针对树木三维重构过程中面临的处理速度慢、重构精度低等问题,提出一种采用激光点云数据的单木骨架三维重构方法。首先,根据点云数据类型确定组合滤波方式,以去除离群点和地面点;其次,采用一种基于内部形态描述子(ISS)和相干点漂移算法(...针对树木三维重构过程中面临的处理速度慢、重构精度低等问题,提出一种采用激光点云数据的单木骨架三维重构方法。首先,根据点云数据类型确定组合滤波方式,以去除离群点和地面点;其次,采用一种基于内部形态描述子(ISS)和相干点漂移算法(CPD)的混合配准算法(Intrinsic Shape-Coherent Point Drift,IS-CPD),以获取单棵树木的完整点云数据;最后,采用Laplace收缩点集和拓扑细化相结合的方法提取骨架,并通过柱体构建枝干模型,实现骨架三维重构。试验结果表明,相比传统CPD算法,研究设计的配准方案精度和执行速度分别提高50%和95.8%,最终重构误差不超过2.48%。研究结果证明可有效地重构单棵树木的三维骨架,效果接近树木原型,为构建林木数字孪生环境和林业资源管理提供参考。展开更多
树木的几何建模在林木性状评价、森林动态经营管理与可视化研究中具有重要意义。现今,从激光雷达(Light Detection And Ranging,LiDAR)数据中重建树体三维模型并精准获取林木空间枝干结构参数是数字林业发展的必然趋势。该研究提出了一...树木的几何建模在林木性状评价、森林动态经营管理与可视化研究中具有重要意义。现今,从激光雷达(Light Detection And Ranging,LiDAR)数据中重建树体三维模型并精准获取林木空间枝干结构参数是数字林业发展的必然趋势。该研究提出了一种深度学习与计算机图形学相融合的树木骨架重建与参数反演方法。该方法以PR107、CATAS 7-20-59、CATAS 8-79三个品种的橡胶树为实验对象,首先,采用背包移动激光雷达获取三个橡胶树品种的样地数据,并通过体素剖分和数据增广策略来构建橡胶树训练样本集。其次,构造由四层特征编码层和特征解码层所组成的点云分类深度学习网络,并包含优化的PointConv模块与不同尺度的特征插值模块,以实现在多尺度条件下,全面考虑点云的全局和局部优化特征,引导网络实现枝叶点云的精确分类。最后,面向分类后的枝干点云,运用计算机图形学的空间连通性算法与圆柱拟合策略,重建树木骨架模型,并自动解决叶子点云与对应的一级枝干归属问题,进而在叶团簇尺度下开展对单株树的精细描述与参数反演。通过对三块橡胶树测试样地的验证和与实测值的比对表明,该研究提出的深度学习网络枝叶分类总体准确率在90.32%以上。骨架重建与叶团簇分析结果显示,PR107品种橡胶树具有较为发散的树冠、最大的分枝夹角和叶团簇体积;CATAS 7-20-59品种橡胶树冠呈花瓶型,分枝夹角和叶团簇体积较小;而CATAS 8-79品种橡胶树尽管胸径最粗,但不耐寒害处于落叶期导致冠积最小。同时,反演得到的橡胶树一级枝干直径与实测值比对为:决定系数R^(2)不低于0.94,均方根误差(Root Mean Square Error,RMSE)小于3.01 cm;主枝干与一级枝干的分枝角为:决定系数R^(2)不低于0.91,均方根误差RMSE不高于4.94°。同时发现橡胶树一级枝干的直径与对应的叶团簇体积呈正相关分布。该研究将人工智能的理论模型应用于林木的激光点云数据处理中,为林木激光点云的智能化分析与处理提供了新颖的解决思路。展开更多
3D modeling of trees in real environments is a challenge in computer graphics and computer vision, since the geometric shape and topological structure of trees are more complex than conventional artificial objects. In...3D modeling of trees in real environments is a challenge in computer graphics and computer vision, since the geometric shape and topological structure of trees are more complex than conventional artificial objects. In this paper, we present a multi-process approach that is mainly performed in 2D space to faithfully construct a 3D model of the trunk and main branches of a real tree from a single range image. The range image is first segmented into patches by jump edge detection based on depth discontinuity. Coarse skeleton points and initial radii are then computed from the contour of each patch. Axis directions are estimated using cylinder fitting in the neighborhood of each coarse skeleton point. With the help of axis directions, skeleton nodes and corresponding radii are computed. Finally, these skeleton nodes are hierarchically connected, and improper radii are modified based on plant knowledge. 3D models generated from single range images of real trees demonstrate the effectiveness of our method. The main contributions of this paper are simple reconstruction by virtue of image storage order of single scan and skeleton computation based on axis directions.展开更多
文摘针对树木三维重构过程中面临的处理速度慢、重构精度低等问题,提出一种采用激光点云数据的单木骨架三维重构方法。首先,根据点云数据类型确定组合滤波方式,以去除离群点和地面点;其次,采用一种基于内部形态描述子(ISS)和相干点漂移算法(CPD)的混合配准算法(Intrinsic Shape-Coherent Point Drift,IS-CPD),以获取单棵树木的完整点云数据;最后,采用Laplace收缩点集和拓扑细化相结合的方法提取骨架,并通过柱体构建枝干模型,实现骨架三维重构。试验结果表明,相比传统CPD算法,研究设计的配准方案精度和执行速度分别提高50%和95.8%,最终重构误差不超过2.48%。研究结果证明可有效地重构单棵树木的三维骨架,效果接近树木原型,为构建林木数字孪生环境和林业资源管理提供参考。
基金This work is supported by the National High Technology Development 863 Program of China under Grant Nos.2006AA01Z301 and 2006AA10Z229the National Natural Science Foundation of China under Grant Nos.60674128,60073007,and 60473110Beijing Municipal Natural Science Foundation under Grant No.4062033.
文摘3D modeling of trees in real environments is a challenge in computer graphics and computer vision, since the geometric shape and topological structure of trees are more complex than conventional artificial objects. In this paper, we present a multi-process approach that is mainly performed in 2D space to faithfully construct a 3D model of the trunk and main branches of a real tree from a single range image. The range image is first segmented into patches by jump edge detection based on depth discontinuity. Coarse skeleton points and initial radii are then computed from the contour of each patch. Axis directions are estimated using cylinder fitting in the neighborhood of each coarse skeleton point. With the help of axis directions, skeleton nodes and corresponding radii are computed. Finally, these skeleton nodes are hierarchically connected, and improper radii are modified based on plant knowledge. 3D models generated from single range images of real trees demonstrate the effectiveness of our method. The main contributions of this paper are simple reconstruction by virtue of image storage order of single scan and skeleton computation based on axis directions.
