Recognition of crowd behavior from mobile sensors with pattern analysis and graph clustering methods

Abstract

Mobile on-body sensing has distinct advantages for the analysis and understanding of crowd dynamics: sensing is not geographically restricted to a specific instrumented area, mobile phones offer on-body sensing and they are already deployed on a large scale, and the rich sets of sensors they contain allows one to characterize the behavior of users through pattern recognition techniques.In this paper we present a methodological framework for the machine recognition of crowd behavior from on-body sensors, such as those in mobile phones. The recognition of crowd behaviors opens the way to the acquisition of largescale datasets for the analysis and understanding of crowd dynamics. It has also practical safety applications by providing improved crowd situational awareness in cases of emergency.The framework comprises: behavioral recognition with the user's mobile device, pairwise analyses of the activity relatedness of two users, and graph clustering in order to uncover globally, which users participate in a given crowd behavior. We illustrate this framework for the identification of groups of persons walking, using empirically collected data.We discuss the challenges and research avenues for theoretical and applied mathematics arising from the mobile sensing of crowd behaviors.2000 Mathematics Subject Classification. Primary: 68T10, 91-04, 91-02, 91D30, 62H30; Secondary: 91C20, 93A15, 93A30.

Asymmetric Pedestrian Dynamics on a Staircase Landing from Continuous Measurements

“…Several geometric configurations and flow scenarios have been studied in controlled laboratory conditions, such as corridors, bottlenecks, intersections and T-junctions dynamics [1,15,16]. More recently, 3D-range cameras and wireless sensors enabled reliable measurements in real-life conditions [3,4,11,9], allowing for data collection with reduced (potential) influences of laboratory environments. Notably, these technologies are privacy-safe, as recorded pedestrians are not identifiable, thus, unlimited data collections, e.g., via long term measurement campaigns [4] are possible.…”

Frame vs. Trajectory Analyses of Pedestrian Dynamics Asymmetries in a Staircase Landing

“…We bin the detection set {d} with respect to the longitudinal position x between x = −1 m and x = 0.8 m in 40 equal bins. For each bin we consider the distribution of transversal positions y x (where the x subscript indicates the dependence on the bin), and we take the 15 th and 85 th percentiles (indicated by y x, 15 and y x,85 ) of the distribution to define the preferred position band.…”

“…Real-life condition measurements, recently tackled via, e.g., wireless sensors [15] or, as here, via 3D sensors [10,12,13], likely eliminate potential behavioral biases introduced by a laboratory environment, such as the awareness of being part of a scientific experiment. Furthermore, measurements in real-life enable and are necessary if one aims at resolved statistical descriptions of physical observables (e.g., positions, velocities, accelerations) or to quantify related rare events [16,17].…”

From the Microscale to Collective Crowd Dynamics

“…On the other hand, the behavioral influence of panic conditions can play an important role in the modification of the usual dynamics [19,20]. This objective can be pursued by an appropriate tuning of the model proposed in this paper also by taking advantage of recent studies on the behavioral dy- namics of pedestrians [25,27], and evolutive game theory [11]. Accordingly, the guidelines toward this important objective are given:…”