三维惯性传感参数表征下的行人混合步态分类
|
摘要
在行人步态分类研究领域中,传统的基于微机电系统(micro-electro-mechanical system,MEMS)惯性传感器技术的步态分类方法侧重于对行人单一步态模式进行区分,忽略了两个单一步态模式之间的过渡步态模式,从而降低了行人行走过程中走、跑、停等混合步态的分类精度,还会在时间上造成缺失,进而造成行人航迹推算产生不可估量的定位误差.从人体运动学角度出发分析了行人步态特点,同时利用9轴MEMS惯性传感器采集了行人步态原始数据并对其进行剖析,设定了人体三维惯性传感参数,以供后续分类算法使用.为了进一步提高整体混合步态的分类精度,针对朴素贝叶斯算法对相反过渡步态模式区分精度不高的问题,在其基础上通过加窗判断前后两个步态的连续性,完成了行人混合步态的最终分类.验证结果表明,和传统的样本熵与小波能量相结合方法相比,提出的三维惯性传感参数表征下的行人混合步态分类方法,不仅能区分出行人混合步态中的多种单一步态模式和多种过渡步态模式,同时整体分类精度提高了14.46%,从而有效证明了该方法在行人步态分类领域具有良好的理论价值和应用价值.
In pedestrian gait classification research, the traditional method based on the micro-electro-mechanical system(MEMS) inertial sensor technique focuses on distinguishing a single pedestrian gait, and ignoring transition gait between two single gaits. It leads to poor classification accuracy of mixed gaits such as walking, running, halting,and even causes loss of time. As a result, positioning error of pedestrian dead reckoning becomes large. This paper analyzes gait characteristics based on kinesiology, and collects raw data of pedestrian using a 9-axis MEMS sensor. 3D inertial sensor parameters are then selected to be applied to the subsequent classification algorithm. Because the Naive Bayes algorithm has low accuracy to distinguish reverse transition gaits, the improved algorithm based on the Naive Bayes algorithm judges continuity of two adjacent windows to realize mixed gait classification. Experimental results show that the proposed mixed pedestrian gait classification method with 3D inertial sensor parameters characterization can distinguish a variety of single gaits and transition gaits from mixed gaits. It can also improve the overall classification accuracy by 14.46% as compared with the method of combining sample entropy and wavelet energy. Therefore, the proposed method has a good theoretical and practical value in gait classification.
In pedestrian gait classification research, the traditional method based on the micro-electro-mechanical system(MEMS) inertial sensor technique focuses on distinguishing a single pedestrian gait, and ignoring transition gait between two single gaits. It leads to poor classification accuracy of mixed gaits such as walking, running, halting,and even causes loss of time. As a result, positioning error of pedestrian dead reckoning becomes large. This paper analyzes gait characteristics based on kinesiology, and collects raw data of pedestrian using a 9-axis MEMS sensor. 3D inertial sensor parameters are then selected to be applied to the subsequent classification algorithm. Because the Naive Bayes algorithm has low accuracy to distinguish reverse transition gaits, the improved algorithm based on the Naive Bayes algorithm judges continuity of two adjacent windows to realize mixed gait classification. Experimental results show that the proposed mixed pedestrian gait classification method with 3D inertial sensor parameters characterization can distinguish a variety of single gaits and transition gaits from mixed gaits. It can also improve the overall classification accuracy by 14.46% as compared with the method of combining sample entropy and wavelet energy. Therefore, the proposed method has a good theoretical and practical value in gait classification.
引文
[1]Hu Z,Ai G,Zhang L,et al.Novel research on improving global positioning system accuracy in the pedestrian integrated navigation monitoring system[J].Australian Journal of Electrical&Electronics Engineering,2014,11(4):411-420.
[2]李若涵,张金艺,徐德政,等.运动分类步频调节的微机电惯性测量单元室内行人航迹推算[J].上海大学学报(自然科学版),2014,20(5):612-623.
[3]Wahab Y,Mazalan M,Bakar N A,et al.Low power shoe integrated intelligent wireless gait measurement system[J].Journal of Physics:Conference,2014,495(1):43-46.
[4]Qi Y,Soh C B,Gunawan E,et al.Estimation of spatial-temporal gait parameters using a low-cost ultrasonic motion analysis system[J].Sensors,2014,14(8):15434-15457.
[5]Kivimaki T,Vuorela T,Peltola P,et al.A review on device-free passive indoor positioning methods[J].International Journal of Smart Home,2014,8(1):71-94.
[6]Zhang M,Sawchuk A A.Human daily activity recognition with sparse representation using wearable sensors[J].IEEE Journal of Biomedical and Health Informatics,2013,17(3):553-560.
[7]Panahandeh G,Mohammadiha N,Leijon A,et al.Continuous hidden Markov model for pedestrian activity classification and gait analysis[J].IEEE Trans on Instrumentation and Measurement,2013,62(5):1073-1083.
[8]邢秀玉,刘鸿宇,黄武.基于加速度的小波能量特征及样本熵组合的步态分类算法[J].传感技术学报,2013,26(4):545-549.
[9]Tian Z,Fang X,Zhou M,et al.Smartphone-based indoor integrated Wi Fi/MEMS positioning algorithm in a multi-floor environment[J].Micromachines,2015,6(3):347-363.
[10]刘华,吴文华.高跟鞋对行走中女性躯干、下肢的力学影响[J].北京生物医学工程,2011,30(1):105-108.
[11]蒋伟宇,于亮,马维虎,等.一种新型寰枢椎后路动态固定系统的稳定性研究[J].中国临床解剖学杂志,2014,32(1):76-79.
[12]Sabatelli S,Galgani M,Fanucci L,et al.A double-stage Kalman filter for orientation tracking with an integrated processor in 9-D IMU[J].IEEE Transactions on Instrumentation and Measurement,2013,62(3):590-598.
[13]高东,马昕,许欣,等.基于滑动窗口的定性趋势分析方法及应用[J].计算机应用研究,2014,31(5):1441-1444.
[14]李娟娟,张金艺,张秉煜,等.蓝牙4.0标准规范下的模糊指纹定位算法[J].上海大学学报(自然科学版),2013,19(2):126-131.
[15]范彦勤.基于贝叶斯分类器的个人信用评估研究[D].西安:西安电子科技大学,2014.
[16]Ettelt D,Rey P,Jourdan G,et al.3D magnetic field sensor concept for use in inertial measurement units(IMUs)[J].IEEE Journal of Microelectromechanical Systems,2014,23(2):324-333.
[17]Shany T,Redmond S J,Narayanan M R,et al.Sensors-based wearable systems for monitoring of human movement and falls[J].IEEE Sensors Journal,2012,12(3):658-670.
[2]李若涵,张金艺,徐德政,等.运动分类步频调节的微机电惯性测量单元室内行人航迹推算[J].上海大学学报(自然科学版),2014,20(5):612-623.
[3]Wahab Y,Mazalan M,Bakar N A,et al.Low power shoe integrated intelligent wireless gait measurement system[J].Journal of Physics:Conference,2014,495(1):43-46.
[4]Qi Y,Soh C B,Gunawan E,et al.Estimation of spatial-temporal gait parameters using a low-cost ultrasonic motion analysis system[J].Sensors,2014,14(8):15434-15457.
[5]Kivimaki T,Vuorela T,Peltola P,et al.A review on device-free passive indoor positioning methods[J].International Journal of Smart Home,2014,8(1):71-94.
[6]Zhang M,Sawchuk A A.Human daily activity recognition with sparse representation using wearable sensors[J].IEEE Journal of Biomedical and Health Informatics,2013,17(3):553-560.
[7]Panahandeh G,Mohammadiha N,Leijon A,et al.Continuous hidden Markov model for pedestrian activity classification and gait analysis[J].IEEE Trans on Instrumentation and Measurement,2013,62(5):1073-1083.
[8]邢秀玉,刘鸿宇,黄武.基于加速度的小波能量特征及样本熵组合的步态分类算法[J].传感技术学报,2013,26(4):545-549.
[9]Tian Z,Fang X,Zhou M,et al.Smartphone-based indoor integrated Wi Fi/MEMS positioning algorithm in a multi-floor environment[J].Micromachines,2015,6(3):347-363.
[10]刘华,吴文华.高跟鞋对行走中女性躯干、下肢的力学影响[J].北京生物医学工程,2011,30(1):105-108.
[11]蒋伟宇,于亮,马维虎,等.一种新型寰枢椎后路动态固定系统的稳定性研究[J].中国临床解剖学杂志,2014,32(1):76-79.
[12]Sabatelli S,Galgani M,Fanucci L,et al.A double-stage Kalman filter for orientation tracking with an integrated processor in 9-D IMU[J].IEEE Transactions on Instrumentation and Measurement,2013,62(3):590-598.
[13]高东,马昕,许欣,等.基于滑动窗口的定性趋势分析方法及应用[J].计算机应用研究,2014,31(5):1441-1444.
[14]李娟娟,张金艺,张秉煜,等.蓝牙4.0标准规范下的模糊指纹定位算法[J].上海大学学报(自然科学版),2013,19(2):126-131.
[15]范彦勤.基于贝叶斯分类器的个人信用评估研究[D].西安:西安电子科技大学,2014.
[16]Ettelt D,Rey P,Jourdan G,et al.3D magnetic field sensor concept for use in inertial measurement units(IMUs)[J].IEEE Journal of Microelectromechanical Systems,2014,23(2):324-333.
[17]Shany T,Redmond S J,Narayanan M R,et al.Sensors-based wearable systems for monitoring of human movement and falls[J].IEEE Sensors Journal,2012,12(3):658-670.