In-Air Handwriting by Passive Gesture Tracking Using Commodity WiFi

被引:23
作者
Han, Zijun [1 ,2 ,3 ]
Lu, Zhaoming [1 ,2 ,3 ]
Wen, Xiangming [1 ,2 ,3 ]
Zhao, Jingbo [1 ,2 ,3 ]
Guo, Lingchao [1 ,2 ,3 ]
Liu, Yue [1 ,2 ,3 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Informat & Commun Engn, Beijing 100876, Peoples R China
[2] Beijing Univ Posts & Telecommun, Beijing Key Lab Network Syst Architecture & Conve, Beijing 100876, Peoples R China
[3] Beijing Univ Posts & Telecommun, Beijing Lab Adv Informat Networks, Beijing 100876, Peoples R China
基金
中国国家自然科学基金;
关键词
Tracking; Wireless fidelity; Antennas; Transceivers; Calibration; Dynamics; Wireless communication; Channel state information; human-computer interaction; handwriting; gesture tracking;
D O I
10.1109/LCOMM.2020.3007982
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Recent years have witnessed the great potential of adopting Channel State Information (CSI) for human-computer interaction by gestures. However, most current solutions either depend on specialized hardware or demand priori learning of wireless signal patterns, which face critical downsides in availability, reliability and extensibility. Hence this letter presents AirDraw, a novel learning-free in-air handwriting system by passive gesture tracking using only three commodity WiFi devices. First, we denoise CSI measurements by the ratio between two close-by antennas, and further separate the reflected signal from noise by performing Principal Component Analysis. Besides, we propose a robust signal calibration algorithm for tracking correction by eliminating the static components unrelated to hand motion. The prototype of AirDraw is fully realized and evaluated in real scenario. Extensive experiments yield that AirDraw can track user's hand trace with a median error lower than 2.2 cm.
引用
收藏
页码:2652 / 2656
页数:5
相关论文
共 15 条
[1]   See Through Walls with Wi-Fi! [J].
Adib, Fadel ;
Katabi, Dina .
ACM SIGCOMM COMPUTER COMMUNICATION REVIEW, 2013, 43 (04) :75-86
[2]   Writing in the Air with WiFi Signals for Virtual Reality Devices [J].
Fu, Zhangjie ;
Xu, Jiashuang ;
Zhu, Zhuangdi ;
Liu, Alex X. ;
Sun, Xingming .
IEEE TRANSACTIONS ON MOBILE COMPUTING, 2019, 18 (02) :473-484
[3]  
Guo LL, 2019, INT C ELECTR MACH SY, P3499, DOI [10.1109/icems.2019.8921843, 10.1109/cciot48581.2019.8980294, 10.1109/CCIOT48581.2019.8980294]
[4]   From Signal to Image: Capturing Fine-Grained Human Poses With Commodity Wi-Fi [J].
Guo, Lingchao ;
Lu, Zhaoming ;
Wen, Xiangming ;
Zhou, Shuang ;
Han, Zijun .
IEEE COMMUNICATIONS LETTERS, 2020, 24 (04) :802-806
[5]   Predictable 802.11 Packet Delivery from Wireless Channel Measurements [J].
Halperin, Daniel ;
Hu, Wenjun ;
Sheth, Anmol ;
Wetherall, David .
ACM SIGCOMM COMPUTER COMMUNICATION REVIEW, 2010, 40 (04) :159-170
[6]  
Han Z., 2020, IEEE WCNC, P1
[7]  
Leap motion, LEAP MOT MAC PC GEST
[8]   Low-Effort Place Recognition with WiFi Fingerprints Using Deep Learning [J].
Nowicki, Michal ;
Wietrzykowski, Jan .
AUTOMATION 2017: INNOVATIONS IN AUTOMATION, ROBOTICS AND MEASUREMENT TECHNIQUES, 2017, 550 :575-584
[9]   Whole-Home Gesture Recognition Using Wireless Signals (Demo) [J].
Pu, Qifan ;
Jiang, Siyu ;
Gollakota, Shyamnath .
ACM SIGCOMM COMPUTER COMMUNICATION REVIEW, 2013, 43 (04) :485-486
[10]   WiDraw: Enabling Hands-free Drawing in the Air on Commodity WiFi Devices [J].
Sun, Li ;
Sen, Souvik ;
Koutsonikolas, Dimitrios ;
Kim, Kyu-Han .
MOBICOM '15: PROCEEDINGS OF THE 21ST ANNUAL INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND NETWORKING, 2015, :77-89