랜드마크 및 층 감지 방법을 이용한 스마트폰 기반 실내 보행자 항법 시스템

Abstract

In this paper, an indoor PDR(Pedestrian Dead Reckoning) system using landmark and floor detection is proposed. The proposed method uses the PDR technique with error correction based on detecting the landmark. The system consists of an improved PDR, the landmark recognition, and the floor detection components. The improved PDR component is a PDR system with an improved capability using the recognition of holding styles. The landmark recognition component detects whether the user walks on the landmarks. Two kinds of landmarks are defined including the WiFi and the turning landmarks. The methods for recognizing each landmark are developed. Whenever the landmark is detected, the system updates the position with the given position of the landmark, which means to remove the cumulative position error. In addition, an adaptive floor detection method using a barometer and a WiFi fingerprinting technique is suggested for tracking a pedestrian in a multi-floor building. The experimental results on a three-floor building with three subjects show the superior performance of the proposed system.