Unmanned aerial vehicle based measurement of urban forests

Abstract

Urban forests are dynamic and change in response to both human and natural forces. To effectively monitor and manage urban forests, periodic inventories are needed to ensure that information about them is current and comprehensive. This task has traditionally been accomplished by manual ground-based field surveys, or more recently using GIS techniques utilizing remote sensing products, especially lidar. Low-cost Unmanned Aerial Vehicles (UAVs) employing Structure from Motion (SfM) techniques have the potential to augment these sources for urban forest inventories. We present the results of an analysis of approximately 1000 urban trees and compare accuracy in the measurement of tree heights and diameters from manual measurements, lidar, and Structure from Motion (SfM) from UAV-based imaging. Results indicate that in an urban environment, the SfM method produces estimates of tree height (R2 = 0.96; RMSE =1.91 m) and diameter (R2 = 0.98; RMSE =3 cm) comparable to manual field measurement, and better than those derived from conventional aerial lidar. In addition, the gains in accuracy from SfM come largely from younger, smaller trees that are often poorly imaged with lidar.