三维人体点云模型多约束肢体分割

doi:10.11772/j.issn.1001-9081.2015.03.830

计算机应用 ›› 2015, Vol. 35 ›› Issue (3): 830-834.DOI: 10.11772/j.issn.1001-9081.2015.03.830

三维人体点云模型多约束肢体分割

张翔宇^1,2, 田庆国^1,2, 葛宝臻^1,2

1. 天津大学精密仪器与光电子工程学院, 天津 300072;
2. 光电信息技术教育部重点实验室(天津大学), 天津 300072

收稿日期:2014-10-15 修回日期:2014-11-22 出版日期:2015-03-10 发布日期:2015-03-13
通讯作者: 田庆国
作者简介:张翔宇(1988-),男,河北唐山人,硕士研究生,主要研究方向:三维人体点云模型处理;田庆国(1973-),男,河北唐山人,讲师,博士,主要研究方向:计算机可视化、图像图形学;葛宝臻(1964-),男,内蒙古卓资人,教授,博士,主要研究方向:光电检测与信息处理、激光粒子测量、三维彩色数字成像技术
基金资助:
国家自然科学基金面上项目(61177002)

Multi-constrained segmentation of 3D human point-cloud

ZHANG Xiangyu^1,2, TIAN Qingguo^1,2, GE Baozhen^1,2

1. School of Precision Instruments and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China;
2. Key Laboratory of Opto-Electronics Information and Technical Science of Ministry of Education (Tianjin University), Tianjin 300072, China

Received:2014-10-15 Revised:2014-11-22 Online:2015-03-10 Published:2015-03-13

摘要/Abstract

摘要：

针对人体点云模型的肢体分割这一动作识别和虚拟重建领域的重要问题,提出了一种基于分类骨架线、测地距离、特征点和姿态分析的多约束肢体分割算法,通过生成点云模型的分类骨架线,配合测地距离获得人体各部位粗分割点云集,利用测地路径方法实现关键特征点的定位,并利用曲线拟合方式进行定位优化,针对头颈、上肢、下肢和躯干之间关联部位的解剖学特征,构造多种约束条件,对各部位粗分割点云集进行了优化再分割。实验结果表明,所提算法对站姿条件下的不同动作、不同体型、不同精度人体点云模型均能取得与视觉理解相吻合的分割效果。通过该算法得到的肢体各部分点云数据可用于姿态分析等后续研究。

关键词: 人体点云模型, 点云分割, 测地距离, 姿态分析, 多约束

Abstract:

Body parts segmentation of human point-cloud model is an important research content in action recognition and virtual reconstruction fields. Focused on this issue, a multi-constrained segmentation algorithm based on classified skeleton,geodesic distance, feature points and posture analysis was proposed.By generating the classified skeleton and geodesic distance of point-cloud, the roughly segmented point sets of each body part were got. Feature points were positioned by an algorithm depending on geodesic path and optimized by a curve fit method.According to these feature points and some anatomical features of human body, multiple constraints were constructed and roughly segmented point sets were segmented once again.The experimental results demonstrate that the segmentation effects of human point cloud models with different action, size and precision in standing posture are consistent with visual understanding of human. The point-cloud of body parts obtained through this algorithm can be used for posture analysis and so on.

Key words: human point-cloud model, point-cloud segmentation, geodesic distance, posture analysis, multi-constraint

中图分类号:

TP391.9

张翔宇, 田庆国, 葛宝臻. 三维人体点云模型多约束肢体分割[J]. 计算机应用, 2015, 35(3): 830-834.

ZHANG Xiangyu, TIAN Qingguo, GE Baozhen. Multi-constrained segmentation of 3D human point-cloud[J]. Journal of Computer Applications, 2015, 35(3): 830-834.

参考文献

[1] ZHANG Y, ZHANG X, ZHA H, et al. A survey of topologically structural representation and computation of 3D point cloud data[J]. Journal of Image and Graphics, 2008,13(8):1576-1587.(张义宽,张晓鹏,查红彬,等.3维点云的拓扑结构表征与计算技术[J].中国图象图形学报,2008,13(8):1576-1587.)
[2] XIAO C, FENG J, MIAO Y, et al. Geodesic path computation and region decomposition of point-based surface based on level set method[J].Chinese Journal of Computers, 2005,28(2):250-258.(肖春霞,冯结青,缪永伟,等.基于Level Set方法的点采样曲面测地线计算及区域分解[J].计算机学报,2005,28(2):250-258.)
[3] MA T, LONG X, FENG L, et al. Point cloud segmentation based on spectral clustering[J]. Journal of Computer-Aided Design and Computer Graphics, 2012,24(12):1549-1558.(马腾,龙翔,冯路,等.点云模型的谱聚类分割[J].计算机辅助设计与图形学学报,2012,24(12):1549-1558.)
[4] SUN H, SUN X, LI H. 3D point cloud model segmentation based on K-means cluster analysis[J]. Computer Engineering and Applications, 2006,42(10):42-45.(孙红岩,孙晓鹏,李华.基于 K-means 聚类方法的三维点云模型分割[J].计算机工程与应用,2006,42(10):42-45.)
[5] JIA N. Point cloud data segmentation based on quadric surface approach[D]. Jinan: Shandong University, 2008.(贾宁. 基于二次曲面逼近的点云模型分割[D].济南:山东大学,2008.)
[6] LAI Y-K, HU S-M, Martin R R, et al. Rapid and effective segmentation of 3D models using random walks[J]. Computer Aided Geometric Design, 2009,26(6):665-679.
[7] DU C-J, FERGUSON J G, HAWKINS P T, et al. Fast random walker for neutrophil cell segmentation in 3D[C]//Proceedings of the 2012 9th IEEE International Symposium on Biomedical Imaging. Piscataway: IEEE, 2012:190-193.
[8] KALOGERAKIS E, HERTZMANN A, SINGH K. Learning 3D mesh segmentation and labeling[J]. ACM Transactions on Graphics, 2010,29(4):102.
[9] SUN J, ZHOU L, AN L. Research on point cloud segmentation using a minimum spanning tree[J]. Journal of Image and Graphics, 2012,17(7):858-865.(孙金虎,周来水,安鲁陵.应用最小生成树实现点云分割[J].中国图象图形学报,2012,17(7):858-865.)
[10] WAN Y, TAN L, LONG W, et al. A new segmentation algorithm for 3D colored point cloud based on grid[J]. Journal of Donghua University: Natural Science, 2014,4:481-485.(万燕,谭亮,龙文铮,等.基于网格的三维彩色点云分割算法[J].东华大学学报:自然科学版,2014,4:481-485.)
[11] YAMAZAKI I, NATARAJAN V, BAI Z, et al. Segmenting point sets[C]//Proceedings of the 2006 IEEE International Conference on Shape Modeling and Applications. Piscataway: IEEE, 2006:6.
[12] XIAO Y, SIEBERT P, WERGHI N. A discrete Reeb graph approach for the segmentation of human body scans[C]//Proceedings of the 2003 4th International Conference on 3D Digital Imaging and Modeling. Piscataway: IEEE, 2003:378-385.
[13] GUAN H, GUO L, LI W. A 3D human body segmentation algorithm based on Reeb graph[J]. Communications Technology, 2012,44(11):63-65.(关华,郭立,李文.一种基于Reeb图的3维肢体分割算法[J].通信技术,2012,44(11):63-65.)
[14] WANG C, CHANG T, YUEN M. From laser-scanned data to feature human model: a system based on fuzzy logic concept[J]. Computer-Aided Design, 2003,35(3):241-253.
[15] YAN Y. Research on reconstruction, segmentation and dimension extraction of 3D human model[D]. Zhuzhou: Hunan University of Technology, 2012.(晏义.三维人体模型重建,分割及尺寸提取技术研究[D].株洲:湖南工业大学,2012.)
[16] HOU P, TIAN Q, GE B. Research on method of extracting skeletal curves of 3D human scanning data based on optimizing DRG[J]. Computer Engineering and Applications, 2014,50(18):182-187.(侯培,田庆国,葛宝臻.基于优化DRG的三维人体点云骨架提取方法[J].计算机工程与应用,2014,50(18):182-187.)
[17] DU P, TU C, WANG W. Computing geodesics on point clouds[J]. Journal of Computer-Aided Design and Computer Graphics, 2006,18(3):438-442.(杜培林,屠长河,王文平.点云模型上测地线的计算[J].计算机辅助设计与图形学学报,2006,18(3):438-442.)
[18] CHEN Q, PAN X, ZHANG S. 3D human landmark detection and segmentation with semantic knowledge[J]. Journal of Computer-Aided Design and Computer Graphics, 2011,23(6):1061-1068.(陈启华,潘翔,张三元.语义知识约束的三维人体特征点检测和分割[J].计算机辅助设计与图形学学报,2011,23(6):1061-1068.)
[19] QIAO L, WANG Y, ZENG J. Discussion on methods of curve fitting in experimental data processing[J]. Journal of Chengdu University of Technology: Science and Technology Edition, 2004,31(1):91-95.(乔立山,王玉兰,曾锦光.实验数据处理中曲线拟合方法探讨[J].成都理工大学学报:自然科学版,2004,31(1):91-95.)
[20] CHEN Y. Arts body structural kinematics[M]. Shanghai: Shanghai People's Fine Arts Publishing House, 1984:167-181.(陈聿强.艺用人体结构运动学[M].上海:上海人民美术出版社,1984:161-187.)
[21] LI J. Arts body structural analysis and anatomy[M]. Xi'an: Shaanxi People's Fine Arts Publishing House, 2003:33-151.(李景凯.艺用人体结构形态分析解剖[M].西安:陕西人民美术出版社,2003:33-151.)
[22] GE B, SUN Y. Color 3-D laser scanning digitalization system: China, ZL200510013085.8[P]. 2005-07-27.(葛宝臻,孙宇臣.激光三维彩色扫描数字化方法及数字化仪:中国,ZL200510013085.8[P].2005-07-27.)

三维人体点云模型多约束肢体分割

Multi-constrained segmentation of 3D human point-cloud

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

[1]	郑振涛, 赵卓峰, 王桂玲, 徐垚. 面向港口停留区域识别的船舶停留轨迹提取方法[J]. 计算机应用, 2019, 39(1): 113-117.
[2]	储珺吴侗王璐. 基于体密度变化率的点云多平面检测算法[J]. 计算机应用, 2013, 33(05): 1411-1419.
[3]	鲁萍王玉英. 多约束分级寻优结合预测计算的智能组卷策略[J]. 计算机应用, 2013, 33(02): 342-345.
[4]	邹永贵魏来. 带多约束条件的最优路径选择算法研究[J]. 计算机应用, 2008, 28(5): 1101-1103.
[5]	朱翠涛高靓汪汉新. 多约束QoS移动IP最优路由的求解[J]. 计算机应用, 2007, 27(5): 1180-1182.
[6]	陈立家，周建国，江昊，晏蒲柳. QoS多约束优化路径选择算法[J]. 计算机应用, 2005, 25(04): 900-902.