Surfaces reconstruction of plant leaves based on point cloud data

As one of the most important organs, the high-accuracy plant leaf geometric model contributes to agronomic research such as shape feature exaction and canopy light distribution calculation. This paper proposed a method of surface reconstruction based on 3D scanned point cloud for plant leaves. This method generated the initial surface mesh from the point cloud through Delaunay triangulation after removing the noise points, and an optimization algorithm was applied to eliminate wrong edges. The results show that the proposed method can reconstruct high-quality 3D surface of plant leaf from point cloud data, which is also applicable to complex shapes like wilting and withered leaves.