[1]张天安,云 挺,薛联凤,等.基于骨架提取的树木主枝干三维重建算法[J].南京师范大学学报(工程技术版),2014,14(04):051.
　Zhang Tianan,Yun Ting,Xue Lianfeng,et al.Three-Dimensional Reconstruction Algorithm of Tree LimbsBased on Skeleton Extraction[J].Journal of Nanjing Normal University(Engineering and Technology),2014,14(04):051.
点击复制

基于骨架提取的树木主枝干三维重建算法
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
14卷
期数:
2014年04期
页码:
051
栏目:
出版日期:
2014-12-31

文章信息/Info

Title:
Three-Dimensional Reconstruction Algorithm of Tree LimbsBased on Skeleton Extraction
作者:
张天安; 云 挺; 薛联凤; 高纪青
南京林业大学信息科学技术学院,江苏 南京 210037
Author(s):
Zhang Tian’an; Yun Ting; Xue Lianfeng; Gao Jiqing
College of Information Science and Technology,Nanjing Forestry University,Nanjing 210037,China
关键词:
三维点云; 骨架提取; Dijkstra距离; 优化模型
Keywords:
3D point cloud; skeleton extraction; Dijkstra distance; optimization model
分类号:
TP391.9
文献标志码:
A
摘要:
为了实现树木主枝干的三维重建,提出了一种基于骨架提取的算法.首先,根据Dijkstra距离对点云数据进行分段.然后,提取出每个连通部分的骨架,并采用线性规划的优化模型求出距离与角度的权值,根据加权后的匹配度进行骨架的连接,得到整株树的完整骨架.最后利用圆柱体拟合出树木枝干的模型,对含笑树和樱花树分别进行了实验,得到了令人满意的实验结果.
Abstract:
In order to achieve the 3D reconstruction of the tree limbs,this paper proposes an algorithm based on skeleton extraction.Firstly,the point cloud data are segmented according to Dijkstra distance.Then,the skeletons of each connected part are extracted.By adopting the linear programming optimization model to calculate the weights of distance and angle,the skeleton is connected according to the matching degree to get a complete skeleton of the whole tree.Finally,the models of sakura’s and michelia’s limbs are reconstructed by fitting the cylinder and the result of the experiment is satisfying.

参考文献/References:

[1] Bremer M,Rutzinger M,Wichmann V.Derivation of tree skeletons and error assessment using LiDAR point cloud data of varying quality[J].ISPRS Journal of Photogrammetry and Remote Sensing,2013,80:39-50.
[2]Li Er,Che Wujun,Zhang Xiaopeng,et al.Direct quad-dominant meshing of point cloud via global parameterization[J].Computers and Graphics,2011,35:452-460.
[3]Jiang Wei,Xu Kai,Cheng Zhiquan,et al.Skeleton-based intrinsic symmetry detection on point clouds[J].Graphical Models,2013,75:177-188.
[4]Liu Hongzhi,Wu Zhonghai,Frank Hsu D,et al.On the generation and pruning of skeletons using generalized Voronoi diagrams[J].Pattern Recognition Letters,2012,33:2 113-2 119.
[5]Shen Wei,Bai Xiang,Hu Rong,et al.Skeleton growing and pruning with bending potential ratio[J].Pattern Recognition,2011,44:196-209.
[6]Wang Sen,Wu Jianhuang,Wei Mingqiang,et al.Robust curve skeleton extraction for vascular structures[J].Graphical Models,2012,74:109-120.
[7]John Chaussard,Michel Couprie,Hugues Talbot.Robust skeletonization using the discrete k-medial axis[J].Pattern Recognition Letters,2011,32:1 384-1 394.
[8]Liu Hongzhi,Wu Zhonghai,Zhang Xing,et al.A skeleton pruning algorithm based on information fusion[J].Pattern Recognition Letters,2013,34:1 138-1 145.
[9]Stelios Krinidis,Michail Krinidis.Empirical mode decomposition on skeletonization pruning[J].Image and Vision Computing,2013,31:533-541.
[10]Sun Zheng,Yan Qi.Motion estimation of 3D coronary vessel skeletons from X-ray angiographic sequences[J].Computerized Medical Imaging and Graphics,2011,35:353-364.

备注/Memo

备注/Memo:
收稿日期:2014-08-16.
基金项目:国家自然科学基金(31300472)、江苏省自然科学基金(BK2012418)、2014科技支撑计划项目(BE2014688).
通讯联系人:云挺,博士,副教授,研究方向:虚拟现实与机器视觉.E-mail:njyunting@qq.com
更新日期/Last Update: 2014-12-31