面向动作捕捉的非线性时间序列预测方法研究

doi:10.16182/j.issn1004731x.joss.201807047

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (7): 2808-2815.doi: 10.16182/j.issn1004731x.joss.201807047

• 短文 • 上一篇

面向动作捕捉的非线性时间序列预测方法研究

黄天羽, 郭芸莹

北京理工大学,北京 100081

收稿日期:2017-10-01 出版日期:2018-07-10 发布日期:2019-01-08
作者简介:黄天羽(1979-),女,山东,博士,副教授,研究方向为虚拟现实、数字表演与仿真、计算机动画等;郭芸莹(1995-),女,云南,硕士生,研究方向为数字表演与仿真、计算机动画等。

Research of Nonlinear Time Series Prediction Method for Motion Capture

Tianyu Huang, Yunying Guo

Beijing Institute of Technology, Beijing 100081, China

Received:2017-10-01 Online:2018-07-10 Published:2019-01-08

摘要/Abstract

摘要： 为研究面向动作捕捉的非线性时间序列预测的方法。通过对人体动作数据进行分析,研究并实现基于动作捕捉数据的预测方法,解决因传感器故障而引起的数据丢失、修正问题。通过模拟实验假设动作序列中某一个传感器发生故障,随后使用8种机器学习方法,利用6种指标进行评估,对比各种方法的预测效果,并将预测后的动作进行可视化。通过实验,随机森林、决策树、最近邻方法对数据的预测准确率能达到90%以上。由此,面向动作捕捉的非线性时间序列预测方法能够准确地还原动作。

关键词: 动作捕捉, 非线性时间序列预测, 机器学习, 性能评估, 动作预测

Abstract: In this paper, we study the nonlinear time series prediction method for action capture. A prediction method based on the capture data is studied and implemented by analyzing human motion data to solve the data loss and correction problem caused by sensor failure. Based on this research purpose, the simulation experiment assumes that a sensor in the sequence of actions fails, then uses eight kinds of machine learning methods, and evaluates them with six indexes. The prediction results of different methods are compared and the predicted motions are visualized. Through the experiments, data prediction accuracy by random forest, decision tree, nearest neighbor (KNN) method can reach more than 90%. Thus, the nonlinear time series prediction method for motion capture can accurately reconstruct the action.

Key words: motion capture, nonlinear time series prediction, machine learning, performance evaluation, action prediction

中图分类号:

TP391.72

黄天羽, 郭芸莹. 面向动作捕捉的非线性时间序列预测方法研究[J]. 系统仿真学报, 2018, 30(7): 2808-2815.

Tianyu Huang, Yunying Guo. Research of Nonlinear Time Series Prediction Method for Motion Capture[J]. Journal of System Simulation, 2018, 30(7): 2808-2815.

参考文献

[1] 纪俐, 姬晓飞. 基于惯性测量系统的人体运动捕捉技术[J]. 计算机工程与设计, 2016, 37(4): 1098-1101.
Ji Li, Ji Xiao-fei.Human motion capture based on inertial measurement system[J]. Computer Engineering and Design, 2016, 37(4): 1098-1101.
[2] 李豪杰, 林守勋, 张勇东. 基于视频的人体运动捕捉综述[J]. 计算机辅助设计与图形学学报, 2006, 18(11): 1645-1651.
Li Haojie, Lin Shouxun, Zhang Yongdong.A Survey of Video Based Human Motion Capture[J]. Journal of Computer-aided Design & Computer Graphics, 2006, 18(11): 1645-1651.
[3] 黄波士, 陈福民. 人体运动捕捉及运动控制的研究[J]. 计算机工程与应用, 2005, 41(7): 60-63.
Huang Boshi, Chen Fumin.Research on Human Body Motion Capture and Motion Control[J]. Computer Engineering and Applications, 2005, 41(7): 60-63.
[4] Murphy M J, Isaakson M, Jalden J.Adaptive filtering to predict lung tumor motion during free breathing[C]//16th International Congress and Exhibition of Comuter Assisted Radiology and Surgery. Springer Berlin Heidelberg, 2002: 539-544.
[5] S Haykin.Neural networks: A comprehensive foundation[M]. New York: Prentice Hall, 2008: 672-730.
[6] 王怡鸥. 基于机器学习的非线性时间序列预测方法研究[D]. 北京: 北京理工大学, 2016.
Wang Yi-Ou.Research on Nonlinear Time Series Prediction Methods Based on Machine Learning [D]. Beijing: Beijing Institute of Technology, 2016.
[7] 魏小鹏, 刘瑞, 张强, 等. 基于模板匹配的人体运动捕捉数据处理方法[J]. 系统仿真学报, 2010, 22(10): 2368-2391.
Wei Xiaopeng, Liu Rui, Zhang Qiang, et al.Apporach of human capture data processing based on template matching[J]. Journal of System Simulation, 2010, 22(10): 2368-2391.
[8] Ju Zhaojie, Liu Honghai. human hand motion analysis with multisensory information[J]. IEEE/ASME Transaction on Mechatronics (S1083-4435), 2014, 19(2): 456-466.
[9] 郭志虎. 基于微惯性全姿态测量的人体运动捕捉系统研究[D]. 上海: 上海交通大学, 2013: 22-31.
Guo Zhihu.The research of human motion capture system based on the micro inertial and wholly-owned state measurement [D] Shanghai: Shanghai Jiao Tong University, 2013: 22-31.
[10] Slyper R, Hodgins J K.Action capture with accelerometers[C]//ACM Siggraph/eurographics Symposium on Computer Animation. Eurographics Association, 2008: 193-199.
[11] Schepers H M, Roetenberg D, Veltink P H.Ambulatory human motion tracking by fusion of inertial and magnetic sensing with adaptive actuation[J]. Medical & Biological Engineering & Computing (S0140-0118), 2010, 48(1): 27-37.
[12] Vlasic D, Adelsberger R, Vannucci G, et al.Practical motion capture in everyday surroundings[J]. Acm Transactions on Graphics (S0730-0301), 2007, 26(3): 35.
[13] Tournier M, Wu X, Courty N, et al.Motion Compression using Principal Geodesics Analysis[J]. Computer Graphics Forum (S0167-7055), 2009, 28(2): 355-364.
[14] Tautges J, Zinke A, Baumann J, et al.Motion reconstruction using sparse accelerometer data[J]. Acm Transactions on Graphics (S0730-0301), 2011, 30(3): 1-12.
[15] Björn Krüger, Tautges J, Weber A, et al.Fast local and global similarity searches in large motion capture databases[C]//Eurographics/acm SIGGRAPH Symposium on Computer Animation, SCA 2010, Madrid, Spain. DBLP, 2010: 1-10.

面向动作捕捉的非线性时间序列预测方法研究

Research of Nonlinear Time Series Prediction Method for Motion Capture

PDF (PC)

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

本文评价

[1]	唐传谦, 刘志强, 苏毅俊, 刘晓静. 基于Kinect的皮影动作实时匹配研究[J]. 系统仿真学报, 2022, 34(3): 633-639.
[2]	张琪, 曾俊杰, 许凯, 秦龙, 尹全军. 基于机器学习的计算机生成兵力行为建模研究综述[J]. 系统仿真学报, 2021, 33(2): 280-287.
[3]	毕振波, 张世友, 杨花, 吴远红. 基于浅层机器学习的视频监控船舶检测综述[J]. 系统仿真学报, 2021, 33(12): 2792-2807.
[4]	刘灏哲, 李伟, 马萍, 杨明. 基于多源先验数据的系统性能评估方法[J]. 系统仿真学报, 2021, 33(11): 2673-2680.
[5]	陈莹, 沈栎. 基于特征回归的单目深度图无标记人体姿态估计[J]. 系统仿真学报, 2020, 32(2): 269-277.
[6]	冯振杰, 樊煜. 混沌时间序列的高斯过程混合模型预测[J]. 系统仿真学报, 2019, 31(7): 1387-1396.
[7]	杨永利, 胡晓峰, 荣明, 殷小静, 王文祥. 基于机器学习的作战体系能力特征指标挖掘[J]. 系统仿真学报, 2019, 31(6): 1048-1054.
[8]	贾立山, 刘喆, 孙毅. 基于RMBP神经网络的飞机电气故障智能诊断[J]. 系统仿真学报, 2018, 30(9): 3493-3501.
[9]	李琦, 户杏启, 赵建敏. 基于机器学习的热源总供热量优化控制[J]. 系统仿真学报, 2018, 30(3): 1134-1143.
[10]	王雨潇, 王松艳, 晁涛, 杨明. 制导控制系统的多准则变权综合评估方法[J]. 系统仿真学报, 2018, 30(2): 435-442.
[11]	祖象欢, 王银燕, 杨传雷, 杜剑维, 王佳伦. 增压柴油机EGR性能评估研究与实现[J]. 系统仿真学报, 2017, 29(12): 3075-3081.
[12]	张登辉, 晁涛, 王松艳, 马萍. 基于改进拉丁超立方的制导控制系统性能评估[J]. 系统仿真学报, 2017, 29(10): 2345-2352.
[13]	陈琰, 李康顺, 杨磊. 加入动态惩罚因子的GEP自动聚类算法[J]. 系统仿真学报, 2016, 28(4): 806-814.
[14]	王建国, 鄂群, 徐晓刚, 姚科明, 万新龙. 舰载直升机着舰指挥模拟训练系统[J]. 系统仿真学报, 2016, 28(2): 329-334.
[15]	戚宗锋, 韩山, 李建勋. 基于粗糙集的雷达抗干扰性能评估指标体系研究[J]. 系统仿真学报, 2016, 28(2): 335-342.