WiDet: Wi-Fi based device-free passive person detection with deep convolutional neural networks

Abstract To achieve device-free person detection, various types of signal features, such as moving statistics and wavelet representations, have been extracted from the Wi-Fi Received Signal Strength Index (RSSI), whose value fluctuates when human subjects move near the Wi-Fi transceivers. However, these features do not work effectively under different deployments of Wi-Fi transceivers because each transceiver has a unique RSSI fluctuation pattern that depends on its specific wireless channel and hardware characteristics. To address this problem, we present WiDet, a system that uses a deep Convolutional Neural Network (CNN) approach for person detection. The CNN takes the 2-dimensional wavelet coefficients as input, and extracts effective and robust detection features automatically. With a large number of internal parameters, the CNN can record and recognize the different RSSI fluctuation patterns from different transceivers. We further apply the data augmentation method to improve the algorithm robustness to wireless interferences and pedestrian speed changes. To take advantage of the wide availability of the existing Wi-Fi devices, we design a collaborative sensing technique that can recognize the subject’s moving directions. To validate the proposed design, we implement a prototype system that consists of three Wi-Fi packet transmitters and one receiver on low-cost off-the-shelf embedded development boards. In a multi-day experiment with a total of 163 walking events, WiDet achieves 95.5% of detection accuracy in detecting pedestrians, which outperforms the moving statistics and the wavelet representation based approaches by 22% and 8%, respectively.

[1]  Shan Lin,et al.  WiDet: Wi-Fi Based Device-Free Passive Person Detection with Deep Convolutional Neural Networks , 2018, MSWiM.

[2]  Kaishun Wu,et al.  CSI-Based Indoor Localization , 2013, IEEE Transactions on Parallel and Distributed Systems.

[3]  Andrew G. Dempster,et al.  Differences in RSSI readings made by different Wi-Fi chipsets: A limitation of WLAN localization , 2011, 2011 International Conference on Localization and GNSS (ICL-GNSS).

[4]  Richard W. Bohannon Comfortable and maximum walking speed of adults aged 20-79 years: reference values and determinants. , 1997, Age and ageing.

[5]  Wei Wang,et al.  Device-Free Human Activity Recognition Using Commercial WiFi Devices , 2017, IEEE Journal on Selected Areas in Communications.

[6]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[7]  Michael G. Rabbat,et al.  Compressed RF Tomography for Wireless Sensor Networks: Centralized and Decentralized Approaches , 2009, DCOSS.

[8]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9]  Tong Liu,et al.  Enhanced Sparse Representation-Based Device-Free Localization with Radio Tomography Networks , 2018, J. Sens. Actuator Networks.

[10]  Moustafa Youssef,et al.  CoSDEO 2016 Keynote: A decade later — Challenges: Device-free passive localization for wireless environments , 2007, 2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).

[11]  Xiaocheng Wang,et al.  Device-Free Wireless Localization Using Artificial Neural Networks in Wireless Sensor Networks , 2018, Wirel. Commun. Mob. Comput..

[12]  Shiwen Mao,et al.  DeepFi: Deep learning for indoor fingerprinting using channel state information , 2015, 2015 IEEE Wireless Communications and Networking Conference (WCNC).

[13]  Yusheng Ji,et al.  Accurate Location Tracking From CSI-Based Passive Device-Free Probabilistic Fingerprinting , 2018, IEEE Transactions on Vehicular Technology.

[14]  Xiaodong Cui,et al.  Data Augmentation for Deep Neural Network Acoustic Modeling , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[15]  Chao Yang,et al.  PhaseBeat: Exploiting CSI Phase Data for Vital Sign Monitoring with Commodity WiFi Devices , 2017, 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS).

[16]  Neal Patwari,et al.  Radio Tomographic Imaging with Wireless Networks , 2010, IEEE Transactions on Mobile Computing.

[17]  Maurizio Bocca,et al.  Enhancing the accuracy of radio tomographic imaging using channel diversity , 2012, 2012 IEEE 9th International Conference on Mobile Ad-Hoc and Sensor Systems (MASS 2012).

[18]  Philip Levis,et al.  The β-factor: measuring wireless link burstiness , 2008, SenSys '08.

[19]  Fadel Adib,et al.  Emotion recognition using wireless signals , 2016, MobiCom.

[20]  Lionel M. Ni,et al.  An RF-Based System for Tracking Transceiver-Free Objects , 2007, Fifth Annual IEEE International Conference on Pervasive Computing and Communications (PerCom'07).

[21]  Xiang Lu,et al.  Device-Free Localization Based on CSI Fingerprints and Deep Neural Networks , 2018, 2018 15th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON).

[22]  Jie Wang,et al.  DeFi: Robust Training-Free Device-Free Wireless Localization With WiFi , 2018, IEEE Transactions on Vehicular Technology.

[23]  Hong-Goo Kang,et al.  A Priori SNR Estimation Using Air- and Bone-Conduction Microphones , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[24]  Hui Xiong,et al.  Performing Joint Learning for Passive Intrusion Detection in Pervasive Wireless Environments , 2010, 2010 Proceedings IEEE INFOCOM.

[25]  Moustafa Youssef,et al.  Smart cevices for smart environments: Device-free passive detection in real environments , 2009, 2009 IEEE International Conference on Pervasive Computing and Communications.

[26]  K. Woyach,et al.  Sensorless Sensing in Wireless Networks: Implementation and Measurements , 2006, 2006 4th International Symposium on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks.

[27]  Chen Wang,et al.  Low Human-Effort, Device-Free Localization with Fine-Grained Subcarrier Information , 2018, IEEE Transactions on Mobile Computing.

[28]  Xiang Li,et al.  An Accurate and Robust Approach of Device-Free Localization With Convolutional Autoencoder , 2019, IEEE Internet of Things Journal.

[29]  Neal Patwari,et al.  2008 International Conference on Information Processing in Sensor Networks Effects of Correlated Shadowing: Connectivity, Localization, and RF Tomography , 2022 .

[30]  Kaishun Wu,et al.  FIFS: Fine-Grained Indoor Fingerprinting System , 2012, 2012 21st International Conference on Computer Communications and Networks (ICCCN).

[31]  Xiao Zhang,et al.  Device-Free Simultaneous Wireless Localization and Activity Recognition With Wavelet Feature , 2017, IEEE Transactions on Vehicular Technology.

[32]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[33]  Stephan Sigg,et al.  Applicability of RF-based methods for emotion recognition: A survey , 2016, 2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).