基于手势识别的机器人人机交互技术研究

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1068 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
陈一民, 张云华. 基于手势识别的机器人人机交互技术研究[J]. 机器人, 2009, 31(4): 351-356.. CHEN Yi-min, ZHANG Yun-hua. Research on Human-Robot Interaction Technique Based on Hand Gesture Recognition. ROBOT, 2009, 31(4): 351-356..

摘要研究了基于视觉的动态手势识别技术，采用基于肤色的高斯模型与改进的光流场跟踪算法结合的方法，实现了复杂背景下实时的手势跟踪，具有快速和准确的特点，且具有较好的鲁棒性．对于动态手势识别器，采用了隐马尔可夫模型（HMM）作为训练识别算法．考虑到动态手势特征本身的一些特点，对HMM参数优化算法重估式加以修正，调整了算法比例因子，从而推导了最佳状态链的确定算法、对HMM参数优化算法．最后将研究开发的动态手势识别算法成功地应用到了基于网络的远程机器人控制系统中．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈一民
	张云华

关键词 ：手势识别, 光流跟踪, 模式识别, 隐马尔可夫模型

Abstract：Vision based dynamic hand gesture recognition technology is studied,skin-color based Gauss model and a revised optical flow tracing algorithm are combined,and real-time hand gesture tracking in complex background is realized with characteristics of rapidity,accuracy and good robustness.Hidden Markov model(HMM) is adopted as training recognition algorithm for the dynamic hand gesture recognizer.Considering characteristics of dynamic hand gesture,the best state chain determination algorithm and HMM parameter optimization algorithm are deduced by modifying the reestimation formula of HMM parameter optimization algorithm and adjusting the scale factors of the algorithm.At last,the dynamic hand gesture recognition algorithm is successfully used in a network based remote robot control system.

Key words： hand gesture recognition optical flow tracking pattern recognition hidden Markov model

收稿日期: 2008-07-21

TP391

基金资助:国家科技支撑计划资助项目（2006BAK13B10）；上海市重点学科建设资助项目（J50103）

作者简介: 陈一民（1961- ），男，博士，教授，博士生导师．研究领域:机器人控制技术，网络与多媒体技术．
张云华（1970- ），男，博士生，讲师．研究领域:机器学习和人机交互技术，网络技术．

链接本文:

https://robot.sia.cn/CN/ 或 https://robot.sia.cn/CN/Y2009/V31/I4/351

[1] Shin J H,Kim J H,Hong K S.Implementation and performance evaluation of glove-based HCI methods:Gesture recognition systems using fuzzy algorithm and neural network for the wearable PC[A]. Lecture Notes in Computer Science (vol.3849)[M]. Berlin,Germany:Springer,2006.139～145.
[2] Lee H K,Kim J H.An HMM-based threshold model approach for gesture recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(10):961～973.
[3] 任海兵,祝远新,徐光佑,等.复杂背景下的手势分割与识别[J]. 自动化学报,2002,28(2):256～261.Pen Hai-hing,Zhu Yuan-xin,Xu Guang-you,et al.Hand gesture segmentation and recognition with complex backgrounds[J]. Acta Automatica Sinica,2002.28(2):256～261.
[4] Brethes L,Menezes P,Lerasle F,et al.Face tracking and hand gesture recognition for human-robot interaction[A]. Proceedings of the IEEE International Conference on Robotics and Automation[C]. Piscataway,NJ,USA:IEEE,2004.1901～1906.
[5] Hu H H,Jia P,Lu T,et al.Head gesture recognition for handsfree control of an intelligent wheelchair[J]. Industrial Robot,2007,34(1):60～68.
[61 Triesch J,Bochum A.Vision based robotic gesture recognition[DB/OL]. ftp://ftp.neoroinformatik.ruhr-unibochum.de/pub/manuscripts/theses/triesch_PhD.pdf,1999.
[7] Waldherr S,Romero R,Thrun S.Gesture based interface for human-robot interaction[J]. Autonomous Robots,2000,9(2):151～173.
[8] 张家林.基于立体视觉的皮肤表面检测技术的研究[D]. 北京:北京工业人学,2002.34～44.Zhang Jia-lin.Research on Measurement Technique of Skin Surface Based on Stereo Vision[D]. Beijing:Beijing University of Technology,2002.34～44.
[9] Ghahramani Z.An introduction to hidden Markov models and Bayesian networks[J]. International Jonrual of Pattern Recognition and Artificial Intelligence,2001,15(1):9～42.
[10] Stefanov N,Galata A,Hubbold R.A real-time hand tracker using variable-length Markov models of behaviour[J]. Computer Vision and Image Understanding,2007,108(1-2):98～115.
[11] Saul L K,Jordan M I.Mixed memory Markov models:Decomposing complex stochastic processes as mixtures of simpler ones[J]. Machine Learning,1999,37(1):75～87.