Method for counting numbers of indoor persons on basis of WiFi (wireless fidelity) channel state information and support vector machines

Abstract

The invention provides a method for counting the numbers of indoor persons on the basis of WiFi (wireless fidelity) channel state information (CSI) and support vector machine (SVM) regression. Specialhardware facilities can be omitted, and the numbers of the indoor persons can be counted only by the aid of existing WiFi wireless networks; CSI data can be denoised by the aid of DBSCAN (density-based spatial clustering of application with noise) algorithms after the CSI data are acquired, then non-zero rates of each subcarrier are obtained by the aid of expansive matrix algorithms and are usedas CSI feature fingerprint samples, accordingly, the influence of great change of signal amplitudes on person number counting can be enhanced, and influence of environmental noise on small change of the signal amplitudes can be reduced; accurate nonlinear dependency relationship models between the numbers of the persons and the CSI feature fingerprint samples can be obtained by the aid of SVM regression algorithms without consideration on complicated indoor environments, and accordingly the purpose of accurately counting the numbers of the indoor persons can be achieved. The method has the advantages that the numbers of the persons can be accurately counted on the basis of the existing WiFi wireless networks, the method is low in cost and high in universality, and the privacy problems canbe solved.

Description

technical field [0001] The invention relates to the field of people counting, in particular to a method for indoor people counting based on WiFi channel state information and a support vector machine. Background technique [0002] The number of people indoors is very important information for many applications. For example, it can help businesses determine the number of customers entering the store and arrange employees accordingly. It can monitor the crowd density in public places and initiate emergency measures in time to ensure safety. Make automatic air conditioning adjustments to save energy, etc. The traditional people counting method mainly adopts video surveillance method or wireless radio frequency method. Video monitoring methods have been widely used at present, but in low-light environments or non-line-of-sight situations, the camera cannot work well, resulting in a decrease in monitoring quality or monitoring blind spots. In addition, there are still major priv...

AI Technical Summary

Problems solved by technology

However, due to the complexity of the indoor environment, the WiFi signal has multipath effects, that is, the signal will propagate from the sending end to the receiving end through multiple paths, and each path has different delays, attenuation, and phase shifts, resulting in RSSI being a multi-path signal superposition, resulting in unstable RSSI and poor accuracy when used for people counting

Images