyperspectral and LIDAR remote sensing data for the classification of complex forest areas

In this paper we propose an analysis on the joint effect of hyperspectral and LIDARdata for the classification of complex forest areas. In greater detail, we describe an advanced system for LI-DAR and hyperspectral image analysis and investigate the effectiveness of Support Vector Ma-chine and Gaussian Maximum Likelihood (with Leave-One-Out-Covariance estimation) classifi-cation techniques in complex forest scenarios characterized by a high number of species. In addition, we present an analysis on the influence of LIDAR data on the classification accuracy obtained by using hyperspectral images. Several experiments were carried out using different subsets of hyperspectral bands and adding to these bands LIDAR channels. From results of these experiments it is possible to derive interesting conclusions on the effectiveness and potentialities of the joint use of hyperspectral and LIDARdata and on the effectiveness of the different classi-fication techniques analyzed.