Abstract
Crowd density counting obtained popularity in recent years with COVID-19 and the social separation constraints that have to be enforced in public areas. Many methods and techniques can be utilized for crowd density counting. However, these techniques depend on expensive equipment and massive deployment of different sensors in the targeted area. In this work, a simple crowd density counting framework based on measuring the received signal strength (RSS) of IEEE802.11, known as, WIFI in closed areas is leveraged. An access point (AP) and a Raspberry PI kit has been located in a closed area to harvest the RSS value when people pass through the area. K-NN machine learning algorithm has been trained with different features extracted from the RSS to predict the number of people in the area. Finally, an Android smartphone App has been written to monitor the counted number to enforce the counting constraint in the closed areas. The model has been deployed in the engineering faculty. Our results show that K-NN with RSS features for passively crowd density counting achieved 88% accuracy. However, this accuracy dropped to 75% with people running scenario.
Sign-in/Register to access full text options 
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 callMore From: Periodicals of Engineering and Natural Sciences (PEN)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
