Ground point extraction by iterative labeling of airborne LiDAR data in a forested area

Abstract

Given that the distribution of trees is irregular and individual trees differ from one another, applying a Digital Terrain Model (DTM) for cityscapes to a forest inventory causes many errors. In this study, a new DTM-generating technique that utilizes airborne Light Detection And Ranging (LiDAR), with iterative labeling for recovery of ground points, is proposed to solve the inaccuracy problem that occurs when DTMs are generated in forested areas. The proposed method consists of three steps: (1) generation of the initial DTM by a process that performs mean planar filtering and multireturn filtering, (2) recovery of ground points by iterative labeling through application of a ground extraction filter and limitation conditions, and (3) refinement to create the final DTM. The proposed method was tested at the experimental site with morphological and TerraScan DTM-generating techniques, followed by a visual assessment and a quantitative accuracy assessment through comparison with in-situ data. In the visual assessment, the proposed method exhibits such advantages as less noise and more precise representation of topographic features. Also, the method shows excellent performance in improving the average absolute deviation values of 110.3 cm and 50.4 cm over the morphological method and the TerraScan method, respectively, in the quantitative assessment. Thus, the proposed method is judged to have successfully solved the inaccuracy problem that often occurs with generation of DTMs for a forested area.