Next Article in Journal
Self-Calibration of an Industrial Robot Using a Novel Affordable 3D Measuring Device
Previous Article in Journal
Synthetic Aperture Radar Processing Approach for Simultaneous Target Detection and Image Formation
Previous Article in Special Issue
An Artificial Bee Colony-Based Green Routing Mechanism in WBANs for Sensor-Based E-Healthcare Systems
Article

Multi-Target Intense Human Motion Analysis and Detection Using Channel State Information

1
Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, School of Software, Dalian University of Technology, Dalian 116621, China
2
College of Engineering, Nanjing Agricultural University, Nanjing 210031, China
3
School of Engineering, University of Lincoln, Brayford Pool, Lincoln LN6 7TS, UK
*
Author to whom correspondence should be addressed.
This paper is an extended version of paper published in Liu, J.; Wang, L.; Guo, L.; Fang, J.; Lu, B.; Zhou, W. A Research on CSI-based Human Motion Detection in Complex Scenarios. In Proceedings of the 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), 12–15 October 2017.
Sensors 2018, 18(10), 3379; https://doi.org/10.3390/s18103379
Received: 29 August 2018 / Revised: 3 October 2018 / Accepted: 6 October 2018 / Published: 10 October 2018
(This article belongs to the Special Issue Sensor-based E-Healthcare System: Greenness and Security)
Intense human motion, such as hitting, kicking, and falling, in some particular scenes indicates the occurrence of abnormal events like violence and school bullying. Camera-based human motion detection is an effective way to analyze human behavior and detect intense human motion. However, even if the camera is properly deployed, it will still generate blind spots. Moreover, camera-based methods cannot be used in places such as restrooms and dressing rooms due to privacy issues. In this paper, we propose a multi-target intense human motion detection scheme using commercial Wi-Fi infrastructures. Compared with human daily activities, intense human motion usually has the characteristics of intensity, rapid change, irregularity, large amplitude, and continuity. We studied the changing pattern of Channel State Information (CSI) influenced by intense human motion, and extracted features in the pattern by conducting a large number of experiments. Considering occlusion exists in some complex scenarios, we distinguished the Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) conditions in the case of obstacles appearing between the transmitter and the receiver, which further improves the overall performance. We implemented the intense human motion detection system using single commercial Wi-Fi devices, and evaluated it in real indoor environments. The experimental results show that our system can achieve intense human motion detection rate of 90%. View Full-Text
Keywords: human motion detection; Channel State Information (CSI); multi-path effect; device-free; Support Vector Machine (SVM) human motion detection; Channel State Information (CSI); multi-path effect; device-free; Support Vector Machine (SVM)
Show Figures

Figure 1

MDPI and ACS Style

Liu, J.; Wang, L.; Fang, J.; Guo, L.; Lu, B.; Shu, L. Multi-Target Intense Human Motion Analysis and Detection Using Channel State Information. Sensors 2018, 18, 3379. https://doi.org/10.3390/s18103379

AMA Style

Liu J, Wang L, Fang J, Guo L, Lu B, Shu L. Multi-Target Intense Human Motion Analysis and Detection Using Channel State Information. Sensors. 2018; 18(10):3379. https://doi.org/10.3390/s18103379

Chicago/Turabian Style

Liu, Jialin; Wang, Lei; Fang, Jian; Guo, Linlin; Lu, Bingxian; Shu, Lei. 2018. "Multi-Target Intense Human Motion Analysis and Detection Using Channel State Information" Sensors 18, no. 10: 3379. https://doi.org/10.3390/s18103379

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop