Abstract
Forests play a key role in terrestrial ecosystems, and the variables extracted from single trees can be used in various fields and applications for evaluating forest production and assessing forest ecosystem services. In this study, we developed an automated hierarchical single-tree segmentation approach based on the high density three-dimensional (3D) Unmanned Aerial Vehicle (UAV) point clouds. First, this approach obtains normalized non-ground UAV points in data preprocessing; then, a voxel-based mean shift algorithm is used to roughly classify the non-ground UAV points into well-detected and under-segmentation clusters. Moreover, potential tree apices for each under-segmentation cluster are obtained with regard to profile shape curves and finally input to the normalized cut segmentation (NCut) algorithm to segment iteratively the under-segmentation cluster into single trees. We evaluated the proposed method using datasets acquired by a Velodyne 16E LiDAR system mounted on a multi-rotor UAV. The results showed that the proposed method achieves the average correctness, completeness, and overall accuracy of 0.90, 0.88, and 0.89, respectively, in delineating single trees. Comparative analysis demonstrated that our method provided a promising solution to reliable and robust segmentation of single trees from UAV LiDAR data with high point cloud density.
Highlights
Forests play a key role in the terrestrial ecosystem and have a large amount of economic, ecological, and social benefits because they regulate the water cycle and carbon cycle on the surface of the Earth [1]
To obtain single trees segmented from Unmanned Aerial Vehicle (UAV) light detection and ranging (LiDAR) data, our proposed approach includes the following steps: (1) data preprocessing, which first separates ground points from non-ground points and normalizes the UAV LiDAR data according to the produced digital terrain model (DTM) from the filtered ground points, (2) a voxel-based mean shift method, which voxelizes and roughly segments non-ground points into well-detected and under-segmentation clusters, and (3) an improved normalized cut segmentation method, based on a tree apex detection strategy, which iteratively identifies single trees from the under-segmentation clusters that contain multiple overlapped trees
Before we investigated the applicability and feasibility of the proposed single-tree segmentation method, several parameters were empirically selected in advance, according to prior acknowledge of the UAV LiDAR data and the test site
Summary
Forests play a key role in the terrestrial ecosystem and have a large amount of economic, ecological, and social benefits because they regulate the water cycle and carbon cycle on the surface of the Earth [1]. LiDAR technology can improve the accuracy of forest parameter retrieval at the single-tree level because of its capability of providing accurate and spatially detailed information of tree structure elements (such as branches and foliage) [14]. Airborne LiDAR is considered to be a standard data source for deriving forest spectral and spatial information at the scale of single trees because it provides timely, large-scale, and accurate forest information to support forest management. Matasci et al [2] demonstrated that the integration of airborne LiDAR and Landsat-derived reflectance products predicted a total of 10 forest structural attributes by using a nearest neighbor imputation approach based on the random forest framework, with R2 values ranging from 0.49–0.61 for key response variables such as canopy cover, stand height, basal area, and stem volume. It is still difficult to detect single trees automatically from airborne LiDAR data due to the various shapes of trees and their periodic changes with the seasons, especially to segment trees with complex and heterogeneous crowns
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
