Stijn Denis

Dense urban environments pose significant challenges when it comes to detecting and measuring crowd size due to their nature of being free-flow environments containing many dynamic factors. In this paper, we use a wireless sensor network (WSN) to perform device-free crowd size estimation in a subway station. Our sensing solution uses the change in attenuation of the communication links between sensor nodes to estimate the number of people standing on the platform. In order to achieve this, we use the same attenuation information coming from the WSN to detect the presence of a rail vehicle in the station and compensate for the channel fading caused by the introduced rail vehicle. We make use of two separately trained regression models depending on the presence or absence of a rail vehicle to estimate the people count. The detection of rail vehicles occurred with a near-perfect accuracy. When evaluating the resulting estimation model on our test set, we achieved a mean average error of 3.567 people, which is a significant improvement over 6.192 people when using a single regression model. This demonstrates that device-free sensing technologies can be successfully implemented in dynamic environments by implementing detection techniques and using different regression models depending on the environment’s state.

The majority of radio frequency crowd estimation systems are tested with at most a few tens of human individuals. At the same time, they are particularly useful for crowd safety management for events with hundreds or thousands of visitors. We deployed our passive crowd estimation system in two environments at a 400 000-visitor music festival. This paper describes our system’s architecture and compares our results to those of an access control system. We found a correlation coefficient of 0.97 between our system and the access control system. Additionally, we show that we can estimate the crowd size correctly up to a few hundred individuals. A system such as ours can provide a direct objective measurement to security personnel who are currently making estimates under stress and influenced by experience, view angle, and occlusions.

Organisers of events attracting many people have the important task to ensure the safety of the crowd on their venue premises. Measuring the size of the crowd is a critical first step, but often challenging because of occlusions, noise and the dynamics of the crowd. We have been working on a passive Radio Frequency (RF) sensing technique for crowd size estimation, and we now present three datasets of measurements collected at the Tomorrowland music festival in environments containing thousands of people. All datasets have reference data, either based on payment transactions or an access control system, and we provide an example analysis script. We hope that future analyses can lead to an added value for crowd safety experts.

The creation of an automatic crowd estimation system capable of providing reliable, real-time estimates of human crowd sizes would be an invaluable tool for organizers of large-scale events, particularly so in the context of safety management. We describe a set of experiments in which we installed a passive Radio Frequency (RF) sensor network in different environments containing thousands of human individuals and discuss the accuracy with which the resulting measurements can be used to estimate the sizes of these crowds. Depending on the selected training approach, a median crowd estimation error of 184 people could be obtained for a large scale environment which contained 3227 people at its peak. Additionally, we look into the potential benefits of dividing one of our experimental environments into multiple subregions and open up a potentially interesting new topic of research regarding the estimation of crowd flows. Finally, we investigate the combination of our measurements with another sources of crowd-related data: sales data from drink stands within the environment. In doing so, we aim to integrate the concept of an automatic RF-based crowd estimation system into the broader domain of crowd analysis.

The requirement of active localization techniques to attach a hardware device to the targets that need to be located can be difficult or even impossible for certain applications. For this reason, there has been an increasing interest in tagless or device-free localization (DFL) approaches. In particular, the research domain of RF-based device-free localization has been steadily evolving since its inception slightly over a decade ago. Many novel techniques have been developed regarding the three core aspects of DFL: detection, tracking, and identification. The increasing use of channel state information (CSI) has contributed considerably to these developments. In particular, the progress it enabled regarding the exceptionally difficult `identification problem’ has been highly impressive. In this survey, we provide a comprehensive overview of this evolutionary process, describe essential DFL concepts and highlight several key techniques whose creation marked important milestones within this field of research. We do so in a structured manner in which each technique is categorized according to the DFL core aspect it emphasizes most. Additionally, we discuss current blocking issues within the state-of-the-art and suggest multiple high-level research directions which will aid in the search towards eventual solutions.