Recognition of human gait using 2D continuous dynamic programming towards realization of invisible user interfaces

One of the most distinctive characteristics of human beings is an ability to walk erect (bipedalism). However, this fact has not been much taken into consideration in designing user-interfaces. In this paper we present real-time recognition of human gait captured by a floor mat device. Two-dimensional continuous dynamic programming, 2DCDP, which is a powerful object recognition algorithm is adapted so that it fits to demands for real-time human gait recognition. Experiments showed that the system is promising towards realization of invisible user interfaces.