Pruning of Tree Crops through 3D Reconstruction and Light Simulation using Mobile LiDAR

Abstract

Consistent sunlight access is critical when growing fruit crops, and therefore pruning is a vital operation for tree management as it can be used for controlling shading within and between trees. This thesis focuses on using Light Detection And Ranging (LiDAR) to understand and improve the light distribution of fruit trees. To enable commercial applications, the tools developed aim to provide insights on every individual tree at whole orchard scale. Since acquisition and labelling of 3D data is difficult at a large scale, a system is developed for simulating LiDAR scans of tree crops for development and validation of techniques using infinite, perfectly-labelled datasets. Furthermore, processing scans at a large scale require rapid and relatively low-cost solutions, but many existing methods for point cloud analysis require a priori information or expensive high quality LiDAR scans. New tools are presented for structural analysis of noisy mobile LiDAR scans using a novel graph-search approach which can operate on unstructured point clouds with significant overlap between trees. The light available to trees is important for predicting future growth and crop yields as well as making pruning decisions, but many measurement techniques cannot provide branch-level analysis, or are difficult to apply on a large scale. Using mobile LiDAR, which can easily capture large areas, a method is developed to estimate the light available throughout the canopy. A study is then performed to demonstrate the viability of this approach to replace traditional agronomic methods, enabling large-scale adoption. The main contribution of this thesis is a novel framework for suggesting pruning decisions to improve light availability of individual trees. A full-tree quality metric is proposed and branch-scale light information identifies underexposed areas of the tree to suggest branches whose removal will improve the light distribution. Simulated tree scans are then used to validate a technique for estimating matter removed from the point cloud given specific pruning decisions, and this is used to quantify the improvement of real tree scans. The findings of this iv ABSTRACT v thesis demonstrate the value and application of mobile LiDAR in tree crops, and the tools developed through this work promise usefulness in scientific and commercial contexts.