A Motion Recognition Method Using Foot Pressure Sensors
Ayumi Ohnishi, Tsutomu Terada, Masahiko Tsukamoto · 2018
This paper proposes a method for recognizing postures and gestures using foot pressure sensors, and we investigate optimal positions for pressure sensors on soles are the best for motion recognition. In experiments, the recognition accuracies of 22 kinds of daily postures and gestures were evaluated from foot-pressure sensor values. Furthermore, the optimum measurement points for high recognition accuracy were examined by evaluating combinations of two foot pressure measurement areas on a round-robin basis. As a result, when selecting the optimum two points for a user, the recognition accuracy was about 93.6% on average. Although individual differences were seen, the best combinations of areas for each subject were largely divided into two major patterns. When two points were chosen, combinations of the near thenar, which is located near the thumb ball, and near the heel or point of the outside of the middle of the foot were highly recognized. Of the best two points, one was commonly the near thenar for subjects. By taking three points of data and covering these two combinations, it will be possible to cope with individual differences. The recognition accuracy of the averaged combinations of the best two combinations for all subjects was classified with an accuracy of about 91.0% on average. On the basis of these results, two types of pressure sensing shoes were developed.