SimTreeLS: Simulating aerial and terrestrial laser scans of trees

Abstract

There are numerous emerging applications for digitizing trees using terrestrial and aerial laser scanning, particularly in the fields of agriculture and forestry. Interpretation of LiDAR point clouds is increasingly relying on data-driven methods (such as supervised machine learning) that rely on large quantities of hand-labelled data. As this data is potentially expensive to capture, and difficult to clearly visualise and label manually, a means of supplementing real LiDAR scans with simulated data is becoming a necessary step in realising the potential of these methods. We present an open source tool, SimTreeLS (Simulated Tree Laser Scans), for generating point clouds which simulate scanning with user-defined sensor, trajectory, tree shape and layout parameters. Upon simulation, material classification is kept in a pointwise fashion so leaf and woody matter are perfectly known, and unique identifiers separate individual trees, foregoing post-simulation labelling. This allows for an endless supply of procedurally generated data with similar characteristics to real LiDAR captures, which can then be used for development of data processing techniques or training of machine learning algorithms. To validate our method, we compare the characteristics of a simulated scan with a real scan using similar trees and the same sensor and trajectory parameters. Results suggest the simulated data is significantly more similar to real data than a sample-based control. We also demonstrate application of SimTreeLS on contexts beyond the real data available, simulating scans of new tree shapes, new trajectories and new layouts, with results presenting well. SimTreeLS is available as an open source resource built on publicly available libraries.

A procedure for automated tree pruning suggestion using LiDAR scans of fruit trees

“…Prior to the processes described in this section, we isolate each tree using ground detection and the segmentation procedure presented by Westling et al (2020c). Separately, we generate simulated LiDAR scans of trees using Westling et al (2020a) for ground truth analysis of our pruning simulator, so that we could know exactly where the cut points are and what effect it had on the tree. To acquire perfectly labelled pruning data for ground truth, we manually "pruned" several trees at the mesh stage and then simulate the LiDAR scan so we have virtual scans before and after pruning for between 1 and 6 limbs removed.…”

“…Our real data for pruning was noisy, with several operations taking place at once and no clear definition as to where cuts were taking place. Instead, we tested our pruning simulator by using the "SimTreeLS" LiDAR simulator presented by Westling et al (2020a) to generate point clouds for which we can perfectly define removal of matter. Three unique tree models were generated to roughly match the structural characteristics of avocado trees, and then 4 cut points were specified manually for each tree, chosen to remove one major limb with each cut.…”

“…Here we present a method for non-destructive analysis of the impact of pruning decisions, specifically on the immediate light distribution characteristics on a 3D point cloud model of individual trees as captured by a handheld laser scanner. Due to the difficulty of capturing real-world data during pruning and tracking commercial pruning decisions, we develop a virtual tree data set using the SimTreeLS system presented by Westling et al (2020a) which can be used to produce realistic LiDAR data upon which pruning analysis can be conducted, though we demonstrate the ability to transfer the method to real data.…”