Towards accurate object localization with smartphones

Publication Type

Journal Article

Publication Date

9-2013

Abstract

In this study, we explore the possibility of locating remote objects via cameras together with built-in inertial sensors of off-the-shelf smartphones. Our solution, CamLoc, enables a user taking two photos of an object using a smartphone at a fixed location and immediately knowing the location of the object in global coordinates, thus facilitating myriad location-based services. Such usage is user-friendly but error prone. We devise several techniques to mitigate the errors caused by cheap and noisy sensors, upgrading the positioning accuracy to an applicable level. We prototype CamLoc on Android OS, and evaluate its performance across different scenarios with various building densities. Experiment results show that our system achieves 89 percent and 72 percent physical location mapping accuracy in rural and downtown areas, respectively, which is competitive with existing solutions.

Discipline

Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

IEEE Transactions on Parallel and Distributed Systems

Volume

25

Issue

10

First Page

2731

Last Page

2742

ISSN

1045-9219

Identifier

10.1109/TPDS.2013.236

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Additional URL

https://doi.org/10.1109/TPDS.2013.236

This document is currently not available here.

Share

COinS