Analyzing Pedestrian Flows Based on Wi-Fi and Bluetooth Captures

The rapid deployment of smartphones has led to a wide adoption of wireless communication systems such as Wi-Fi and Bluetooth. Both techniques leak information to the surroundings during operation. This information has been used in literature for estimating pedestrian flows, b ut t he c orrelation t o g round truth has not yet been evaluated. Thus, a reliable deployment in real world scenarios is rather difficult. To fill in this gap, we use ground truth provided by the security check process at a major airport and evaluate the quality of crowd information gathered from Wi-Fi and Bluetooth captures. We analyze estimated pedestrian flows and present three approaches improving the accuracy compared 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. The presented approaches yield a better correlation and allow for a practical estimation of pedestrian flows.