Volume I-3
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., I-3, 129-134, 2012
https://doi.org/10.5194/isprsannals-I-3-129-2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., I-3, 129-134, 2012
https://doi.org/10.5194/isprsannals-I-3-129-2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.

  20 Jul 2012

20 Jul 2012

A COMPARITIVE STUDY USING GEOMETRIC AND VERTICAL PROFILE FEATURES DERIVED FROM AIRBORNE LIDAR FOR CLASSIFYING TREE GENERA

C. Ko1, G. Sohn1, and T. K. Remmel2 C. Ko et al.
  • 1Department of Earth & Space Science & Engineering, York University, Toronto, Ontario, Canada
  • 2Department of Geography, York University, Toronto, Ontario, Canada

Keywords: LiDAR, tree genera, classification, Random Forest, feature selection, vertical profile

Abstract. We present a comparative study between two different approaches for tree genera classification using descriptors derived from tree geometry and those derived from the vertical profile analysis of LiDAR point data. The different methods provide two perspectives for processing LiDAR point clouds for tree genera identification. The geometric perspective analyzes individual tree crowns in relation to valuable information related to characteristics of clusters and line segments derived within crowns and overall tree shapes to highlight the spatial distribution of LiDAR points within the crown. Conversely, analyzing vertical profiles retrieves information about the point distributions with respect to height percentiles; this perspective emphasizes of the importance that point distributions at specific heights express, accommodating for the decreased point density with respect to depth of canopy penetration by LiDAR pulses. The targeted species include white birch, maple, oak, poplar, white pine and jack pine at a study site northeast of Sault Ste. Marie, Ontario, Canada.