LiDAR Data Classification Using Extinction Profiles and a Composite Kernel Support Vector Machine

Abstract

This letter proposes a novel framework for the classification of light detection and ranging (LiDAR)-derived features. In this context, several features are extracted directly from the LiDAR point cloud data using aggregated local point neighborhoods, including laser echo ratio, variance of point elevation, plane fitting residuals, and echo intensity. Additionally, the LiDAR digital surface model (DSM) is input to our classification. Thus, both the LiDAR raster DSM and also rich geometric and also backscatter 3-D point cloud information aggregated to images are considered in our workflow. These extracted features are characterized as base images to be fed to extinction profiles to model spatial and contextual information. Then, a composite kernel support vector machine is investigated to efficiently integrate the elevation and spatial information suitable for the LiDAR data. Results indicate that the proposed method can obtain high classification accuracy using LiDAR data alone (e.g., more than 86% overall accuracy on the benchmark Houston LiDAR data using the standard set of training and test samples on all 15 classes) in a short CPU processing time.