Hybrid Ensemble Classification of Tree Genera Using Airborne LiDAR Data

Remote Sensing

Connie Ko⁴  Gunho Sohn¹  Tarmo K. Remmel³  John Miller²  Nicolas Baghdadi⁵ 

[1] Department of Earth and Space Science and Engineering, York University, 4700 Keele Street, Petrie Building 149, Toronto, ON M3J 1P3, Canada; E-Mail:;Department of Earth and Space Science and Engineering, York University, 4700 Keele Street, Petrie Building 318, Toronto, ON M3J 1P3, Canada; E-Mail:;Department of Geography, York University, 4700 Keele Street, Ross North 430, Toronto, ON M3J 1P3, Canada; E-Mail:;Department of Earth and Space Science and Engineering, York University, 4700 Keele Street, Ross North 430, Toronto, ON M3J 1P3, Canada;id="af1-remotesensing-06-11225">1Department of Earth and Space Science and Engineering, York University, 4700 Keele Street, Ross North 430, Toronto, ON M3J 1P3, Cana

关键词: LiDAR;    ensemble classification;    tree genera;    Random Forests;   

DOI  :  10.3390/rs61111225

来源: mdpi

【 摘 要 】

This paper presents a hybrid ensemble method that is comprised of a sequential and a parallel architecture for the classification of tree genus using LiDAR (Light Detection and Ranging) data. The two classifiers use different sets of features: (1) features derived from geometric information, and (2) features derived from vertical profiles using Random Forests as the base classifier. This classification result is also compared with that obtained by replacing the base classifier by LDA (Linear Discriminant Analysis), kNN (k Nearest Neighbor) and SVM (Support Vector Machine). The uniqueness of this research is in the development, implementation and application of three main ideas: (1) the hybrid ensemble method, which aims to improve classification accuracy, (2) a pseudo-margin criterion for assessing the quality of predictions and (3) an automatic feature reduction method using results drawn from Random Forests. An additional point-density analysis is performed to study the influence of decreased point density on classification accuracy results. By using Random Forests as the base classifier, the average classification accuracies for the geometric classifier and vertical profile classifier are 88.0% and 88.8%, respectively, with improvement to 91.2% using the ensemble method. The training genera include pine, poplar, and maple within a study area located north of Thessalon, Ontario, Canada.

【 授权许可】

CC BY   
© 2014 by the authors; licensee MDPI, Basel, Switzerland.