We have created a system for identifying people based on their footstep force profiles and have tested its accuracy against a large pool of footstep data. This floor system may be used to transparently identify users in their everyday living and working environments. We have created user footstep models based on footstep profile features and have been able to achieve a recognition rate of 93 % using this feature-based approach. We have also shown that the effect of footwear is negligible on recognition accuracy.

This article presents a probabilistic approach to the tracking and estimation of the lower body posture of users moving on foot over an instrumented floor surface. The latter consists of an array of low-cost force platforms providing intermittent foot-floor contact data with limited spatial resolution. We use this data to track body posture in 3D space using Bayesian filters with a switching state-space model. Potential applications of this work to person tracking and human-computer interaction are described. 1.