Comparison of Different Algorithms for Calculating Velocity and Stride Length in Running Using Inertial Measurement Units

Running has a positive impact on human health and is an accessible sport for most people. There is high demand for tracking running performance and progress for amateurs and professionals alike. The parameters velocity and distance are thereby of main interest. In this work, we evaluate the accuracy of four algorithms, which calculate the stride velocity and stride length during running using data of an inertial measurement unit (IMU) placed in the midsole of a running shoe. The four algorithms are based on stride time, foot acceleration, foot trajectory estimation, and deep learning, respectively. They are compared using two studies: a laboratory-based study comprising 2377 strides from 27 subjects with 3D motion tracking as a reference and a field study comprising 12 subjects performing a 3.2-km run in a real-world setup. The results show that the foot trajectory estimation algorithm performs best, achieving a mean error of 0.032 ± 0.274 m/s for the velocity estimation and 0.022 ± 0.157 m for the stride length. An interesting alternative for systems with a low energy budget is the acceleration-based approach. Our results support the implementation decision for running velocity and distance tracking using IMUs embedded in the sole of a running shoe.

[1]  Véronique A. Cornelissen,et al.  Effects of Endurance Training on Blood Pressure, Blood Pressure–Regulating Mechanisms, and Cardiovascular Risk Factors , 2005, Hypertension.

[2]  B C Elliott,et al.  Optimal stride length considerations for male and female recreational runners. , 1979, British journal of sports medicine.

[3]  Björn Eskofier,et al.  Movement Speed Estimation Based on Foot Acceleration Patterns , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[4]  Julius Hannink,et al.  Sensor-Based Gait Parameter Extraction With Deep Convolutional Neural Networks , 2016, IEEE Journal of Biomedical and Health Informatics.

[5]  R. Marshall,et al.  Interaction of step length and step rate during sprint running. , 2004, Medicine and science in sports and exercise.

[6]  Jeff Bird,et al.  Indoor navigation with foot-mounted strapdown inertial navigation and magnetic sensors [Emerging Opportunities for Localization and Tracking] , 2011, IEEE Wireless Communications.

[7]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[8]  Stephen J. McGregor,et al.  Effect of Treadmill versus Overground Running on the Structure of Variability of Stride Timing , 2014, Perceptual and motor skills.

[9]  Gerhard Tröster,et al.  Out of the lab and into the woods: kinematic analysis in running using wearable sensors , 2011, UbiComp '11.

[10]  Björn Eskofier,et al.  A wireless trigger for synchronization of wearable sensors to external systems during recording of human gait , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  Irene S Davis,et al.  A kinematic method for footstrike pattern detection in barefoot and shod runners. , 2012, Gait & posture.

[12]  Isaac Skog,et al.  Zero-Velocity Detection—An Algorithm Evaluation , 2010, IEEE Transactions on Biomedical Engineering.

[13]  S. Simon.  Gait Analysis, Normal and Pathological Function. , 1993 .

[14]  Rezaul K. Begg,et al.  Foot Plantar Pressure Measurement System: A Review , 2012, Sensors.

[15]  Shiwei Mo,et al.  Accuracy of three methods in gait event detection during overground running. , 2018, Gait & posture.

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[18]  Thomas L. Milani,et al.  Detecting foot-to-ground contact from kinematic data in running , 2009 .

[19]  Bjoern M. Eskofier,et al.  Mobile Stride Length Estimation With Deep Convolutional Neural Networks , 2018, IEEE Journal of Biomedical and Health Informatics.

[20]  M. Silvis,et al.  Common Leg Injuries of Long-Distance Runners , 2012, Sports health.

[21]  Gareth P. Bailey,et al.  Sampling Rates and Sensor Requirements for Kinematic Assessment During Running Using Foot Mounted IMUs , 2014, icsports 2014.

[22]  Eric Foxlin,et al.  Pedestrian tracking with shoe-mounted inertial sensors , 2005, IEEE Computer Graphics and Applications.

[23]  Kamiar Aminian,et al.  3D gait assessment in young and elderly subjects using foot-worn inertial sensors. , 2010, Journal of biomechanics.

[24]  Marco Parvis,et al.  Procedure for effortless in-field calibration of three-axial rate gyro and accelerometers , 1995 .

[25]  Joseph S. B. Mitchell,et al.  The Discrete Geodesic Problem , 1987, SIAM J. Comput..

[26]  Charles F. F. Karney.  Algorithms for geodesics , 2011, Journal of Geodesy.

[27]  Björn Eskofier,et al.  Inertial Sensor-Based Stride Parameter Calculation From Gait Sequences in Geriatric Patients , 2015, IEEE Transactions on Biomedical Engineering.

[28]  Brigit De Wit,et al.  Biomechanical analysis of the stance phase during barefoot and shod running. , 2000, Journal of biomechanics.

[29]  Björn Eskofier,et al.  Kinematic parameter evaluation for the purpose of a wearable running shoe recommendation , 2018, 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[30]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[31]  Lorenzo Chiari,et al.  A Mobile Kalman-Filter Based Solution for the Real-Time Estimation of Spatio-Temporal Gait Parameters , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[32]  S. Blair,et al.  Leisure-time running reduces all-cause and cardiovascular mortality risk. , 2014, Journal of the American College of Cardiology.

[33]  Isaac Skog,et al.  Foot-Mounted Inertial Navigation and Cooperative Sensor Fusion for Indoor Positioning , 2010 .

[34]  Gareth P. Bailey,et al.  Assessment of Foot Kinematics During Steady State Running Using a Foot-mounted IMU , 2014 .

[35]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[36]  M Bonnard,et al.  Stride variability in human gait: the effect of stride frequency and stride length. , 2003, Gait & posture.

[37]  Julius Hannink,et al.  Activity recognition in beach volleyball using a Deep Convolutional Neural Network , 2017, Data Mining and Knowledge Discovery.

[38]  Peter R. Cavanagh,et al.  Biomechanics of Distance Running. , 1990 .