A Review of Tree Species Classification Based on Airborne LiDAR Data and Applied Classifiers

Abstract

Remote sensing techniques, developed over the past four decades, have enabled large-scale forest inventory. Light Detection and Ranging (LiDAR), as an active remote sensing technology, allows for the acquisition of three-dimensional point clouds of scanned areas, as well as a range of features allowing for increased performance of object extraction and classification approaches. As many publications have shown, multiple LiDAR-derived metrics, with the assistance of classification algorithms, contribute to the high accuracy of tree species discrimination based on data obtained by laser scanning. The aim of this article is to review studies in the species classification literature which used data collected by Airborne Laser Scanning. We analyzed these studies to figure out the most efficient group of LiDAR-derived features in species discrimination. We also identified the most powerful classification algorithm, which maximizes the advantages of the derived metrics to increase species discrimination performance. We conclude that features extracted from full-waveform data lead to the highest overall accuracy. Radiometric features with height information are also promising, generating high species classification accuracies. Using random forest and support vector machine as classifiers gave the best species discrimination results in the reviewed publications.

Estimating Ground Elevation and Vegetation Characteristics in Coastal Salt Marshes Using UAV-Based LiDAR and Digital Aerial Photogrammetry

“…Aircraft are generally preferred to UAVs to survey larger areas rapidly, at the expense of the spatial resolution of the collected datasets [39]. Airborne LiDARs have been widely used to survey coastal wetlands [31,40], and salt meadows [32], as well as for forestry applications [41][42][43][44][45]. Airborne LiDAR had also been coupled with other remote sensing datasets, which lack tridimensionality and adequate spatial resolution to supply this information.…”

IMG2nDSM: Height Estimation from Single Airborne RGB Images with Deep Learning

“…The authors aspired to the idea that the possibility of deriving high-precision digital elevation models from RGB images without expensive equipment and high costs will accelerate global efforts in various application domains that require the geometric analysis of areas and scenes. Such domains include urban planning and digital twins for smart cities [11], tree growth monitoring and forest mapping [12], modeling ecological and hydrological dynamics [60], detecting farmland infrastructures [61], etc. Such lowcost estimations of building heights will allow policymakers to understand the potential revenue of rooftop photovoltaics based on the yearly access to sunshine [62] and law enforcement to verify whether urban/or rural infrastructures comply with the local land registry legislation.…”

“…As described above, the latter dataset had a lower resolution and more inconsistencies, but the model training ignored the vegetation and low-standing objects to its favor. However, despite the associated higher MAE, this behavior of the model with a vegetation height estimation could be beneficial under some circumstances, such as projects that focus on tree counting, monitoring tree growth or tree coverage in an area [12].…”

“…However, these images are predominantly twodimensional (2D) and constitute a poor source of three-dimensional (3D) information, hindering the adequate understanding of vertical geometric shapes and relations within a scene. Ancillary 3D information improves the performance of many GIS tasks and facilitates the development of tasks that require a geometric analysis of the scene, such as digital twins for smart cities [11] and forest mapping [12]. In such cases, the most popular type of this complementary 3D information is the form of a Digital Surface Model (DSM).…”

Random Forest Machine Learning Technique for Automatic Vegetation Detection and Modelling in LiDAR Data

“…RF and object-based classification methods were employed together to extract the distribution map of urban vegetation. [20,21] underlined the efficiency of RF for vegetation detection in forest and urban areas. Huang & Zhu [15] developed an approach for fusing hyperspectral image and LiDAR data based on RF.…”