Real-time recognition of multi-category human motion using μIMU data

Weiwei Wan; Hong Liu; Guangyi Shi; Wen J. Li

doi:10.1109/ICMA.2007.4303831

Real-time recognition of multi-category human motion using μIMU data

Weiwei Wan, Hong Liu, Guangyi Shi, Wen J. Li

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

2 Citations (Scopus)

Abstract

This paper describes a novel approach for human motion recognition via motion feature vectors collected from a micro Inertial Measurement Unit (μSMV), which measures angular rates and accelerations of the three different directions in the workspace based on MEMS sensors. The recognizer is composed of three parts. The first part is a preprocessor, in which Vector Quantization is used to reduce dimensions of vectors. Recognition is implemented by the second part, which is a classifier composed of Hidden Markov Model and an efficient second layer criterion. The third part uses a sliding window algorithm for precise recognition. There were 200 sequences (about 100,000 vectors) for 10 different kinds of motions tested in our work, including falling-down motion and other typical human motions. Experimental results show that for the given 10 different categories, correct recognition rates range from 95%-100%, of which the falling-down motion can be classified from others with a 100% recognition rate. © 2007 IEEE.

Original language	English
Title of host publication	Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007
Pages	1845-1850
DOIs	https://doi.org/10.1109/ICMA.2007.4303831
Publication status	Published - 2007
Externally published	Yes
Event	2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007 - Harbin, China Duration: 5 Aug 2007 → 8 Aug 2007

Conference

Conference	2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007
Place	China
City	Harbin
Period	5/08/07 → 8/08/07

Research Keywords

μIMU Data
Hidden Markov model
Human motion recognition
Vector quantization

Access Output

10.1109/ICMA.2007.4303831

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{1e50e6740b234b07bdb0db4c7d8faf23,

title = "Real-time recognition of multi-category human motion using μIMU data",

abstract = "This paper describes a novel approach for human motion recognition via motion feature vectors collected from a micro Inertial Measurement Unit (μSMV), which measures angular rates and accelerations of the three different directions in the workspace based on MEMS sensors. The recognizer is composed of three parts. The first part is a preprocessor, in which Vector Quantization is used to reduce dimensions of vectors. Recognition is implemented by the second part, which is a classifier composed of Hidden Markov Model and an efficient second layer criterion. The third part uses a sliding window algorithm for precise recognition. There were 200 sequences (about 100,000 vectors) for 10 different kinds of motions tested in our work, including falling-down motion and other typical human motions. Experimental results show that for the given 10 different categories, correct recognition rates range from 95%-100%, of which the falling-down motion can be classified from others with a 100% recognition rate. {\textcopyright} 2007 IEEE.",

keywords = "μIMU Data, Hidden Markov model, Human motion recognition, Vector quantization",

author = "Weiwei Wan and Hong Liu and Guangyi Shi and Li, {Wen J.}",

year = "2007",

doi = "10.1109/ICMA.2007.4303831",

language = "English",

isbn = "1424408288",

pages = "1845--1850",

booktitle = "Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007",

note = "2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007 ; Conference date: 05-08-2007 Through 08-08-2007",

}

Wan, W, Liu, H, Shi, G & Li, WJ 2007, Real-time recognition of multi-category human motion using μIMU data. in Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007., 4303831, pp. 1845-1850, 2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007, Harbin, China, 5/08/07. https://doi.org/10.1109/ICMA.2007.4303831

Real-time recognition of multi-category human motion using μIMU data. / Wan, Weiwei; Liu, Hong; Shi, Guangyi et al.
Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007. 2007. p. 1845-1850 4303831.

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

TY - GEN

T1 - Real-time recognition of multi-category human motion using μIMU data

AU - Wan, Weiwei

AU - Liu, Hong

AU - Shi, Guangyi

AU - Li, Wen J.

PY - 2007

Y1 - 2007

N2 - This paper describes a novel approach for human motion recognition via motion feature vectors collected from a micro Inertial Measurement Unit (μSMV), which measures angular rates and accelerations of the three different directions in the workspace based on MEMS sensors. The recognizer is composed of three parts. The first part is a preprocessor, in which Vector Quantization is used to reduce dimensions of vectors. Recognition is implemented by the second part, which is a classifier composed of Hidden Markov Model and an efficient second layer criterion. The third part uses a sliding window algorithm for precise recognition. There were 200 sequences (about 100,000 vectors) for 10 different kinds of motions tested in our work, including falling-down motion and other typical human motions. Experimental results show that for the given 10 different categories, correct recognition rates range from 95%-100%, of which the falling-down motion can be classified from others with a 100% recognition rate. © 2007 IEEE.

AB - This paper describes a novel approach for human motion recognition via motion feature vectors collected from a micro Inertial Measurement Unit (μSMV), which measures angular rates and accelerations of the three different directions in the workspace based on MEMS sensors. The recognizer is composed of three parts. The first part is a preprocessor, in which Vector Quantization is used to reduce dimensions of vectors. Recognition is implemented by the second part, which is a classifier composed of Hidden Markov Model and an efficient second layer criterion. The third part uses a sliding window algorithm for precise recognition. There were 200 sequences (about 100,000 vectors) for 10 different kinds of motions tested in our work, including falling-down motion and other typical human motions. Experimental results show that for the given 10 different categories, correct recognition rates range from 95%-100%, of which the falling-down motion can be classified from others with a 100% recognition rate. © 2007 IEEE.

KW - μIMU Data

KW - Hidden Markov model

KW - Human motion recognition

KW - Vector quantization

UR - http://www.scopus.com/inward/record.url?scp=37049026902&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-37049026902&origin=recordpage

U2 - 10.1109/ICMA.2007.4303831

DO - 10.1109/ICMA.2007.4303831

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

SN - 1424408288

SN - 9781424408283

SP - 1845

EP - 1850

BT - Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007

T2 - 2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007

Y2 - 5 August 2007 through 8 August 2007

ER -

Real-time recognition of multi-category human motion using μIMU data

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this