Indoor Wi-Fi multi-person detection method based on path separation

Abstract

The invention discloses an indoor Wi-Fi multi-person detection method based on path separation, and the method comprises the following steps: 1), constructing a Wi-Fi signal system which comprises a signal transmitting and receiving device, the signal transmitting and receiving device is provided with an antenna array, a signal transmitting and receiving device collects a channel state information (CSI) matrix and a receiving signal; 2) constructing a joint probability model of multi-dimensional parameters according to the CSI matrix obtained in the step 1) and a received signal, and searching and obtaining the multi-dimensional parameters of single paths with different intensities according to the joint probability model of the multi-dimensional parameters; (3) extracting all reflection path parameters and the number of paths by using the multi-dimensional parameters of the single path with the maximum intensity; and 4) carrying out indoor Wi-Fi dynamic and static mixed state multi-person detection according to the extracted all reflection path parameters and path quantity, and the method can carry out Wi-Fi indoor multi-person detection, and is strong in environmental adaptability and high in detection precision.

Description

technical field [0001] The invention belongs to the field of wireless perception, and relates to an indoor Wi-Fi multi-person detection method based on path separation. Background technique [0002] Indoor human detection is fundamental to many practical applications such as security surveillance, behavior analysis, and elderly care. A variety of positioning and tracking technologies have emerged, including ultrasound, infrared, cameras, and LED visible light. But they have limitations such as narrow line-of-sight signal coverage and difficult deployment. Other solutions usually require the target to carry special equipment, which is inconvenient or even not feasible in situations such as elderly care, burglary, etc. And wireless device-based solutions have unique advantages in these areas, and wireless device-based solutions have unique advantages in these areas, such systems receive and process Wi-Fi signals reflected by nearby objects to obtain information from nearby r...

AI Technical Summary

Problems solved by technology

[0006] 1. Fingerprint-based methods require a lot of training and have low environmental adaptability;

[0007] 2. The detection accuracy of the method using single-dimensional information is low, and the method based on time-of-flight requires precise synchronization of hardware devices;

[0008] 3. It can only detect a single dynamic target, and cannot accurately detect static targets and multiple targets

Images