Large scale crowd density estimation using a sub-GHz wireless sensor network

Automatic crowd density estimation can be very useful for a multitude of applications such as traffic control or crowd control systems during large-scale events. Classic camera-based setups have several shortcomings, the most notorious of which is the privacy issue. The use of a crowd estimator which makes use of a wireless sensor network (WSN) can provide a potential solution to this problem. We deployed a sub-GHz (433 MHz & 868 MHz) wireless sensor network in an indoor stage at a music festival. Visual validation was established by a team of volunteers who manually analyzed a large set of low-quality camera images which were taken during the event. Next, RSS measurements obtained by the network were classified into different density-based categories by a simple probabilistic neural network. Results indicate that the system is capable of estimating the crowd density with a high accuracy, proving the feasibility of using a WSN for such a task.

Publication year:2018

Keywords:P1 Proceeding

BOF-keylabel:yes

Authors from:Higher Education

Accessibility:Closed