Abstract
This article introduces an opportunistic calibration method for walking distance estimation using a waist-mounted inertial sensor. In the proposed method, the calibration data are automatically collected from daily normal walking and it does not require a laboratory calibration procedure. While the walking steps can be accurately detected, the walking step length estimation is more difficult in a waist-mounted sensor case. In our method, when short walking data are detected from normal walking, a smoothing algorithm is used to estimate its walking distance. The walking step length and walking features of these data are used to update the step length model. Two experiments are conducted to evaluate the performance of the proposed method. The accuracy of smoother-based short walking distance estimation has been investigated in the first experiment. This experiment also investigates which feature is the best fit for our linear step length model. The second experiment is to demonstrate the opportunistic nature of the proposed method; 3–10 walking steps segments are extracted from 2 h walking data of one healthy subject and used to calibrate his walking profile. This method can be applied to a consumer device for human walking distance estimation without laboratory calibration procedure.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Instrumentation and Measurement
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
