| LIDAR is a useful tool for quickly digitalizing real world objects, but it usually takes some effort to produce a recognizable object from the raw input. When the object is a tree, the challenge is to create a three-dimensional model that represents its general shape, while avoiding the influence of undersampling and noise. In the method developed for this research, the user creates a sketch overlaying a display of the raw input data. Each node in the sketch creates an estimated slice of the tree skeleton at that point, and the slices are connected according to the connectivity of the sketch. Both user-guided and automated sketches are tested. Analysis is performed by simulating the LIDAR scan process on pre-existing three-dimensional tree models, and then comparing the surface of the reconstruction to that of the original. The results of the method are presented on scans of both synthetic and real trees. It is shown that the output meshes follow the general shapes of the trees, although the influence of undersampling and noise can still be found. |
