Robust smooth fitting method for LIDAR data using weighted adaptive mapping LS-SVM

Abstract

In many spatial analyses and visualizations related to terrain, a high resolution and accurate digital surface model (DSM) is essential. To develop a robust interpolation and smoothing solutions for airborne light detection and ranging (LIDAR) point clouds, we introduce the weighted adaptive mapping LS-SVM to fit the LIDAR data. The SVM and the weighted LS-SVM are introduced to generate DSM for the sub-region in the original LIDAR data, and the generated DSM for this region is optimized using the points located within this region and additional points from its neighborhood. The fitting results are adaptively optimized by the local standard deviation and the global standard deviation, which decide whether the SVM or the weighted LS-SVM is applied to fit the sub-region. The smooth fitting results on synthesis and actual LIDAR data set demonstrate that the proposed smooth fitting method is superior to the standard SVM and the weighted LS-SVM in robustness and accuracy.