TY - JOUR
T1 - An indoor locationtracking system for smart parking
AU - Lan, Kun Chan
AU - Shih, Wen Yuah
N1 - Copyright:
Copyright 2014 Elsevier B.V., All rights reserved.
PY - 2014/5/4
Y1 - 2014/5/4
N2 - There are always frustrations for drivers in finding parking space and parking is costly in almost every major city in the world. In this paper, we propose a crowdsourcing solution by exploiting sensors in the smartphone to collect real-time parking availability information. In particular, we utilise a pedestrian dead reckoning (PDR) system to track the driver's trajectory to detect when he is about to leave his parking space. However, the effectiveness of a PDR system lies in its success in accurately estimating the user's moving distance and direction. In this work, we implement a waist-mounted-based PDR method on a smartphone that can measure the user's moving distance with a high accuracy. Furthermore, we design a map-matching algorithm to calibrate the direction errors from the gyro using building floor plans. The results of our experiment show that we can achieve about 98% accuracy in estimating the user's walking distance, with an overall location error of about 0.48 m.
AB - There are always frustrations for drivers in finding parking space and parking is costly in almost every major city in the world. In this paper, we propose a crowdsourcing solution by exploiting sensors in the smartphone to collect real-time parking availability information. In particular, we utilise a pedestrian dead reckoning (PDR) system to track the driver's trajectory to detect when he is about to leave his parking space. However, the effectiveness of a PDR system lies in its success in accurately estimating the user's moving distance and direction. In this work, we implement a waist-mounted-based PDR method on a smartphone that can measure the user's moving distance with a high accuracy. Furthermore, we design a map-matching algorithm to calibrate the direction errors from the gyro using building floor plans. The results of our experiment show that we can achieve about 98% accuracy in estimating the user's walking distance, with an overall location error of about 0.48 m.
UR - http://www.scopus.com/inward/record.url?scp=84894105866&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84894105866&partnerID=8YFLogxK
U2 - 10.1080/17445760.2013.855933
DO - 10.1080/17445760.2013.855933
M3 - Article
AN - SCOPUS:84894105866
SN - 1744-5760
VL - 29
SP - 215
EP - 238
JO - International Journal of Parallel, Emergent and Distributed Systems
JF - International Journal of Parallel, Emergent and Distributed Systems
IS - 3
ER -