基于SURF特征跟踪的动态手势识别算法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (2821 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
包加桐, 宋爱国, 郭晏, 唐鸿儒. 基于SURF特征跟踪的动态手势识别算法[J]. 机器人, 2011, 33(4): 482-489.. BAO Jiatong, SONG Aiguo, GUO Yan, TANG Hongru. Dynamic Hand Gesture Recognition Based on SURF Tracking. ROBOT, 2011, 33(4): 482-489..

摘要提出了一种基于加速鲁棒特征（SURF）跟踪的动态手势识别算法．其特征在于算法无需预先检测分割人手区域，仅通过跟踪统计相邻帧间匹配SURF特征点的移动主方向来刻画手势运动轨迹．提出采用经时间规整的轨迹方向数据流来建立动态手势模型，利用基于相关分析的数据流聚类方法实现动态手势的识别，大大提高动态手势识别速度．实验使用26个英文字母作为动态手势训练和识别，手势训练集和测试集的识别率分别为87.1%和84.6%，并成功用于实验室自主研制的侦察移动机器人Hunter的运动控制中，证实了该方法的有效性．

	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
	包加桐
	宋爱国
	郭晏
	唐鸿儒

关键词 ：动态手势识别, 加速鲁棒特征, 特征跟踪, 动态手势模型

Abstract：A method of dynamic hand gesture recognition based on SURF(speeded up robust feature) tracking is proposed. The main characteristic is that the hand trajectory is described only by tracking the dominant movement directions of matched SURF points in adjacent frames with no need of the previous detection and segmentation of the hand region.The dynamic hand gesture is then modeled by a series of trajectory direction data streams after time warping.Accordingly,the data stream clustering method based on correlation analysis is developed to recognize a dynamic hand gesture and to speed up calculation. The proposed algorithm is tested on 26 alphabetic hand gestures and yields a satisfactory recognition rate,which is 87.1% on the training set and 84.6%on the testing set.Its successful application to the motion control of our self-developed robot Hunter also establishes the effectiveness of the approach.

Key words： dynamic hand gesture recognition SURF(speeded up robust feature) feature tracking dynamic hand gesture model

收稿日期: 2010-10-20 录用日期: 2011-04-21

TP391

基金资助:国家863计划资助项目（2006AA04Z246）；国家自然科学基金资助项目（61075068）；教育部重大创新工程培育资金资助项目（708045）；江苏省自然科学基金重点项目（BK2009183），江苏省自然科学基金重点项目（BK2010063）

通讯作者: 宋爱国 E-mail: a.g.song@seu.edu.cn

作者简介: 包加桐（1983- ），男，博士生．研究领域：移动机器人，机器人视觉．
宋爱国（1968- ），男，博士，教授，博士生导师．研究领域：机器人传感与控制，人机交互技术．
郭晏（1984- ），男，博士生．研究领域：移动机器人，机器人视觉．

链接本文:

https://robot.sia.cn/CN/ 或 https://robot.sia.cn/CN/Y2011/V33/I4/482

[1] Malima A,Ozgur E,Cetin M.A fast algorithm for vision-based hand gesture recognition for robot controI[C]//14th IEEE Signal Processing and Communications Applications Conference.Piscataway,NJ,USA:IEEE,2006:1-4.
[2] Sanchez-Nielsen E,Ant6n-Canalis L,Hemandez-Tejera M.Hand gesture recognition for human-machinc intcraction[J].Journal of WSCG,2004,12(1):91-96.
[3] Wu Y,Liu Q,Huang T S.An adaptive self-organizing color segmentation algorithm with application to robust real-time human hand localization[C]//Proceedings of the 9th Asian Conference on Computer Vision.2000:1106-1111.
[4] Zhu Y X,Xu G Y,Kriegman D J.A real-time approach to the spotting,representation,and recognition of hand gestures for human-computer interaction[J].Computer Vision and ImageUnderstanding,2002,85(3):189-208.

[5] Weng C B,Li Y,Zhang M M,et al.Robust hand posture recognition integrating multi-cue hand tracking[M]//Lecture Notes in Computer Science,vol.6249.Berlin,Germany:SpringerVerlag,2010:497-508.
[6] Heap T,Samaria F.Real-time hand tracking and gesture recognition using smart snakes[C]//Proceedings of the Conference on Interface to Real and Virtual Worlds.1995.
[7] Zhong Y,Jain A K,Dubuisson-Jolly M P.Object tracking using deformable templates[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(5):544-549.

[8] MacCormick J,Isard M.Partitioned sampling,articulated objects,and interface-quality hand tracking[C]//6th European Conference on Computer Vision,Part Ⅱ.London,UK:Springer-Verlag,2000:3-19.
[9] Shan C F,Tan T N,Wei Y C.Real-time hand tracking using a mean shift embedded particle filter[J].Pattern Recognition,2007,40(7):1958-1970.

[10] Ong E J,Bowden R.A boosted classifier tree for hand shape detection[C]//6th IEEE Intemational Conference on Automatic Face and Gesture Recognition.Piscataway,NJ,USA:IEEE,2004:889-894.
[11] Mohamed Mansoor Roomi S,Jyothi Priya R,Jayalakshmi H.Hand gesture recognition for human-computer interaction[J].Journal of Computer Science,2010,6(9):994-999.
[12] Yoon H S,Soh J,Bae Y J,et al.Hand gesture recognition using combined features oflocation,angle and velocity[J].Pattem Recognition,2001,34(7):1491-1501.

[13] Bobick A F,Davis J W.The recognition of human movement using temporal templates[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(3):257-267.

[14] McKenna S J,Morrison K.A comparison of skin history and trajectory-based representation schemes for the recognition of user-specified gestures[J].Pattem Recognition,2004,37(5):999-1009.

[15] Bay H,Ess A,Tuytelaars T,et al.SURF:Speeded up robust features[J].Computer Vision and Image Understanding,2008,110(3):346-359.

[16] Lowe D G.Distinctive image features from scale-invariant keypoints[J].Intemational Journal of Computer Vision,2004,60(2):91-110.

[17] Bao J T,Guo Y,Song A G,et al.A multi-agent based robot telesupervision architecture for hazardous materials detection[C]//IEEE International Conference on Information and Automation.Piscataway,NJ,USA:IEEE,2010:2428-2432.