TY - GEN
T1 - No need to war-drive
T2 - 10th International Conference on Mobile Systems, Applications, and Services, MobiSys'12
AU - Wang, He
AU - Sen, Souvik
AU - Elgohary, Ahmed
AU - Farid, Moustafa
AU - Youssef, Moustafa
AU - Choudhury, Romit Roy
N1 - Copyright:
Copyright 2013 Elsevier B.V., All rights reserved.
PY - 2012
Y1 - 2012
N2 - We propose UnLoc, an unsupervised indoor localization scheme that bypasses the need for war-driving. Our key observation is that certain locations in an indoor environment present identifiable signatures on one or more sensing dimensions. An elevator, for instance, imposes a distinct pattern on a smartphone's accelerometer; a corridor-corner may overhear a unique set of WiFi access points; a specific spot may experience an unusual magnetic fluctuation. We hypothesize that these kind of signatures naturally exist in the environment, and can be envisioned as internal landmarks of a building. Mobile devices that "sense" these landmarks can recalibrate their locations, while dead-reckoning schemes can track them between landmarks. Results from 3 different indoor settings, including a shopping mall, demonstrate median location errors of 1:69m. War-driving is not necessary, neither are floorplans the system simultaneously computes the locations of users and landmarks, in a manner that they converge reasonably quickly. We believe this is an unconventional approach to indoor localization, holding promise for real-world deployment.
AB - We propose UnLoc, an unsupervised indoor localization scheme that bypasses the need for war-driving. Our key observation is that certain locations in an indoor environment present identifiable signatures on one or more sensing dimensions. An elevator, for instance, imposes a distinct pattern on a smartphone's accelerometer; a corridor-corner may overhear a unique set of WiFi access points; a specific spot may experience an unusual magnetic fluctuation. We hypothesize that these kind of signatures naturally exist in the environment, and can be envisioned as internal landmarks of a building. Mobile devices that "sense" these landmarks can recalibrate their locations, while dead-reckoning schemes can track them between landmarks. Results from 3 different indoor settings, including a shopping mall, demonstrate median location errors of 1:69m. War-driving is not necessary, neither are floorplans the system simultaneously computes the locations of users and landmarks, in a manner that they converge reasonably quickly. We believe this is an unconventional approach to indoor localization, holding promise for real-world deployment.
KW - landmarks
KW - location
KW - mobile phones
KW - recursion
KW - sensing
UR - http://www.scopus.com/inward/record.url?scp=84864335859&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864335859&partnerID=8YFLogxK
U2 - 10.1145/2307636.2307655
DO - 10.1145/2307636.2307655
M3 - Conference contribution
AN - SCOPUS:84864335859
SN - 9781450313018
T3 - MobiSys'12 - Proceedings of the 10th International Conference on Mobile Systems, Applications, and Services
SP - 197
EP - 210
BT - MobiSys'12 - Proceedings of the 10th International Conference on Mobile Systems, Applications, and Services
Y2 - 25 June 2012 through 29 June 2012
ER -