基于连续数据流的动态手势识别算法

郑韡; 沈旭昆

基于连续数据流的动态手势识别算法

郑韡,
沈旭昆

北京航空航天大学虚拟现实技术与系统国家重点实验室, 北京 100191

基金项目: 国家高科技研究发展计划重点资助项目(2009AA012103)

详细信息

中图分类号: TP 391.4
计量
- 文章访问数: 8618
- HTML全文浏览量: 228
- PDF下载量: 2448
- 被引次数: 27
出版历程
- 收稿日期: 2010-10-27
- 网络出版日期: 2012-02-29

Algorithm based on continuous data stream for dynamic gesture recognition

The State Key Laboratory of Virtual Reality Technology and Systems, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 为识别用户做出的动态手势序列,基于数据手套采集的连续数据流,运用奇异值分解消除数据噪点,提取手势的特征信息,并利用关节弯曲的生理学特性与用户解耦合,将各种动作片段抽象成用户无关的手势模板,从而唯一定义手势特征并屏蔽不同用户的手势差异,再基于Hill Climbing思想把连续数据流分割成有序的动作序列,并按时序对所有片段在预先构造的层次树上实时搜索,根据欧式距离度量序列与手势模板的相似性.该算法对手势序列的分割准确,对多用户具有良好的适应性,其有效性在使用5DT数据手套搭建的两组动态手势识别的实验中得以验证.
- 连续数据流 /
- 奇异值分解 /
- 动态手势识别
Abstract: For the purpose of recognizing the sequence of dynamic gesture made by operator, a method was presented based on continuous data streams sampled from data glove, which used singular value decomposition (SVD) to eliminating noise and extracting features. The characteristics of physiology about joint bend was applied making user-dependent information be culled. A set of gesture template which across different users was set up. The template which gives a complete description of gesture's feature and generalizes it is therefore user-independent. Based on Hill Climbing heuristic, these streams were separated into action sequences, then a similarity measurement using Euclidian distance was adopted in real time between all segments and templates on a hierarchy search tree built in advance. The sequences segmented by this method are accuracy and suitable for multi users. The effectiveness of this approach for identifying dynamic gesture was verified by two empirical experiments which using 5DT data glove.
- continuous data stream /
- singular value decomposition(SVD) /
- dynamic gesture recognition

HTML全文

参考文献(14)

[1]	Agrawal R,Faloutsos C,Swami A.Efficient similarity search in sequence databases//FODO 1993 Proceedings of the 4th International Conference on Foundations of Data Organization and Algorithms.London:Springer-Verlag,1993:69-84
[2]	Babu S,Widom J.Continuous queries over data streams[J].ACM SIGMOD Record,2001,30(3):109-120
[3]	Gehrke J,Korn F,Srivastava D.On computing correlated aggregates over continuous data streams//2001 ACM SIGMOD International Conference on Management of Data.NY:Association for Computing Machinery,2001
[4]	Mitra S.Gesture recognition:a survey[J].IEEE Transactions on Systems,Man,and Cybernetics,Part C:Applications and Reviews,2007,37(3):311-324
[5]	Emran S M,Ye N.Robustness of canberra metric in computer intrusion detection//Proceedings of the 2001 IEEE Workshop on Information Assurance and Security.NY:United States Military Academy,West Point,2001
[6]	Chan Kinpong,Waichee Fu A.Efficient time series matching by wavelets//Proceedings-International Conference on Data Engineering.Los Alamitos,CA:Institute of Electrical and Electronics Engineers Computer Society,1999:126-133
[7]	Ju Zhaojie,Liu Honghai,Zhu Xiangyang,et al.Dynamic grasp recognition using time clustering, gaussian mixture models and hidden markov models//Intelligent Robotics and Applications-First International Conference,ICIRA 2008,Proceedings.Heidelberg:Springer-Verlag,2008,23(10):669-678
[8]	Bedregal B C,Costa A C R,Dimuro G P.Fuzzy rule-based hand gesture recognition,artificial intelligence in theory and practice//IFIP International Federation for Information Processing.Boston,MA:World Computer Congress,2006,217:285-294
[9]	Vamplew P,Adams A.Recognition and anticipation of hand motions using a recurrent neural network//IEEE International Conference on Neural Networks.Piscataway,NJ:IEEE,1995,6:2904-2907
[10]	Zollner R,Rogalla O,Dillmann R,et al.Dynamic grasp recognition within the framework of programming by demonstration//Robot and Human Communication-Proceedings of the IEEE International Workshop.Piscataway,NJ:IEEE,2001:418-423
[11]	Frolov V,Deml B,Hannig G.Geture recognition with hidden Markov models to enable multimodal haptic feedback//Proceedings of the 6th international conference on Haptics:Perception, Devices and Scenarios.Berlin,Heidelberg:Springer-Verlag,2008,5024:786-795
[12]	Fifth Dimension Technologies Corporation.5DT data glove ultra manual .Irvine,CA:Fifth Dimension Technologies,2004:42-56
[13]	Lewis J P,Cordner M,Fong N.Pose space deformations:a unified approach to shape interpolation and skeleton-driven deformation//Proceedings of the ACM SIGGRAPH Conference on Computer Graphics.NY:ACM Press,2000:165-172
[14]	Costello E.Random House Webster-s concise American sign language dictionary[M].NY:Random House,1999:3-25

施引文献

期刊类型引用(15)

1.	姚静，杨帅，王梦阳，王佩. 一种低功耗数字阀建模、性能分析及试验验证. 航空学报. 2025(02): 324-339 . 百度学术
2.	徐纯洁，谢方伟，凡镕瑞，魏汝路，田祖织. 考虑电磁铁线圈构型的高速开关阀动态特性分析. 西安交通大学学报. 2024(04): 211-220 . 百度学术
3.	刘广阔. 负载口独立控制的压铸机比例插装压射速度系统研究. 液压气动与密封. 2024(06): 73-79 . 百度学术
4.	吴会刚，韦文术，徐龙. 高速开关阀动态响应特性研究及性能优化. 机床与液压. 2024(12): 119-126 . 百度学术
5.	朱牧之，黄兴溶，张杰，刘勇. 电机直驱式高速开关阀及其系统特性研究. 南京工程学院学报(自然科学版). 2024(01): 24-32 . 百度学术
6.	陈楠，魏汝路，谢方伟. 高速开关阀阀芯频响及流量输出特性研究. 机床与液压. 2024(19): 159-164 . 百度学术
7.	何新军，何小群. 基于普通换向阀的高精度油缸位置控制. 液压与气动. 2023(01): 167-174 . 百度学术
8.	马克凡，王立勇，唐长亮，贾然. 基于高速开关阀的湿式离合器缓冲控制系统研究. 机床与液压. 2023(02): 174-179 . 百度学术
9.	高强，朱勇，钱鹏飞，张兵，王杰. 阵列压电叠堆驱动高速开关阀的设计与仿真分析. 液压与气动. 2023(09): 56-62 . 百度学术
10.	熊志文，崔玉国，蔡永根，马剑强，杨依领. 压电执行器输出位移的精密自感知. 仪器仪表学报. 2023(07): 28-36 . 百度学术
11.	赵天宇，吴帅，李文顶，房成，傅俊勇. 基于模型的数字式电液作动器智能控制方法. 飞控与探测. 2022(01): 48-56 . 百度学术
12.	张啸甫，施光林. 基于变溢流压力的电液机械臂节能控制策略. 液压与气动. 2022(07): 25-30 . 百度学术
13.	毛景禄，王聪，张彦伟，苗峰，崔雷. 复杂时变环境高速开关阀自适应控制算法. 液压与气动. 2022(12): 109-114 . 百度学术
14.	赵凯平，何涛，王传礼，史瑞. 双弹簧电液激振缸振幅补偿性能的研究. 工程设计学报. 2021(06): 737-745 . 百度学术
15.	刘伟静，赵超泽，王东，徐文丽，姚宁，王小涛. 基于CC430F6137的工业手柄摇杆优化模型研究. 自动化仪表. 2021(12): 77-81 . 百度学术