Just-in-Time Human Gesture Recognition Using WiFi Signals  

作　　者：MENG Xianjia FENG Lin CHEN Hao CHEN Ting MA Jianfeng WANG Anwen LIU Dongdong ZHAO Yanfeng 

机构地区：[1]Shaanxi International Research Center for Passive Internet of Things,Northwest University,Xi’an 710127,China [2]China University of Labor Pelations,Beijing 100048,China [3]Chang’an University,Xi’an 710064,China [4]Xidian University,Xi’an 710071,China [5]Xi’an University of Finance and Economics,Xi’an 710100,China

出　　处：《Chinese Journal of Electronics》2021年第6期1111-1119,共9页电子学报（英文版）

基　　金：supported by National Natural Science Foundation of China (No.61702416, No.61602382, No.61802310, No.61672428, No.61772422);the Key R&D Foundation of Shaanxi Province (No.2018SF-369);the Shaan Xi Science and Technology Innovation Team Support Project (No.2018TD-O26);the China University of Labor Relations(No.20XYJS007);Shaanxi International Joint Research Centre for the Battery-free Internet of Things (No.2018SD0011);Research on Target Perception,Recognition and Imaging Based on Low-Cost Commercial Equipment Wireless Signal (No.2019KWZ-05)。

摘　　要：In-air gesture recognition using wireless signals acts as a key enabler for various applications including smart homes, remote healthcare, shared autopilot, etc. Although researchers have conducted extensive research on Wi Fi-based gesture recognition, it remains an open question of providing accurate, robust, and in-time recognition system with the commodity WiFi infrastructure. We present Fa See, a just-in-time Wi Fibased gesture recognition system by identifying the fine-grained Channel state information(CSI) features upon off-the-shelf WiFi devices. The core of Fa See is essentially a novel hybrid recognition algorithm, which combines the classical K-Means algorithm with Dynamic time warping(DTW) together, to transform the feature matching in traditional gesture recognition schemes into a hierarchical manner, thereby significantly improving the recognition efficiency. Experimental results show that Fa See recognizes 9 representative gestures with an average accuracy of 94.75% without tedious per-person training,while achieving 30% signal processing delay saving when compared with the state-of-the-arts gesture recognition schemes.

关 键 词：Gesture recognition Hierarchical matching JUST-IN-TIME 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN92[自动化与计算机技术—计算机科学与技术]