WiHumo: a real-time lightweight indoor human motion detection

WiFi is one of the most popular techniques, which has been used to detect human motion. In this paper, we extract channel state information (CSI) of wireless signal to detect human motion and prototype a detection system, WiHumo. First, we use a linear transformation to eliminate the shift of phases of different subcarriers. Subsequently, we design two criteria for the short-term case (SES) and the long-term case (LES), respectively. The former is to detect if someone is walking in the indoor room and the latter is to detect whether the person is walking continuously. We prototype the detection system with the commodity WiFi infrastructure and evaluate its performances in various environments. Experimental results show that WiHumo has high accuracy with real-time detection and outperforms the existing methods.

[1]  Moustafa Youssef,et al.  RASID: A robust WLAN device-free passive motion detection system , 2011, 2012 IEEE International Conference on Pervasive Computing and Communications.

[2]  Romit Roy Choudhury,et al.  Using mobile phones to write in air , 2011, MobiSys '11.

[3]  Yunhao Liu,et al.  PADS: Passive detection of moving targets with dynamic speed using PHY layer information , 2014, 2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS).

[4]  Nicola Cordeschi,et al.  Performance evaluation of a multi-frame persistent neighbor discovery strategy based on Sift-distribution in DTN RFID networks , 2014, International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS 2014).

[5]  Kaishun Wu,et al.  WiFall: Device-Free Fall Detection by Wireless Networks , 2017, IEEE Transactions on Mobile Computing.

[6]  I. Cuthill,et al.  Effect size, confidence interval and statistical significance: a practical guide for biologists , 2007, Biological reviews of the Cambridge Philosophical Society.

[7]  Simon Fong,et al.  Atmospheric pattern recognition of human activities on ubiquitous sensor network using data stream mining algorithms , 2016, Int. J. Sens. Networks.

[8]  Shaojie Tang,et al.  Wi-Sleep: Contactless Sleep Monitoring via WiFi Signals , 2014, 2014 IEEE Real-Time Systems Symposium.

[9]  Ozan K. Tonguz,et al.  A Blind Zone Alert System Based on Intra-Vehicular Wireless Sensor Networks , 2015, IEEE Transactions on Industrial Informatics.

[10]  Fatih Erden,et al.  A robust system for counting people using an infrared sensor and a camera , 2015 .

[11]  Guowei Shen,et al.  FRID: Indoor Fine-Grained Real-Time Passive Human Motion Detection , 2015, 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom).

[12]  Yang Xiao,et al.  Monitoring Space Segmentation in Deploying Sensor Arrays , 2014, IEEE Sensors Journal.

[13]  Enzo Baccarelli,et al.  Performance evaluation of primary-secondary reliable resource-management in vehicular networks , 2014, 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication (PIMRC).

[14]  Licai Zhu,et al.  A HCI Motion Recognition System Based on Channel State Information with Fine Granularity , 2017, WASA.

[15]  Weiguo Gong,et al.  EMD-Based Symbolic Dynamic Analysis for the Recognition of Human and Nonhuman Pyroelectric Infrared Signals , 2016, Sensors.

[16]  Deng Li,et al.  A human body positioning system with pyroelectric infrared sensor , 2016, Int. J. Sens. Networks.

[17]  Naoto Sasaoka,et al.  K factor estimation for MIMO multipath channels , 2015, 2015 IEEE International Conference on Digital Signal Processing (DSP).

[18]  Jaeseok Yun,et al.  Human Movement Detection and Idengification Using Pyroelectric Infrared Sensors , 2014, Sensors.

[19]  Qi Hao,et al.  Multiple Human Tracking and Identification With Wireless Distributed Pyroelectric Sensor Systems , 2009, IEEE Systems Journal.

[20]  Michael Mock,et al.  A step counter service for Java-enabled devices using a built-in accelerometer , 2009, CAMS '09.

[21]  Chris Gordon,et al.  Analysis of XBOX Kinect sensor data for use on construction sites: Depth accuracy and sensor interference assessment , 2012 .