Human Behavior Measurement Based on Sensor Network and Robot Partners

Abstract

This paper proposes to measure human behavior based on a sensor network. It starts by explaining informationally structured space, robot partners, and sensor networks developed in this study. Next, it discusses the applicability of sensor network and robot partner to rehabilitation. Growing neural gas is applied to extract an image of a person from a background image and a steady-state genetic algorithm is used to extract human movement from threedimensional distance images. We confirm the effectiveness of our proposal through experiments.