Participatory Bluetooth Scans Serving as Urban Crowd Probes

We describe a system that leverages users voluntarily having their smartphones scan the environment for discoverable Bluetooth devices to analyze crowd conditions in urban environments. Our method goes beyond mere counting of discoverable devices toward a set of more complex, robust features. We also show how to extend the analysis from crowd density to crowd flow direction. We evaluate our methods on a data set consisting of nearly 200 000 discoveries from nearly 1000 scanning devices recorded during a three day city-wide festival in Zurich. The data set also includes as ground truth 23 million global positioning system location points from nearly 30 000 users.