Calculation of Tree Height and Canopy Crown from Drone Images Using Segmentation

Abstract

Drone imaging, which is more cost-effective and controllable compared to airborne LiDAR, requires a lowcost camera and is used for capturing color images. From the overlapped color images, we produced two highresolution digital surface models over different test areas. After segmentation, we performed tree identification according to the method proposed by La et al. (2015), and computed the tree height and the canopy crown size. Compared with the field measurements, the computed results for the tree height in test area 1 (coniferous trees) were found to be accurate, while the results in test area 2 (deciduous coniferous trees) were found to be underestimated. The RMSE of the tree height was 0.84 m, and the width of the canopy crown was 1.51 m in test area 1. Further, the RMSE of the tree height was 2.45 m, and the width of the canopy crown was 1.53 m in test area 2. The experiment results validated the use of drone images for the extraction of a tree structure.