Estimating Forest Structure from UAV-Mounted LiDAR Point Cloud Using Machine Learning

Abstract

Monitoring the structure of forest stands is of high importance for forest managers to help them in maintaining ecosystem services. For that purpose, Unmanned Aerial Vehicles (UAVs) open new prospects, especially in combination with Light Detection and Ranging (LiDAR) technology. Indeed, the shorter distance from the Earth’s surface significantly increases the point density beneath the canopy, thus offering new possibilities for the extraction of the underlying semantics. For example, tree stems can now be captured with sufficient detail, which is a gateway to accurately locating trees and directly retrieving metrics—e.g., the Diameter at Breast Height (DBH). Current practices usually require numerous site-specific parameters, which may preclude their use when applied beyond their initial application context. To overcome this shortcoming, the machine learning Hierarchical Density-Based Spatial Clustering of Application of Noise (HDBSCAN) clustering algorithm was further improved and implemented to segment tree stems. Afterwards, Principal Component Analysis (PCA) was applied to extract tree stem orientation for subsequent DBH estimation. This workflow was then validated using LiDAR point clouds collected in a temperate deciduous closed-canopy forest stand during the leaf-on and leaf-off seasons, along with multiple scanning angle ranges. The results show that the proposed methodology can correctly detect up to 82% of tree stems (with a precision of 98%) during the leaf-off season and have a Maximum Scanning Angle Range (MSAR) of 75 degrees, without having to set up any site-specific parameters for the segmentation procedure. In the future, our method could then minimize the omission and commission errors when initially detecting trees, along with assisting further tree metrics retrieval. Finally, this research shows that, under the study conditions, the point density within an approximately 1.3-meter height above the ground remains low within closed-canopy forest stands even during the leaf-off season, thus restricting the accurate estimation of the DBH. As a result, autonomous UAVs that can both fly above and under the canopy provide a clear opportunity to achieve this purpose.

Estimating Canopy Density Parameters Time-Series for Winter Wheat Using UAS Mounted LiDAR

“…In contrast to typical passive multispectral methods, light detection and ranging (Li-DAR) can retrieve signals from the canopy, the whole plant, and the ground. LiDAR's ability to penetrate through vegetation canopy tops is often used for height measurements, to map underlying terrain, or even to measure tree trunk diameters [26][27][28]. It is also possible to relate the rate at which these signals pass through gaps in the canopy, essentially applying GF principles to LiDAR, that is reflective of vegetation density that can be related to LAI.…”

Under-Canopy UAV Laser Scanning Providing Canopy Height and Stem Volume Accurately

“…An alternative technological solution for the future is an above-canopy flying UAV that can measure the arcs of a tree stem from the above, as first proposed in [37] and recently also partly tested in [38,39]. This requires a small laser beam, a low enough point spacing distance (a high pulse repetition rate) and a low mirror scan speed.…”

3D Point Cloud Data in Conveying Information for Local Green Factor Assessment

“…Both deep learning and machine learning techniques [78] have been tested and deployed in point cloud data analysis, leading to promising results in urban point cloud classification via algorithms, such as random forest [79] and presence and background learning [80], and also via deep-learning architectures, such as SPGraph [81]. Tree attributes, such as canopy and stem surveying-based quantitative methods, have already been widely studied for forestry e.g., [35][36][37]82,83]. For green factor-like evaluations, questions around quality as well as the variety of objects and species arise.…”

“…However, especially in 3D city modeling, the emphasis has traditionally been on buildings, rather than on small-scale natural environments, yards, and their elements. The applications on forestry research have been widely studied from both structural [36][37][38] and individual tree points of view [39][40][41][42][43], including forest inventory and change prediction [44][45][46]. Studies in forestry have also specified levels of detail for a single tree model [47]; however, methods in the field mainly concentrate on tree attributes.…”