Nowadays, laser scanning technology has provided an effective andnondestructive approach to reveal the forest's developmental process and physiological properties. For the purpose of obtaining the 3-D spatial structure and skeleton of trees, this article addresses the separation of wood and foliage from the forest using two phases. The first global phase develops a pointwise supervised learning framework to classify forest point clouds. In order to improve the classification accuracy, we design new features for the learning process, which supplements the current geometric features in terms of the topological information. The second local phase designs a new least-cost path model to further separate wood and foliage points. The separation of branch points is formulated as an energy function and optimized by the dynamic programming technique. Experiments on different plots show that points from stems and branches are detected as wood points completely and correctly. The achieved average completeness, correctness, and $F_1$ score of the wood and foliage separation are 91.25%, 90.34%, and 0.91, respectively, which is promising to the phenotyping study related to the organism's physical form and structure.

中文翻译：

---

使用新颖的最低成本路径模型从地面点云分离树木的木材和树叶


如今，激光扫描技术为揭示森林的发育过程和生理特性提供了一种有效、无损的方法。为了获得树木的 3D 空间结构和骨架，本文使用两个阶段来解决从森林中分离木材和树叶的问题。第一个全局阶段开发了一个逐点监督学习框架来对森林点云进行分类。为了提高分类精度，我们为学习过程设计了新的特征，在拓扑信息方面补充了当前的几何特征。第二个局部阶段设计了一个新的最低成本路径模型，以进一步分离木材和树叶点。分支点的分离被公式化为能量函数并通过动态规划技术进行优化。不同样地的实验表明，茎、枝上的点能够完全正确地检测为木材点。木材和叶子分离的平均完整性、正确性和$F_1$得分分别为91.25%、90.34%和0.91，这对于与生物体物理形态和结构相关的表型研究有希望。