计算机科学 ›› 2017, Vol. 44 ›› Issue (12): 287-291.doi: 10.11896/j.issn.1002-137X.2017.12.052
王海鹏,龚岩,刘武,李泽,张思美
WANG Hai-peng, GONG Yan, LIU Wu, LI Ze and ZHANG Si-mei
摘要: 手势交互作为一种自然便捷的交互方式,在智能家居和智能交通等领域具有日益广泛的应用前景。由于手势行为发生的速度、空间约束和用户差异的影响,同一语义手势表现出具有不同时间和空间尺度的多形态特征,这给保障手势识别的准确率带来了挑战。提出了一种基于动态时间规整DTW(Dynamic Time Warping)方法的时空多尺度手势识别方法SDTW(Spatial-Temporal Dynamic Time Warping),该方法通过对空间形态数据进行分箱操作来达到适应一定程度空间尺度变化的能力。因此,SDTW方法不仅具备DTW方法的时间尺度适应性,而且扩展了空间尺度适应性。文中实现了一个基于智能手机加速度传感设备的SDTW手势识别原型系统。实验测试验证了所提方法能够有效提升手势识别的准确率。
[1] WANG J Q,ZHANG T.An ARM-based embedded gesture recognition system using a data glove[C]∥The 26th Chinese Control and Decision Conference (2014 CCDC).IEEE,2014:1580-1584. [2] AHUJA M K,SINGH A.Static vision based Hand Gesture re-cognition using principal component analysis[C]∥2015 IEEE 3rd International Conference on MOOCs,Innovation and Technology in Education (MITE).IEEE,2015:402-406. [3] GIRUOIU M C,MARITA T.Gesture recognition toolkit using a Kinect sensor[C]∥2015 IEEE International Conference on Intelligent Computer Communication and Processing(ICCP).IEEE,2015:317-324. [4] REHM M,BEE N.Wave Like an Egyptian:AccelerometerBased Gesture Recognition for Culture Specific Interactions[C]∥ British Hci Group Conference on People and Computers:Culture,Creativity,Interaction British Computer Society.2008:13-22. [5] LIU J,ZHONG L,et al.uWave:accelerometer based Personalized Gesture Recognition and Its Applications[J].Pervasive & Mobile Computing,2009,5(6):657-675. [6] WANG X,DAI G.A novel method to recognize complex dyna-mic gesture by combining HMM and FNN models[C]∥IEEE Symposium on Computational Intelligence in Image and Signal Processing.IEEE,2007:13-18. [7] ZHANG S,YUAN C,ZHANG Y.Hand Written Character Re-cognition Using Orientation Quantization Based on 3D Accele-rometer[C]∥ International Conference on Mobile and Ubiquitous Systems:Computing,Networking and Services.Mobiquitous 2008,2008. [8] CHOI H R,KIM E J,KIM T Y.A DTW gesture recognition system based on gesture orientation histogram[C]∥The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014).IEEE,2014:1-2. [9] NAGI J,DUCATELLE F,et al.Max-pooling convolutional neural networks for vision-based hand gesture recognition[C]∥2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).IEEE,2011:342-347. [10] CHEN Q,ZHANG C M,ZHANG Y F,et al.Pattern recognition by DTW and series data mining in 3D stratum modelling and 3D visualization[C]∥Fifth International Conference on Fuzzy Systems and Knowledge Discovery,2008(FSKD’08).IEEE,2008:650-654. [11] LIU Q,HUANG Z Q,et al.Utterance verification On DTW based speech recognition using likelihood[C]∥2010 International Conference on Computer Application and System Mode-ling (ICCASM 2010).IEEE,2010:V2-427-V2-431. [12] ANDREA C.Dynamic time warping for offline recognition of a small gesture vocabulary[C]∥Proceedings of the IEEE ICCV Workshop on Recognition,Analysis,and Tracking of Faces and Gestures in Real-Time Systems.August 2001:83. [13] TUSHAR K D,MISRA S,et al.Comparison of DTW score and warping path for text dependent speaker verification system[C]∥2015 International Conference on Circuit,Power and Computing Technologies (ICCPCT).2015:1-4. [14] CHOI H R,KIM E J,KIM T Y.A DTW gesture recognition system based on gesture orientation histogram[C]∥The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014).2014:1-2. |
No related articles found! |
|