Automation of dormant pruning in specialty crop production: An adaptive framework for automatic reconstruction and modeling of apple trees

Dormant pruning is one of the most costly and labor-intensive operations in specialty crop production. During winter, a large crew of trained seasonal workers has to carefully remove the branches from hundreds of trees using a set of pre-defined rules. The goal of automatic pruning is to reduce this dependence on a large workforce that is currently needed for the job. Automatically applying the pruning “rules” entails construction of 3D models of the trees in their dormant condition (that is, without foliage) and accurate estimation of the pruning points on the branches. This paper investigates the use of Skeleton-based Geometric (SbG) features in a 3D reconstruction scheme. The results obtained demonstrate the effectiveness of the SbG features for automatic reconstruction using only two views - the front and the back. Our results show that our proposed scheme locates the pruning points on the tree branches with an accuracy of 96.0%. The algorithm that locates the pruning points is based on a new adaptive circle-based-layer-aware modeling scheme for the trunks and the primary branches “PBs” of the trees. Its three main steps are detection, segmentation, and modeling. Localization of the pruning points on the tree branches is a part of the modeling step. Both qualitative and quantitative evaluation are performed on a new challenging apple-trees dataset that is collected for the purpose of evaluating our approach.