A Pedestrian Dead Reckoning system using SEMG based on activities recognition

Abstract

Pedestrian positioning and navigation is an important emerging branch in the field of location-based service (LBS). Due to the loss of satellite signals, the traditional positioning method, such as GNSS, cannot meet the demand of indoor and outdoor seamless navigation. In order to provide the continuous and autonomous navigation information in indoor environment, we propose a novel Pedestrian Dead Reckoning (PDR) algorithm using Surface Electromyography (SEMG) sensors based on activities recognition. This PDR solution includes gait cycle detection, stride length estimation, pedestrian activities recognition, heading and position calculation. We extract several appropriate features from the raw SEMG signal to detect four different walking motions and then these activities information will aid the PDR system to complete the positioning. After the indoor walking tests, the results show that the PDR algorithm has a high positioning accuracy compared with the INS (Inertial Navigation System) algorithm. The step detection accuracy is 100%, the displacement errors in north and south are less than 1.2m and the distance error is less than 4%.