3D based Classification of Urban Area using Height and Density Information of LiDAR

Sung-Eun Jung* ･Woo-Kyun Lee** ･Doo-Ahn Kwak*** ･Hyun-Ah Choi****

 

ABSTRACT 

 LiDAR, unlike satellite imagery and aerial photographs, which provides irregularly distributed three-dimensional coordinates of ground surface, enables three-dimensional modeling.
In this study, urban area was classified based on 3D information collected by LiDAR. Morphological and spatial properties are determined by the ratio of ground and non-ground point that are estimated with the number of ground reflected point data of LiDAR raw data. With this information, the residential and forest area could be classified in terms of height and density of trees. The intensity of the signal is distinguished by a statistical method, Jenk’s Natural Break. Vegetative area (high or low density) and non-vegetative area (high or low density) are classified with reflective ratio of ground surface.
Keywords : LiDAR, Land Cover Classification, GRR, Remote Sensing, Ecological Urban Plan, 3D