Towards HMM based human motion recognition using MEMS inertial sensors

Guangyi Shi; Yuexian Zou; Yufeng Jin; Xiaole Cui; Wen J. Li

doi:10.1109/ROBIO.2009.4913268

Towards HMM based human motion recognition using MEMS inertial sensors

Guangyi Shi, Yuexian Zou^*, Yufeng Jin, Xiaole Cui, Wen J. Li

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

26 Citations (Scopus)

Abstract

This paper presents a new method of human motion recognition based on MEMS inertial sensors data. A Micro Inertial Measurement Unit (μIMU) that is 56mm*23mm*15mm in size was built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, a Bluetooth module and a MCU (Micro Controller Unit), which can record and transfer inertial data to a computer through serial port wirelessly. Five categories of human motion were done including walking, running, going upstairs, fall and standing. Fourier analysis was used to extract the feature from the human motion data. The concentrated information was finally used to categorize the human motions through HMM (Hidden Markov Model) process. Experimental results show that for the given 5 human motions, correct recognition rate range from 90%-100%. Also, a full combination of 6 parameters (G _x, G _y, G _z, A _x, A _y, A _z) was listed and the recognition rate of each combination (total 63) was tested. © 2008 IEEE.

Original language	English
Title of host publication	2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008
Pages	1762-1766
DOIs	https://doi.org/10.1109/ROBIO.2009.4913268
Publication status	Published - 2008
Externally published	Yes
Event	2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008 - Bangkok, Thailand Duration: 21 Feb 2009 → 26 Feb 2009

Conference

Conference	2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008
Place	Thailand
City	Bangkok
Period	21/02/09 → 26/02/09

Research Keywords

μIMU
HMM
Human motion recognition
MEMS

Access Output

10.1109/ROBIO.2009.4913268

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{fd3fb4de204a4717b42aca7008dba6d6,

title = "Towards HMM based human motion recognition using MEMS inertial sensors",

abstract = "This paper presents a new method of human motion recognition based on MEMS inertial sensors data. A Micro Inertial Measurement Unit (μIMU) that is 56mm*23mm*15mm in size was built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, a Bluetooth module and a MCU (Micro Controller Unit), which can record and transfer inertial data to a computer through serial port wirelessly. Five categories of human motion were done including walking, running, going upstairs, fall and standing. Fourier analysis was used to extract the feature from the human motion data. The concentrated information was finally used to categorize the human motions through HMM (Hidden Markov Model) process. Experimental results show that for the given 5 human motions, correct recognition rate range from 90%-100%. Also, a full combination of 6 parameters (G x, G y, G z, A x, A y, A z) was listed and the recognition rate of each combination (total 63) was tested. {\textcopyright} 2008 IEEE.",

keywords = "μIMU, HMM, Human motion recognition, MEMS",

author = "Guangyi Shi and Yuexian Zou and Yufeng Jin and Xiaole Cui and Li, {Wen J.}",

year = "2008",

doi = "10.1109/ROBIO.2009.4913268",

language = "English",

isbn = "9781424426799",

pages = "1762--1766",

booktitle = "2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008",

note = "2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008 ; Conference date: 21-02-2009 Through 26-02-2009",

}

Towards HMM based human motion recognition using MEMS inertial sensors. / Shi, Guangyi; Zou, Yuexian; Jin, Yufeng et al.
2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008. 2008. p. 1762-1766 4913268.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Towards HMM based human motion recognition using MEMS inertial sensors

AU - Shi, Guangyi

AU - Zou, Yuexian

AU - Jin, Yufeng

AU - Cui, Xiaole

AU - Li, Wen J.

PY - 2008

Y1 - 2008

N2 - This paper presents a new method of human motion recognition based on MEMS inertial sensors data. A Micro Inertial Measurement Unit (μIMU) that is 56mm*23mm*15mm in size was built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, a Bluetooth module and a MCU (Micro Controller Unit), which can record and transfer inertial data to a computer through serial port wirelessly. Five categories of human motion were done including walking, running, going upstairs, fall and standing. Fourier analysis was used to extract the feature from the human motion data. The concentrated information was finally used to categorize the human motions through HMM (Hidden Markov Model) process. Experimental results show that for the given 5 human motions, correct recognition rate range from 90%-100%. Also, a full combination of 6 parameters (G x, G y, G z, A x, A y, A z) was listed and the recognition rate of each combination (total 63) was tested. © 2008 IEEE.

AB - This paper presents a new method of human motion recognition based on MEMS inertial sensors data. A Micro Inertial Measurement Unit (μIMU) that is 56mm*23mm*15mm in size was built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, a Bluetooth module and a MCU (Micro Controller Unit), which can record and transfer inertial data to a computer through serial port wirelessly. Five categories of human motion were done including walking, running, going upstairs, fall and standing. Fourier analysis was used to extract the feature from the human motion data. The concentrated information was finally used to categorize the human motions through HMM (Hidden Markov Model) process. Experimental results show that for the given 5 human motions, correct recognition rate range from 90%-100%. Also, a full combination of 6 parameters (G x, G y, G z, A x, A y, A z) was listed and the recognition rate of each combination (total 63) was tested. © 2008 IEEE.

KW - μIMU

KW - HMM

KW - Human motion recognition

KW - MEMS

UR - http://www.scopus.com/inward/record.url?scp=70349187539&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-70349187539&origin=recordpage

U2 - 10.1109/ROBIO.2009.4913268

DO - 10.1109/ROBIO.2009.4913268

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781424426799

SP - 1762

EP - 1766

BT - 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008

T2 - 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008

Y2 - 21 February 2009 through 26 February 2009

ER -

Towards HMM based human motion recognition using MEMS inertial sensors

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this