Three-dimensional(3D)human pose tracking has recently attracted more and more attention in the computer vision field.Real-time pose tracking is highly useful in various domains such as video surveillance,somatosensory games,and human-computer interaction.However,vision-based pose tracking techniques usually raise privacy concerns,making human pose tracking without vision data usage an important problem.Thus,we propose using Radio Frequency Identification(RFID)as a pose tracking technique via a low-cost wearable sensing device.Although our prior work illustrated how deep learning could transfer RFID data into real-time human poses,generalization for different subjects remains challenging.This paper proposes a subject-adaptive technique to address this generalization problem.In the proposed system,termed Cycle-Pose,we leverage a cross-skeleton learning structure to improve the adaptability of the deep learning model to different human skeletons.More-over,our novel cycle kinematic network is proposed for unpaired RFID and labeled pose data from different subjects.The Cycle-Pose system is implemented and evaluated by comparing its prototype with a traditional RFID pose tracking system.The experimental results demonstrate that Cycle-Pose can achieve lower estimation error and better subject generalization than the traditional system.

Chao Yang;Xuyu Wang;Shiwen Mao

Dept of Electrical and Computer Engineering,Auburn University,Auburn,AL,36849-5201,USA;Dept of Computer Science,California State University,Sacramento,CA,95819-6021,USA

数字通信与网络（英文）

[1]Chao Yang;Xuyu Wang;Shiwen Mao-.RFID-based 3D human pose tracking:A subject generalization approach)[J].数字通信与网络（英文）,2022(03):278-288

RFID,human,tracking,generalization,approach,Three,dimensional,has,recently,attracted,more,attention,computer,vision,field,Real,highly,useful,various,domains,such,video,surveillance,somatosensory,games,interaction,However,techniques,usually,raise,privacy,concerns,making,without,data,usage,important,problem,Thus,using,Radio,Frequency,Identification,via,cost,wearable,sensing,device,Although,our,prior,illustrated,how,deep,learning,could,transfer,into,real,different,subjects,remains,challenging,This,paper,proposes,adaptive,address,this,In,proposed,system,termed,Cycle,Pose,leverage,cross,structure,improve,adaptability,model,skeletons,More,over,novel,cycle,kinematic,network,unpaired,labeled,from,implemented,evaluated,by,comparing,its,prototype,traditional,experimental,results,demonstrate,that,can,achieve,lower,estimation,error,better,than

0.577083