Footwear discrimination using dynamic tactile information

Abstract

This paper shows that it is possible to differentiate among various type of footwear solely by using highly dimensional pressure information provided by a sensorised insole. In order to achieve this, a person equipped with two sensorised insoles streaming real-time tactile data to a computer performs normal walking patterns. The sampled data is further transformed and reduced to sets of time series which are used for the classification of footwear. The pressure sensor is formed as a footwear inlay and is based on piezoresistive rubber having 1024 tactile cells providing normal pressure information in the form of a tactile image. The data is transmitted in realtime wirelessly at 30 fps from two such sensors. The online classification is using the dynamic time warping distances for different extracted features to assess the most similar type of footwear based on time series similarities. The paper shows that various footwear types yield distinct tactile patterns which can be assessed by the proposed algorithm.