Assigning apples to individual trees in dense orchards using 3D colour point clouds

We propose a 3D colour point cloud processing pipeline to count apples on individual apple trees in trellis structured orchards. Fruit counting at the tree level requires separating trees, which is challenging dense employ clouds acquired from leaf-off orchard winter period, where branch structure visible, delineate crowns. localise harvest period. Alignment of two enables mapping locations delineated and assigning each its bearing tree. Our assignment method achieves an accuracy rate higher than 95%. In addition presenting first proof feasibility, we also provide suggestions for further improvement our pipeline.