Automatic acquisition of the canopy volume parameters of the Citrus reticulate Blanco cv. Shatangju tree is of great significance to precision management of the orchard. This research combined the point cloud deep learning algorithm with the volume calculation algorithm to segment the canopy of the Citrus reticulate Blanco cv. Shatangju trees. The 3D (Three-Dimensional) point cloud model of a Citrus reticulate Blanco cv. Shatangju orchard was generated using UAV tilt photogrammetry images. The segmentation effects of three deep learning models, PointNet++, MinkowskiNet and FPConv, on Shatangju trees and the ground were compared. The following three volume algorithms: convex hull by slices, voxel-based method and 3D convex hull were applied to calculate the volume of Shatangju trees. Model accuracy was evaluated using the coefficient of determination (R2) and Root Mean Square Error (RMSE). The results show that the overall accuracy of the MinkowskiNet model (94.57%) is higher than the other two models, which indicates the best segmentation effect. The 3D convex hull algorithm received the highest R2 (0.8215) and the lowest RMSE (0.3186 m3) for the canopy volume calculation, which best reflects the real volume of Citrus reticulate Blanco cv. Shatangju trees. The proposed method is capable of rapid and automatic acquisition for the canopy volume of Citrus reticulate Blanco cv. Shatangju trees.

Purpose Apple tree volume is an important factor in apple quality control and spraying strategies. The measurement is a laborious task because of the complex structure of the apple tree. This study developed a technology for accurately estimating the apple tree volume from unmanned aerial vehicle-based multi-view three-dimensional reconstruction data using a novel concave hull by slices algorithm. Method The CloudCompare software was used to preprocess the 3D data and extract a single tree. The 3D point cloud data of the tree were divided into truncated cone-type small slices of a specific thickness. The area of each slice was calculated using the proposed concave hull by slices algorithm. The tree volume was calculated by summing the volume of slices. The proposed method was verified on ten apple trees by comparing the results obtained using the proposed method with those calculated by two existing methods. ResultsThe proposed method provided the most accurate tree volume, while avoiding the influence of gaps and holes in the tree. The mean absolute percentage error (MAPE) and root mean squared error (RMSE) were 8.07% and 0.55 m 3 , respectively. Conclusion These results indicate that the concave hull by slices method can be used to calculate the tree volume from 3D point cloud data more effectively. Tree volume mapping was achieved by combining the tree volume with the tree position.