Abstract
Due to their distinctive presence in everyday life and the variety of available built-in sensors, smartphones have become the focus of recent indoor localization research. Hence, this paper describes a novel smartphone-based sensor fusion algorithm. It combines the relative inertial measurement unit (IMU) based movements of the pedestrian dead reckoning with the absolute fingerprinting-based position estimations of Wireless Local Area Network (WLAN), Bluetooth (Bluetooth Low Energy—BLE), and magnetic field anomalies as well as a building model in real time. Thus, a step-based position estimation without knowledge of any start position was achieved. For this, a grid-based particle filter and a Bayesian filter approach were combined. Furthermore, various optimization methods were compared to weigh the different information sources within the sensor fusion algorithm, thus achieving high position accuracy. Although a particle filter was used, no particles move due to a novel grid-based particle interpretation. Here, the particles’ probability values change with every new information source and every stepwise iteration via a probability-map-based approach. By adjusting the weights of the individual measurement methods compared to a knowledge-based reference, the mean and the maximum position error were reduced by 31%, the RMSE by 34%, and the 95-percentile positioning errors by 52%.
Highlights
The automatic determination of a location in an earth-related reference system is essential in many areas of life and economy
An algorithm for smartphone-based pedestrian localization was shown, whichInctohmisbwinoersk,thaen callagsosricitahlmPDfoRr swmitahrtfpihnognerep-briansteidngpeadnedstarinanovloelcamliuzalttiipolne whyasposhthoewsins, gwrihdic-bhacsoedmibnitneersprtheteatciloanssoicfatlhPeDpRartwiciltehs fionf gtheerpPrFin. tTinhge garnidd-abansoevderlempruelsteipnlteathioynpsoothfetshies fginrigde-rbparsiendtiningtemrparpestaatniodn tohfetheestpimarattiecdlesstoefpthleenPgFt.hTahreegwriedig-bhatseeddwreitphretsheentoaptitoimnsizoaftitohne sficnhgeemreproifntthinegGmAatposaacnhdievtheeheigsthiemraptoedsitsitoenpalcecnugrtahcya.re weighted with the optimization scheme of the Genetic Algorithm (GA) to achieve higher position accuracy
The presented algorithm can deal with natural motion behavior, including dynamic changes of standing and moving with varying step length
Summary
The automatic determination of a location in an earth-related reference system is essential in many areas of life and economy. To fuse the information sources, a Bayesian filter approach is used (Section 3) With this filter, the probability distributions of various location estimations are superimposed to get the current position and to consider the respective sensor inaccuracies. The particles of the PF are not moving freely in contrast to a classic PF [5] Instead, they are represented by localized grid cells of the building model and only the values they associated with can change (Section 4). Some building positions are more likely to represent the actual location than others for every recognized step As a result, this sequence of probable and unlikely positions will increase some grid cells’ value. In summary (Section 8), by adjusting the different uncertainty sensor profiles, the accuracy was improved by about 34% compared to the weighted sensor probability distributions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
