Abstract
Impact of neighbourhood selection methods on mobile LiDAR data classification using machine learning algorithms
Highlights
A part of Paris-Lille-3D benchmark, which is available at http://npm3d.fr/paris-lille-3d, was used to evaluate the three neighbourhood selection methods
Cylindrical neighbourhood selection method provides the highest overall accuracy of the three methods by 92.4%, 78.5%, and 78.2% for RF, GNB, and QDA, respectively
Summary
The study area of this research is a road located in Lille, France. A part of Paris-Lille-3D benchmark, which is available at http://npm3d.fr/paris-lille-3d, was used to evaluate the three neighbourhood selection methods. Lλ: Linearity Pλ: Planarity Sλ: Scattering e1 − e2 e1
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
