Obscured Tree Branches Segmentation and 3D reconstruction using Deep Learning and Geometrical Constraints

Congratulations to Eugene and the co-authors on the acceptance of “Obscured Tree Branches Segmentation and 3D reconstruction using Deep Learning and Geometrical Constraints” by the Journal of  Computers and Electronics in Agriculture!  This work presented a novel framework that reconstructs and recovers 3D obscured branches from planar images and depth maps captured by an RGB-D camera. The framework comprises three parts: branch segmentation using Unet++, branch reconstruction using Point2Skeleton and branch recovery using a novel obscured branch recovery (OBR) algorithm. The experimental results in the orchard environment have shown promising branch reconstruction and recovery for obscured branches. For details, please find https://www.sciencedirect.com/science/article/pii/S0168169923002727