Skip to Main content Skip to Navigation
Conference papers

Device-Free People Counting Using 5 GHz Wi-Fi Radar in Indoor Environment with Deep Learning

Ali El Amine 1, 2 Valery Guillet
2 ADOPNET - Advanced technologies for operated networks
UR1 - Université de Rennes 1, IMT Atlantique - IMT Atlantique Bretagne-Pays de la Loire, IRISA-D2 - RÉSEAUX, TÉLÉCOMMUNICATION ET SERVICES
Abstract : People counting plays an important role in many people-centric applications including crowd control, traffic management and smart home energy management. With the advancements in wireless sensing, it is now possible to intelligently sense the presence of people with wireless signals. Yet, a lot of challenges arise when Wi-Fi solutions are used for counting humans due to the uncertainty of the states in the environment. In this paper, we propose a novel 3D-Convolutional Neural Network (3D-CNN) architecture able to extract features from range-Doppler images to count the number of people present in an indoor environment by detecting their movements. We generate the range-Doppler images from a Celeno Wi-Fi pulse Doppler radar that uses the 5 GHz frequency band. To the best of our knowledge, this work is the first to count people based on a Wi-Fi Doppler radar. Our experimental results show that our deep learning model is able to estimate the number of people for up to four with an average accuracy of 89%.
Complete list of metadata

https://hal-imt-atlantique.archives-ouvertes.fr/hal-03147898
Contributor : Ali El Amine <>
Submitted on : Sunday, February 21, 2021 - 11:16:50 AM
Last modification on : Wednesday, July 21, 2021 - 7:40:02 AM
Long-term archiving on: : Saturday, May 22, 2021 - 6:04:16 PM

File

Device-Free People Counting Us...
Files produced by the author(s)

Identifiers

Citation

Ali El Amine, Valery Guillet. Device-Free People Counting Using 5 GHz Wi-Fi Radar in Indoor Environment with Deep Learning. 2020 IEEE Globecom Workshops (GC Wkshps): IEEE GLOBECOM 2020 Workshop on AI-driven Smart Healthcare (GC 2020 Workshop - AIdSH), IEEE, Dec 2020, Taipei, Taiwan. ⟨10.1109/GCWkshps50303.2020.9367393⟩. ⟨hal-03147898⟩

Share

Metrics

Record views

25

Files downloads

42