Real-Time Privacy Preserving Crowd Estimation Based on Sensor Data

Longo, Salvatore; Cheng, Bin

doi:10.1109/mobserv.2016.24

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are dependent of the actual spatial distribution of people inside the building, therefore using the estimations from previous time periods would be a serious source of error. In this regard, our approach is radically different from approaches that try to model the signal propagation dependence on the presence of people in the propagation space [9,28,29,30,46], and approaches that build image understanding models from optical sensors, either on the visible [4,10,11,13,17] or infrared [6,23] light range. In these approaches, the data is used to build a predictor of the number of people depending on signal features, so that careful experimental design for training data gathering is required.…”

Section: Discussionmentioning

confidence: 99%

Indoor Crowd 3D Localization in Big Buildings from Wi-Fi Access Anonymous Data

Kamińska-Chuchmała

Graña

2019

Sensors

View full text Add to dashboard Cite

Indoor crowd localization and counting in big public buildings pose problems of infrastructure deployment, signal processing, and privacy. Conventional approaches based on optical cameras, either in the visible or infrared range, received signal strength in wireless networks, sound or chemical sensing in sensor networks need careful calibration, noise removal, and sophisticated data processing to achieve results in limited scenarios. Moreover, personal data protection is a growing concern, so that detection methods that preserve the privacy of people are highly desirable. The aim of this paper is to provide a technique that may generate estimations of the localization of people in a big public building using anonymous data from already-deployed Wi-Fi infrastructure. We present a method applying geostatistical techniques to the access data acquired from Access Points (AP) in an open Wi-Fi network. Specifically, only the time series of the number of accesses per AP is required. Geostatistical methods produce a 3D high-quality spatial distribution representation of the people inside the building based on the interaction of their mobile devices with the APs. We report encouraging results obtained from data acquired at a building of Wroclaw University of Science and Technology.

show abstract