Passive detection method of indoor personnel based on wi-fi

Abstract

The invention discloses a passive detection method for indoor personnel based on Wi-Fi. Establish a reasonable indoor measurement point distribution in the offline stage, complete the data collection in the offline stage, and select a part of the measurement point data for offline training; export the original data and perform noise reduction processing on it, generate a probability density function PDF, and determine the threshold δ; Use the sliding window and calculate the sliding window correlation coefficient matrix of each receiving antenna; calculate the correlation coefficient matrix TT of the data received by the receiving antenna in the online state, draw the PDF image of the matrix TT, compare the highest point of the image with the threshold δ, and judge the test Whether the state is a static state determines the specific state of the target in the current scene. Based on the fine-grained physical layer information CSI, the present invention calculates the correlation between subcarriers in the frequency domain to generate fingerprints, avoiding the influence of environmental factors on the wireless signal in the time domain, and the threshold and voting methods determined by multiple trainings can reduce errors. The emergence of the report, the detection accuracy is higher.

Description

technical field [0001] The invention belongs to the field of wireless sensor networks, and relates to a Wi-Fi-based passive detection method for indoor personnel to solve the problems that existing passive personnel detection methods are greatly affected by environmental changes, and the detection accuracy and robustness are insufficient. When the existence of the target is detected, further judgment is made on the current active state of the target. Background technique [0002] With the rapid development of network technology, wireless signals are basically everywhere in every corner of life. Nowadays, the time for people to carry out outdoor activities and work is gradually reduced, and most activities are carried out indoors, such as work, eating, shopping, entertainment and so on. The passive indoor occupant detection method based on Channel State Information (CSI) features can be applied to smart home, medical monitoring, security detection, etc. [0003] In an indoo...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problem that the existing method can only detect the unmanned state of the scene and the existence of dynamic target state, and the fingerprint extracted in the time domain is affected by environmental factors and multipath effects.

Images