Tree Branch Skeleton Extraction from Drone-Based Photogrammetric Point Cloud

Calculating the complex 3D traits of trees such as branch structure using drones/unmanned aerial vehicles (UAVs) with onboard RGB cameras is challenging because extracting skeletons from image-generated sparse point clouds remains difficult. This paper proposes a skeleton extraction algorithm for cloud generated by UAV images photogrammetry. We conducted comparison experiment flying two altitudes (50 m and 20 m) above university orchard several fruit tree species developed three metrics, namely F1-score bifurcation (FBP), end (FEP), Hausdorff distance (HD) to evaluate performance proposed algorithm. The results show that average values FBP, FEP, HD branches collected at 50 altitude were 64.15%, 69.94%, 0.0699, respectively, those 83.24%, 84.66%, 0.0474, respectively. provides method low-cost digital management orchards, which can effectively extract main cloud, assist in analyzing growth state different types trees, has certain practical application value orchards.