Step Cycle Detection of Human Gait Based on Inertial Sensor Signal

As a biologic character Human gait is very important for identity recognized, health evaluation, medical monitoring. Gait cycle is one of the most basic parameters in gait analysis. We can easily calculate the gait uniformity, gait symmetry, gait continuity and other parameters based on this parameter. Especially for many of diseases estimation, such as Parkinsons disease, to get the phase synchronization, the precise time of every step event must be determined. We can simply get gait counts from traditional pedometer, but we can not get the precise step interval. In this paper, based on Pan-Tompkins algorithm used in ECG (electrocardiogram) signal, we develop one method using peak detection based on feet acceleration and angular velocity. Experimental results show the method has high precision and less error.

[1]  Anthony Dalton,et al.  Analysis of gait and balance through a single triaxial accelerometer in presymptomatic and symptomatic Huntington's disease. , 2013, Gait & posture.

[2]  Davrondzhon Gafurov,et al.  Performance and security analysis of Gait-based user authentication , 2008 .

[3]  Nigel H. Lovell,et al.  Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring , 2006, IEEE Transactions on Information Technology in Biomedicine.

[4]  Jorunn L Helbostad,et al.  Estimation of gait cycle characteristics by trunk accelerometry. , 2004, Journal of biomechanics.

[5]  Willis J. Tompkins,et al.  Quantitative Investigation of QRS Detection Rules Using the MIT/BIH Arrhythmia Database , 1986, IEEE Transactions on Biomedical Engineering.

[6]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[7]  Yang Qi,et al.  Gait Recognition Based on Two-scale Dynamic Bayesian Network and More Information Fusion , 2012 .

[8]  B. G. Celler,et al.  Classification of basic daily movements using a triaxial accelerometer , 2004, Medical and Biological Engineering and Computing.

[9]  Allen Y. Yang,et al.  Distributed recognition of human actions using wearable motion sensor networks , 2009, J. Ambient Intell. Smart Environ..

[10]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[11]  Jun-Ming Lu,et al.  Real-time gait cycle parameters recognition using a wearable motion detector , 2011, Proceedings 2011 International Conference on System Science and Engineering.

[12]  Liu Yi Gait Analysis Based on Gait Acceleration , 2009 .