Estimating Crowd Densities and Pedestrian Flows Using Wi-Fi and Bluetooth

Abstract

The rapid deployment of smartphones as all-purpose mobile computing systems has led to a wide adoption of wireless communication systems such as Wi-Fi and Bluetooth in mobile scenarios. Both communication systems leak information to the surroundings during operation. This information has been used for tracking and crowd density estimations in literature. However, an estimation of pedestrian flows has not yet been evaluated with respect to a known ground truth and, thus, a reliable adoption in real world scenarios is rather difficult. With this paper, we fill in this gap. Using ground truth provided by the security check process at a major German airport, we discuss the quality and feasibility of pedestrian flow estimations for both Wi-Fi and Bluetooth captures. We present and evaluate three approaches in order to improve the accuracy in comparison to a naive count of captured MAC addresses. Such counts only showed an impractical Pearson correlation of 0.53 for Bluetooth and 0.61 for Wi-Fi compared to ground truth. The presented extended approaches yield a superior correlation of 0.75 in best case. This indicates a strong correlation and an improvement of accuracy. Given these results, the presented approaches allow for a practical estimation of pedestrian flows.

Building up knowledge through passive WiFi probes

“…7 we set k equal to 2 in our case: the resulting cluster centers are the two feature vectors [1 0 0 0 0] and [1 1 0 1 0]. As one can see, the first cluster is [1][2][3][4][5][6][7][8][9][10][11][12] identified by users which are detected for a short period of time (the first bin is present), but never return. We denote this first cluster as the group of passers-by users.…”

“…The work in [3] targets pedestrian flow estimation across the security check in an airport. Several non-supervised learning approaches are proposed and qualitatively compared against a proxy measure for the flows and density, that is, the number of boarding pass scans performed at the security check at given time intervals.…”

“…In such phase, each end device broadcasts a probe request management frame to stimulate in-range APs to manifest themselves (replying with a probe reply management frame). Such probe requests are usually broadcasted in sequence on all the available WiFi channels (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12)(13)(14). The set of information which is contained in (or can be easily extracted by) probe request frames include the Medium Access Control (MAC) address of the sending device, the Received Signal Strength Indicator (RSSI) out of the transmission of the frame and the Preferred Network List (PNL), that is a list of Service Set IDentifiers (SSID) of the WIFi networks which are already known by the sending device.…”

“…The model parameters are empirically estimated for the test environment through an exhaustive measurement campaign. Namely, for all the possible combinations of parameters p 0 and α, the position of the [1][2][3][4][5][6][7][8][9][10][11][12] reference user, that is the vector coordinates of the cell the user lives in, x , is then estimated by solving the following regularized least-square problem.…”

“…Computer Communications 117 (2018) [1][2][3][4][5][6][7][8][9][10][11][12] average probe request emission frequency for idle terminals is in the range of one probe every 2-5 minutes. A similar behavior has been observed also in our datasets.…”