LAUSR

Individual tree segmentation in forest scenes provides a foundation for forest ecosystem modeling and biodiversity assessment applications. Existing approaches work well for cases where trees do not grow in layers. However, they may fail in the scenario with understory vegetation occlusion and heavily overlapped crowns. In this article, we propose a two-stage solution for individual tree segmentation. This method combines a semantic segmentation module and an instance segmentation module. In the first stage, the semantic segmentation network classifies the point clouds into tree and nontree points. In the second stage, the instance segmentation module is utilized by incorporating object detection and postprocessing refinement. The combination of semantic network and object detection network roughly extracts trees, filters out the understory vegetation that affects the extraction of small trees, and improves the extraction probability of small trees. Meanwhile, the method of object detection extraction trees can solve tree extraction omissions due to unclear stems. For the overlap crown, first, object detection limits the border of the tree crown of an individual tree, and further segmentation was implemented by refining clustering. Experiments show that our method solves the above-mentioned problems and achieves state-of-the-art completeness and mean accuracy performances on benchmark datasets.