Abstract
The rising need of crowd monitoring in public spaces, especially for safety purposes, pushes the research community to propose and experiment novel methods of crowd density estimation. This paper focuses on device-free RF sensing, which does not require the monitored people to carry any electronic device. In particular, the paper proposes and assesses the performance of a crowd density estimation system based on the analysis of the variations of Channel State Information (CSI) computed from unencrypted synchronization signals transmitted by a eNodeB and reflected/scattered by people located in the monitored area. The proposed method uses features extracted from the list of singular values of the CSI secant set. This approach allows to reduce the impact of CSI variations due to noise or HW instability, improving the sensitivity to CSI variations caused by human presence. The average accuracy achieved by the proposed approach is 84%, which is comparable with the accuracy achieved with WiFi based crowd density estimation systems.
Highlights
Crowd counting systems are highly beneficial tools in several emerging applications such as: shopper analytics, where the information on how people move around in a shop can be used both for optimizing the layout of the shop and for optimizing the staff management and/or the goods organization; public safety and security, where crowd counting is fundamental for early detection of dangerous over-crowded situations; intelligent transportation systems (ITS), where bus and train schedules or boarding and payment processes may be adjusted according to the number of people waiting for the service
This paper proposes a novel approach for passive device-free crowd density estimation, based on Channel State Information (CSI) extracted from the Long Term Evolution (LTE) synchronization signals transmitted by an eNodeB
Features are extracted from the sorted list of singular values, which has been demonstrated to be strongly correlated to the number of people in the monitored room
Summary
Crowd counting systems are highly beneficial tools in several emerging applications such as: shopper analytics, where the information on how people move around in a shop can be used both for optimizing the layout of the shop and for optimizing the staff management and/or the goods organization; public safety and security, where crowd counting is fundamental for early detection of dangerous over-crowded situations; intelligent transportation systems (ITS), where bus and train schedules or boarding and payment processes may be adjusted according to the number of people waiting for the service. The paper shows a strong correlation between the number of the people and the shape of the curve achieved by the sorted list of singular values of the CSI secant set, motivating the extraction of novel features for crowd density classification. We propose to extract the CSI from the LTE signal of bandwidth of 15 MHz. We assume that the channel stays rather stationary over a slot (0.5 ms), i.e. the coherence time is equal or greater than the time slot duration (this choice is consistent with crowd density estimation scenario). 2 shows the amplitude of thousands of consecutive CSI overlapped to each other, collected for one of the antenna port and with a bandwidth 15 MHz It can be clearly observed the noisiness of the estimated channel frequency response, which rapidly fluctuates both between adjacent subcarriers and between consecutive instants of time. As discussed the filtered CSI vectors are processed to extract the features that are used by the classifier to count the number of people in a given environment
Sign-in/Register to view highlights & summary 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 callDisclaimer: 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.
