Abstract: The rapid development of contactless identification technology based on Wi-Fi sensing has shown excellent application potential in the fields of intelligent human-computer interaction and intelligent security.However,it has been found that in narrow indoor scenarios,accuracy of existing lightweight identification model decreases with the shortening of transceiver distance.To solve the above problem,a close-range and contactless identification method,WiDoor,is proposed.During the data acquisition stage,WiDoor optimizes antenna deployment at receiving end based on Fresnel propagation model,and reconstructs gait information of multiple antennas to obtain the more complete gait description.In the identification stage,a lightweight convolution model,which combines the concatenated convolution module and the multi-scale convolution module,is used to reduce computational complexity while ensuring high identification accuracy.Experimental results show that WiDoor achieves identification accuracy rate of 99.1% on the 10-person dataset collected at the transceiver distance of 1 m.Moreover,parameter quantity of identification model is only 2% of those with the same identification accuracy,which outperforms other similar methods.

Key words: Wi-Fi sensing, Close-range identification, Antenna deployment optimization, Convolutional neural network