时变曲面一致性骨骼提取

doi:10.11772/j.issn.1001-9081.2014.10.3004

计算机应用 ›› 2014, Vol. 34 ›› Issue (10): 3004-3008.DOI: 10.11772/j.issn.1001-9081.2014.10.3004

时变曲面一致性骨骼提取

逄志强,朱碧颖

武汉大学计算机学院，武汉 430072

收稿日期:2014-04-23 修回日期:2014-05-29 发布日期:2014-10-30 出版日期:2014-10-01
通讯作者: 逄志强
作者简介:逄志强(1989-)，男，山东青岛人，硕士研究生，CCF会员，主要研究方向：计算机图形学、虚拟现实；朱碧颖(1990-)，女，北京人，硕士研究生，主要研究方向：计算机图形学、数据挖掘。

Coherent skeleton extraction for time varying surfaces

p zqZHU Biying²

Received:2014-04-23 Revised:2014-05-29 Online:2014-10-30 Published:2014-10-01
Contact: p zq

摘要/Abstract

摘要：

针对提取时变曲面骨骼效率低下且骨骼序列不一致的问题，提出一种基于传播的策略使用配准算法修复初始不完整骨骼，从而提取时变曲面骨骼的方法。首先，提取时变曲面一些关键帧的完整骨骼，另外直接提取关键帧之间曲面的骨骼序列；然后，利用设计出的全局骨骼配准方法，将关键帧骨骼形变到其邻居骨骼；最后，将形变后的关键帧骨骼信息转移到邻居骨骼，从而产生一个新的完整骨骼。对整个骨骼序列执行该操作，以提取完整骨骼。实验结果表明，该方法高效、准确，且该系统可以应用到未经处理的扫描产生的动态几何数据上，这些数据往往包含着大量的噪声点、奇异点和大块的缺失数据，但仍能较快获得一致性骨骼序列。

Abstract:

Concerning the low efficiency and non-coherency in extracting skeletons of time varying surfaces, a new method through applying a registration based propagation strategy to repair the incomplete initial skeletons was proposed in this paper. Firstly, complete skeletons for the key frames of the time varying surfaces were extracted, the initial skeleton series for the surfaces between the key frames were directly extracted. Then a global skeleton alignment method was designed and used to warp key skeleton to its neighboring skeletons. Finally, the information of the warped key skeleton was transferred to its neighboring skeletons, and a complete skeleton was produced. The entire skeleton series were processed by this process to produce complete skeletons. The experimental results show that this system is efficient and accurate. This system can be applied to the raw scanned dynamic geometry data with significant noise, outliers, and large areas of missing data, but still can receive time coherent skeleton series.

中图分类号:

TP391.41

逄志强朱碧颖. 时变曲面一致性骨骼提取[J]. 计算机应用, 2014, 34(10): 3004-3008.

p zq ZHU Biying. Coherent skeleton extraction for time varying surfaces[J]. Journal of Computer Applications, 2014, 34(10): 3004-3008.

参考文献

［1］LI X, WOON T W, TAN T S, et al.Decomposing polygon meshes for interactive applications ［C］// Proceedings of the 2001 Symposium on Interactive 3D Graphics. New York: ACM, 2001:35-42.
［2］XU X, WU Z, ZHOU M, et al.Modeling and animation of 3D characters with ball B-splines ［J］. Journal of Computer Applications, 2009,29(8):2053-2055.(徐欣,武仲科,周明全,等.基于球B样条的3D人物角色建模与动画［J］.计算机应用,2009,29(8):2053-2055.) ［3］JI Z, ZHANG J. Programmable GPU technology in skeletal animations and their comparison ［J］. Computer Engineering and Design, 2008,29(21):5550-5554.(季卓尔,张景峤.基于可编程图形处理器的骨骼动画算法及其比较［J］.计算机工程与设计,2008,29(21):5550-5554.)
［4］KIM J, POLLARD N S. Fast simulation of skeleton-driven deformable body characters ［J］. ACM Transactions on Graphics, 2011,30(5):Artical No.121.
［5］PAN H, XIAO J, WU F, et al.3D human motion retrieval based on key-frames ［J］. Journal of Computer-Aided Design and Computer Graphics, 2009,21(2):214-222.(潘红,肖俊,吴飞,等.基于关键帧的三维人体运动检索［J］.计算机辅助设计与图形学学报,2009,21(2):214-222.)
［6］CHEN H, LIU C, LI F, et al.Motion simulation method for video ［J］. Journal of System Simulation, 2009,21(19): 6131-6134.(陈红倩,刘陈,李凤霞,等.一种视频运动仿真方法［J］.系统仿真学报,2009,21(19):6131-6134.)
［7］CORNEA N D, SILVER D, MIN P. Curve-skeleton properties, applications, and algorithms ［J］. IEEE Transactions on Visualization and Computer Graphics, 2007,13(3):530-548.
［8］MA C-M, WAN S-Y, LEE J-D. Three-dimensional topology preserving reduction on the 4-subfields ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(12):1594-1605.
［9］WANG Y S, LEE T Y. Curve-skeleton extraction using iterative least squares optimization ［J］. IEEE Transactions on Visualization and Computer Graphics, 2008,14(4):926-936.
［10］MALANDAIN G, FERNNDEZ-VIDAL S. Euclidean skeletons ［J］. Image and Vision Computing, 1998,16(5):317-327.
［11］CHUANG J H, AHUJA N, LIN C C, et al.A potential-based generalized cylinder representation ［J］. Computers and Graphics, 2004,28(6):907-918.
［12］AU O K C, TAI C L, CHU H K, et al.Skeleton extraction by mesh contraction ［J］. ACM Transactions on Graphics, 2008,27(3):Artical No.44.
［13］SHARF A, LEWINER T, SHAMIR A, et al.On-the-fly curve-skeleton computation for 3D shapes ［J］. Computer Graphics Forum, 2007,26(3):323-328.
［14］CAO J, TAGLIASACCHI A, OLSON M, et al.Point cloud skeletons via Laplacian based contraction ［C］// Proceedings of the 2010 Shape Modeling International Conference. Piscataway: IEEE Press, 2010:187-197.
［15］TAGLIASACCHI A, ZHANG H, COHEN-OR D. Curve skeleton extraction from incomplete point cloud ［J］. ACM Transactions on Graphics, 2009,28(3):Artical No.71.
［16］HUANG H, WU S, COHEN-OR D, et al.L1-medial skeleton of point cloud ［J］. ACM Transactions on Graphics, 2013,32(4):Artical No.65.
［17］ZHENG Q, SHARF A, TAGLIASACCHI A, et al.Consensus skeleton for non-rigid space-time registration ［J］. Computer Graphics Forum, 2010,29(2):635-644.
［18］SUMNER R W, SCHMID J, PAULY M. Embedded deformation for shape manipulation ［J］. ACM Transactions on Graphics, 2007,26(3):Artical No.80.
［19］LI H, ADAMS B, GUIBAS L J, et al.Robust single-view geometry and motion reconstruction ［J］. ACM Transactions on Graphics, 2009,28(5):Artical No.175.
［20］LI H, LUO L, VLASIC D, et al.Temporally coherent completion of dynamic shapes ［J］. ACM Transactions on Graphics, 2012,31(1):Artical No.2.
［21］SHARF A, ALCANTARA D A, LEWINER T, et al.Space-time surface reconstruction using incompressible flow ［J］. ACM Transactions on Graphics, 2008,27(5):Artical No.110.
［22］GRASSIA F S. Practical parameterization of rotations using the exponential map ［J］. Journal of Graphics Tools, 1998,3(3):29-48.

[1]	张佳慧李晓明张嘉祥. 强化形态感知的路面缺陷检测算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[2]	况世雄姚俊波陆佳炜王琪冰肖刚. 基于动态图卷积网络的电梯乘客异常行为数据增强方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[3]	康斌陈斌王俊杰李昱林赵军智咸伟志. 基于多粒度共享语义中心关联的文本到人物检索方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[4]	王子怡李卫军刘雪洋丁建平刘世侠苏易礌. 基于Swin Transformer与多尺度特征融合的图像描述方法#br# [J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[5]	付可意, 王高才, 邬满. 基于改进区域提议网络和特征聚合小样本目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3790-3797.
[6]	庞玉东, 李志星, 刘伟杰, 李天昊, 王宁宁. 基于改进实时检测Transformer的塔机上俯视场景小目标检测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3922-3929.
[7]	赵欣, 李鑫杰, 徐健, 刘步云, 毕祥. 基于卷积神经网络与Transformer并行的医学图像配准模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3915-3921.
[8]	颜承志陈颖钟凯高寒. 基于多尺度网络与轴向注意力的3D目标检测算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[9]	王静刘嘉星宋婉莹薛嘉兴丁温欣. 基于空间变换和特征分布校准的小样本皮肤图像分类模型[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[10]	廖炎华鄢元霞潘文林. 基于YOLOv9的交通路口图像的多目标检测算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[11]	谢斌红剌颖坤张英俊张睿. 自步学习指导下的半监督目标检测框架[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[12]	胡立华, 李小平, 胡建华, 张素兰. 基于四叉树先验辅助的多视图立体方法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3556-3564.
[13]	顾聪, 段其强, 任思雨. 基于上下文感知网络的息肉分割算法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3617-3622.
[14]	邹耀斌, 张彬. 四向加权香农熵最大化导向的自动阈值分割方法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3565-3573.
[15]	刘涛, 鞠事宏, 高一萌. 基于改进YOLOv8n的无人机视角下小目标检测算法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3603-3609.

时变曲面一致性骨骼提取

Coherent skeleton extraction for time varying surfaces

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics