SmartLoc: Sensing Landmarks Silently for Smartphone Based Metropolitan Localization

TL;DR

SmartLoc is a smartphone localization system that combines inertial sensors, GPS, landmarks, and driving patterns to improve accuracy in urban environments, especially when GPS signals are weak.

Contribution

SmartLoc introduces a novel method integrating inertial sensors, GPS, landmarks, and driving patterns with linear regression for enhanced urban localization accuracy.

Findings

Achieves approximately 20m error for 90% of the time.

Significantly outperforms GPS alone with a lower mean error.

Demonstrates effectiveness in city environments.

Abstract

We present \emph{SmartLoc}, a localization system to estimate the location and the traveling distance by leveraging the lower-power inertial sensors embedded in smartphones as a supplementary to GPS. To minimize the negative impact of sensor noises, \emph{SmartLoc} exploits the intermittent strong GPS signals and uses the linear regression to build a prediction model which is based on the trace estimated from inertial sensors and the one computed from the GPS. Furthermore, we utilize landmarks (e.g., bridge, traffic lights) detected automatically and special driving patterns (e.g., turning, uphill, and downhill) from inertial sensory data to improve the localization accuracy when the GPS signal is weak. Our evaluations of \emph{SmartLoc} in the city demonstrates its technique viability and significant localization accuracy improvement compared with GPS and other approaches: the error is approximately 20m for 90% of time while the known mean error of GPS is 42.22m.