Exportar Publicação

Santos, R., Leonardo, R., Barandas, M., Moreira, D., Rocha, T., Alves, P....Gamboa, H. (2021). Crowdsourcing-based fingerprinting for indoor location in multi-storey buildings. IEEE Access. 9, 31143-31160

R. Santos et al.,  "Crowdsourcing-based fingerprinting for indoor location in multi-storey buildings", in IEEE Access, vol. 9, pp. 31143-31160, 2021

@article{santos2021_1725560343922,
	author = "Santos, R. and Leonardo, R. and Barandas, M. and Moreira, D. and Rocha, T. and Alves, P. and Oliveira, J. and Gamboa, H.",
	title = "Crowdsourcing-based fingerprinting for indoor location in multi-storey buildings",
	journal = "IEEE Access",
	year = "2021",
	volume = "9",
	number = "",
	doi = "10.1109/ACCESS.2021.3060123",
	pages = "31143-31160",
	url = "https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639"
}

TY  - JOUR
TI  - Crowdsourcing-based fingerprinting for indoor location in multi-storey buildings
T2  - IEEE Access
VL  - 9
AU  - Santos, R.
AU  - Leonardo, R.
AU  - Barandas, M.
AU  - Moreira, D.
AU  - Rocha, T.
AU  - Alves, P.
AU  - Oliveira, J.
AU  - Gamboa, H.
PY  - 2021
SP  - 31143-31160
SN  - 2169-3536
DO  - 10.1109/ACCESS.2021.3060123
UR  - https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639
AB  - The number of available indoor location solutions has been growing, however with insufficient
precision, high implementation costs or scalability limitations. As fingerprinting-based methods rely on
ubiquitous information in buildings, the need for additional infrastructure is discarded. Still, the timeconsuming manual process to acquire fingerprints limits their applicability in most scenarios. This paper
proposes an algorithm for the automatic construction of environmental fingerprints on multi-storey buildings,
leveraging the information sources available in each scenario. It relies on unlabelled crowdsourced data
from users’ smartphones. With only the floor plans as input, a demand for most applications, we apply
a multimodal approach that joins inertial data, local magnetic field and Wi-Fi signals to construct highly
accurate fingerprints. Precise movement estimation is achieved regardless of smartphone usage through
Deep Neural Networks, and the transition between floors detected from barometric data. Users’ trajectories
obtained with Pedestrian Dead Reckoning techniques are partitioned into clusters with Wi-Fi measurements.
Straight sections from the same cluster are then compared with subsequence Dynamic Time Warping
to search for similarities. From the identified overlapping sections, a particle filter fits each trajectory
into the building’s floor plans. From all successfully mapped routes, fingerprints labelled with physical
locations are finally obtained. Experimental results from an office and a university building show that this
solution constructs comparable fingerprints to those acquired manually, thus providing a useful tool for
fingerprinting-based solutions automatic setup.
ER  -