Please wait a minute...
浙江大学学报(工学版)
Journal of ZheJiang University (Engineering Science)  2023, Vol. 57 Issue (2): 415-425    DOI: 10.3785/j.issn.1008-973X.2023.02.020
    
Optimal tag selection method for device-free human tracking system
Jian-sha LU(),Qin BAO,Hong-tao TANG,Yi-ping SHAO,Wen-bin ZHAO
College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou 310023, China
Download: HTML     PDF(1716KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A device-free human tracking method based on selected tags was proposed to address the problems of existing human tracking systems, such as large tracking errors, large changes to the environment caused by hardware deployment, and inconvenience for users to wear the device. The radio frequency (RF) power signals of the human body at different positions were collected, and the relationship between the positions of the human body and the power signal was analyzed. In order to mitigate the effect of signal instability on the system, the features of the RF power signal were extracted as the dataset for model training. Different deep learning models were established by using the features of the RF power signal, and the tracking results and label usage under different training methods were compared to select the appropriate model structure and training method. The general opinion and the specific steps of the optimal tag selection method were given after analyzing the experimental results. Experimental results show that the location system based on the optimal tag selection method is feasible. The tracking error was 0.19 m, which was about 5 cm lower than that of the WallSense system, and the number of tags was reduced by 66.7%. The impact of tag deployment on the environment was obviously reduced, and the tag redundancy was reduced while the accuracy was ensured.

Key words： device-free tracking      signal feature      optimal tag selection      deep learning      radio frequency identification     
Received: 09 August 2021      Published: 28 February 2023
CLC:  TP 399  
Fund:  浙江省重点研发计划资助项目（2018C01003）
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Jian-sha LU
Qin BAO
Hong-tao TANG
Yi-ping SHAO
Wen-bin ZHAO
Cite this article:

Jian-sha LU,Qin BAO,Hong-tao TANG,Yi-ping SHAO,Wen-bin ZHAO. Optimal tag selection method for device-free human tracking system. Journal of ZheJiang University (Engineering Science), 2023, 57(2): 415-425.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2023.02.020     OR     https://www.zjujournals.com/eng/Y2023/V57/I2/415


无设备人体追踪系统的择优标签方法

针对现有人体追踪系统追踪误差大、硬件部署对环境改变大和用户佩戴设备不方便等问题，提出基于择优标签的无设备人体追踪方法. 采集人体在不同位置上的射频(RF)功率信号，分析人体所在位置与功率信号之间的关系. 为了减缓信号不稳定性对系统的影响，提取射频功率信号的特征作为模型训练的数据集. 利用信号特征建立不同的深度学习模型，对比不同训练方式下的追踪效果和标签用量，选择合适的模型结构和训练方式. 分析实验结果，给出普适性意见和最优标签选择方法的具体步骤.实验表明，基于择优标签方法的定位系统是可行的，其中跟踪误差为0.19 m，与表现较好的WallSense系统相比，跟踪误差降低约5 cm，标签量降低66.7%. 基于择优标签方法的定位系统明显降低了标签部署对环境的影响，在保证精度的情况下，减少了标签冗余.


关键词： 无设备追踪,  信号特征,  标签择优,  深度学习,  射频识别 
Fig.1 Flowchart of optimal tag selection method
Fig.2 Extraction of mean and variance of RSSI
Fig.3 Signal collection of testers in monitoring area
Fig.4 Human influence on distribution of power signal features
Fig.5 Recurrent neural network structure
Fig.6 Schematic diagram of seq2seq structure
Fig.7 Addition of additional information and splicing with hidden layers
Fig.8 Amount of calculating weight and state
Fig.9 Attention calculation process
Fig.10 seq2seq combined with attention structure
Fig.11 Schematic diagram of tossing coin to determine input
Fig.12 Multiple decay processes of parameter p
训练方式 A/% ttrain/min
自身推断 86.36 145.6
真实标签 86.60 145.6
线性衰减 88.53 123.6
指数衰减 87.25 181.4
恒定值 87.55 145.6
反向sigmoid衰减 86.23 163.5
Tab.1 Sequence accuracy rate of different training methods
位置 标签
tag1 tag2 tag3 tag4 tag5 tag6
L1 97.34 98.29 99.33 99.90 85.16 99.76
L2 98.96 95.41 94.64 98.10 94.89 99.03
L3 99.32 98.59 95.19 99.61 93.49 98.40
L4 99.76 94.23 88.29 98.22 96.07 99.76
L5 100.00 95.58 93.57 99.93 99.71 98.72
Tab.2 Classification accuracy of all tags with RNN as structural unit
位置 标签
tag1 tag2 tag3 tag4 tag5 tag6
L1 97.05 99.38 98.81 99.38 84.44 99.71
L2 99.17 95.79 92.68 97.79 94.72 99.55
L3 99.47 97.13 92.42 99.12 95.14 99.12
L4 99.73 95.53 90.54 97.40 96.41 99.69
L5 99.81 96.21 93.48 99.78 99.66 99.37
Tab.3 Classification accuracy of all tags with GRU as structural unit
位置 标签
tag1 tag2 tag3 tag4 tag5 tag6
L1 97.05 99.38 98.81 99.38 84.44 99.71
L2 99.17 95.79 92.68 97.79 94.72 99.55
L3 99.47 97.13 92.42 99.12 95.14 99.12
L4 99.73 95.53 90.54 97.40 96.41 99.69
L5 99.81 96.21 93.48 99.78 99.66 99.37
Tab.4 Classification accuracy of all tags with LSTM as structural unit
网络单元 As/% Ap/% No/个
GRU 99.55 99.93 4
LSTM 99.25 99.88 5
RNN 99.88 99.98 6
Tab.5 Results of 3 units in 4000 sequences and 24000 positions
Fig.13 Amount of errors of different units on test set
Fig.14 Filtered tag layout
Fig.15 ImpinjM4 passive tag and VFR4 reader
Fig.16 Three paths in test environment
Fig.17 Layout of optimal tag after filtering
Fig.18 Flow chart of tracking stage after optimal tag selection
[1]   LIU W, LI F, JING C, et al Recognition and location of typical automotive parts based on the RGB-D camera[J]. Complex and Intelligent Systems, 2021, 7 (4): 1759- 1765
doi: 10.1007/s40747-020-00182-z
[2]   LIM S, LEE S, JUNG J, et al Detection and localization of people inside vehicle using impulse radio ultra-wideband radar sensor[J]. IEEE Sensors Journal, 2019, 20 (7): 3892- 3901
[3]   SHOAIB M, BOSCH S, INCEL O D, et al Fusion of smartphone motion sensors for physical activity recognition[J]. Sensors, 2014, 14 (6): 10146- 10176
doi: 10.3390/s140610146
[4]   LIU H, DARABI H, BANERJEE P, et al Survey of wireless indoor positioning techniques and systems[J]. IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews, 2007, 37 (6): 1067- 1080
doi: 10.1109/TSMCC.2007.905750
[5]   NI L M, LIU Y, LAU Y C, et al. LANDMARC: indoor location sensing using active RFID [C]// 1st IEEE International Conference on Pervasive Computing and Communications. Fort Worth: IEEE, 2003: 407-417.
[6]   YANG L , CHEN Y , LI X Y , et al. Tagoram: real-time tracking of mobile RFID tags to high precision using COTS devices [C]// 20th ACM Annual International Conference on Mobile Computing and Networking (MobiCom). Maui: ASSOC Computing Machinery, 2014: 237-248.
[7]   SHEN L, ZHANG Q, PANG J, et al ANTspin: efficient absolute localization method of RFID tags via spinning antenna[J]. Sensors, 2019, 19 (9): 2194- 2213
doi: 10.3390/s19092194
[8]   梁笑轩, 黄樟钦, 邱兰馨. 一种基于二维相控阵天线的RFID定位方法 [J]. 电子学报, 2018, 46(4): 146-152.
LIANG Xiao-xuan, HUANG Zhang-Qin, QIU Lan-xin. An RFID positioning method based on two-dimensional phased array antenna [J]. Acta Electronica Sinica, 2018, 46(4): 146-152.
[9]   马雪松, 赵寒涛, 朱明清 CVIRE-RFID室内定位算法[J]. 自动化技术与应用, 2017, 36 (12): 49- 53
MA Xue-song, ZHAO Han-tao, ZHU Ming-qing CVIRE-RFID indoor positioning algorithm[J]. Techniques of Automation and Applications, 2017, 36 (12): 49- 53
doi: 10.3969/j.issn.1003-7241.2017.12.012
[10]   顾军华, 许鹏, 董瑶, 等 基于克里金插值的自适应VIRE室内定位算法研究[J]. 计算机工程与应用, 2018, 54 (12): 100- 104
GU Jun-hua, XU Peng, DONG Yao, et al Research on adaptive VIRE indoor positioning algorithm based on Kriging interpolation[J]. Computer Engineering and Applications, 2018, 54 (12): 100- 104
doi: 10.3778/j.issn.1002-8331.1709-0242
[11]   SHANGGUAN L, YANG Z, LIU A X, et al STPP: spatial-temporal phase profiling-based method for relative RFID tag localization[J]. IEEE/ACM Transactions on Networking, 2016, 25 (1): 596- 609
[12]   RUAN W J, SHENG Q Z, YAO L, et al. Device-free indoor localization and tracking through human-object interactions [C]// 2016 IEEE 17th International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM). Coimbra: IEEE, 2016.
[13]   LIU M, WANG H, YANG Y, et al RFID 3-D indoor localization for tag and tag-free target based on interference[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 68 (10): 3718- 3732
[14]   XIAO F, WANG Z, YE N, et al One more tag enables fine-grained RFID localization and tracking[J]. IEEE/ACM Transactions on Networking, 2017, 26 (1): 161- 174
[15]   HAN J, QIAN C, WANG X, et al Twins: device-free object tracking using passive tags[J]. IEEE/ACM Transactions on Networking, 2015, 24 (3): 1605- 1617
[16]   MA L, LIU M, WANG H, et al WallSense: device-free indoor localization using wall-mounted UHF RFID tags[J]. Sensors, 2018, 19 (1): 68- 83
doi: 10.3390/s19010068
[17]   丁治国. RFID关键技术研究与实现[D]. 合肥: 中国科学技术大学, 2009.
DING Zhi-guo. Research and implementation of RFID key technology [D]. Hefei: University of Science and Technology of China, 2009.
[18]   谢飞, 张忠臣, 张鹏, 等 多径效应对测向误差的影响[J]. 电子测量技术, 2010, 33 (1): 29- 31
XIE Fei, ZHANG Zhong-cheng, ZHANG Peng, et al The influence of multipath effect on direction finding error[J]. Electronic Measurement Technology, 2010, 33 (1): 29- 31
doi: 10.3969/j.issn.1002-7300.2010.01.009
[19]   徐潇潇, 谢林柏 位置指纹算法关键参数的提取[J]. 江南大学学报:自然科学版, 2015, 14 (3): 264- 268
XU Xiao-xiao, XIE Lin-bai Extraction of key parameters of location fingerprint algorithm[J]. Journal of Clothing Research, 2015, 14 (3): 264- 268
[20]   BERTHOUZE L, TIJSSELING A A neural model for context-dependent sequence learning[J]. Neural Processing Letters, 2006, 23 (1): 27- 45
doi: 10.1007/s11063-005-2838-x
[21]   GREFF K, SRIVASTAVA R K, KOUTNÍK J, et al LSTM: a search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 28 (10): 2222- 2232
[22]   FU R, ZHANG Z, LI L, et al. Using LSTM and GRU Neural Network Methods for Traffic Flow Prediction [C]// 31st Youth Academic Annual Conference of Chinese-Association-of-Automation (YAC). Wuhan: IEEE, 2016: 324-328.
[23]   KONG W C, DONG Z Y, JIA Y W, et al Short-term residential load forecasting based on LSTM recurrent neural network[J]. IEEE Transcations on Smart Grid, 2019, 10 (1): 841- 851
doi: 10.1109/TSG.2017.2753802
[1] Ju-xiang ZENG,Ping-hui WANG,Yi-dong DING,Lin LAN,Lin-xi CAI,Xiao-hong GUAN. Graph neural network based node embedding enhancement model for node classification[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(2): 219-225.
[2] Jun-chi MA,Xiao-xin DI,Zong-tao DUAN,Lei TANG. Survey on program representation learning[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(1): 155-169.
[3] Chen YE,Hong-fei ZHAN,Ying-jun LIN,Jun-he YU,Rui WANG,Wu-chang ZHONG. Design knowledge recommendation based on inference-context-aware activation model[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(1): 32-46.
[4] Jin-zhen LIU,Fei CHEN,Hui XIONG. Open electrical impedance imaging algorithm based on multi-scale residual network model[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(9): 1789-1795.
[5] Wan-liang WANG,Tie-jun WANG,Jia-cheng CHEN,Wen-bo YOU. Medical image segmentation method combining multi-scale and multi-head attention[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(9): 1796-1805.
[6] Kun HAO,Kuo WANG,Bei-bei WANG. Lightweight underwater biological detection algorithm based on improved Mobilenet-YOLOv3[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(8): 1622-1632.
[7] Yong-sheng ZHAO,Rui-xiang LI,Na-na NIU,Zhi-yong ZHAO. Shape control method of fuselage driven by digital twin[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(7): 1457-1463.
[8] Li HE,Shan-min PANG. Face reconstruction from voice based on age-supervised learning and face prior information[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(5): 1006-1016.
[9] Xue-qin ZHANG,Tian-ren LI. Breast cancer pathological image classification based on Cycle-GAN and improved DPN network[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(4): 727-735.
[10] Jing-hui CHU,Li-dong SHI,Pei-guang JING,Wei LV. Context-aware knowledge distillation network for object detection[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(3): 503-509.
[11] Ruo-ran CHENG,Xiao-li ZHAO,Hao-jun ZHOU,Han-chen YE. Review of Chinese font style transfer research based on deep learning[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(3): 510-519, 530.
[12] Tian-le YUAN,Ju-long YUAN,Yong-jian ZHU,Han-chen ZHENG. Surface defect detection algorithm of thrust ball bearing based on improved YOLOv5[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(12): 2349-2357.
[13] Fan ZHONG,Zheng-yao BAI. 3D point cloud super-resolution with dynamic residual graph convolutional networks[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(11): 2251-2259.
[14] Xiang-dong PENG,Cong-cheng PAN,Ze-jun KE,Hua-qiang ZHU,Xiao ZHOU. Classification method for electrocardiograph signals based on parallel architecture model and spatial-temporal attention mechanism[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(10): 1912-1923.
[15] Dong-jie YANG,Xian-jun GAO,Shu-hao RAN,Guang-bin ZHANG,Ping WANG,Yuan-wei YANG. Building extraction based on multiple multiscale-feature fusion attention network[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(10): 1924-1934.