Average Step Length Estimation Models’ Evaluation Using Inertial Sensors: A Review

Abstract

Inertial sensors of smartphones and other Internet-of-Things devices present a very promising tool to monitor users’ activity including their step length. In this review paper, we deal with an in-depth analysis and comparison of 13 representative step length estimation models using smartphone inertial sensors: step-frequency-based, acceleration-based, angle-based, and multiparameter. Hereby, we have studied the influence of different walking speeds and four typical sensor positions on the models’ performance. Results indicate that smartphone position affected the performance of most acceleration-based models derived from a gait model. Their performance deteriorated if smartphone was carried in hand or pocket. Walking speed affected the performance of models that include step frequency when tuned with personalized sets of constants. Most of them performed better for fast and normal walking speeds. During this research, we also established an open-source dataset that contains over 22 km of gait measurements obtained from a group of 15 healthy adults.