Estimating crowd densities and pedestrian flows using wi-fi and bluetooth

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 WiFi 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.