Enhancing Intelligent Shoes with Gait Analysis: A Review on the Spatiotemporal Estimation Techniques

Abstract

The continuous, automated monitoring of sensor-based data for walking capacity and mobility has expanded gait analysis applications beyond controlled laboratory settings to real-world, everyday environments facilitated by the development of portable, cost-efficient wearable sensors. In particular, the integration of Inertial Measurement Units (IMUs) into smart shoes has proven effective for capturing detailed foot movements and spatiotemporal gait characteristics. While IMUs enable accurate foot trajectory estimation through the double integration of acceleration data, challenges such as drift errors necessitate robust correction techniques to ensure reliable performance. This review analyzes current literature on shoe-based systems utilizing IMUs to estimate spatiotemporal gait parameters and foot trajectory characteristics, including foot-ground clearance. We explore the challenges and advancements in achieving accurate 3D foot trajectory estimation using IMUs in smart shoes and the application of advanced techniques like zero-velocity updates and error correction methods. These developments present significant opportunities for achieving reliable and efficient real-time gait assessment in everyday environments.

Keywords: fall prevention; foot clearance; foot movement tracking; foot trajectory estimation; gait analysis; inertial measurement unit; portable; smart shoes; spatiotemporal gait parameters; wearable sensors.

Figure 1

Illustration of different gait events during a gait cycle. Reprinted from [32].

Figure 2

Taxonomy of IMUs for gait analysis [48].

Figure 3

Illustration of the medical and technological requirements for Internet of Health for gait monitoring. Adapted from [81].

Figure 4

Taxonomy of smart shoe for gait analysis illustrating existing research categories [1,10,15,22,25,26,27,55,70,73,83].

Figure 5

Illustration of steps for estimating foot trajectory and spatiotemporal parameters based on literature analysis [9,10,15,22,25,26,27,70,72,73,83,85,86].

Figure 6

Visualization of the gait segmentation based on the peak of acceleration signals. IC: initial contact, MS: mid-stance, TO: toe-off. Reprinted from [70].