Abstract
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.
Highlights
Crowd management is an integral aspect of the organization of any type of large-scale event.Special attention needs to be paid to the layout of the event environment(s) in order to ensure the safety and comfort of the attendees and to decrease the risk of crowd disasters occurring
Results indicated that it was feasible to create an automatic crowd estimation system based on a passive Radio Frequency (RF) sensor network, with over 90% of pnn estimates being at most 1 category removed from the visual estimates
Our initial study based on measurements performed within the Freedom Stage at the 2017 edition of the music festival Tomorrowland showed that the use of a passive RF sensing approach for large-scale crowd estimation was feasible
Summary
Crowd management is an integral aspect of the organization of any type of large-scale event. The resulting smoothed out crowd categorizations were assigned to the crowds at certain timestamps corresponding to the moments when the images were taken While it could hardly be considered a reliable ground truth, this ‘visual validation’ data enabled us to investigate whether a passive RF-based system could perform at least as well as a large set of human eyes. We will make use of the available ground truth and maximum environment capacity data in combination with a linear regression-based approach to perform actual crowd count estimations.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
