Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data

Kosuke Okusa, Toshinari Kamakura

研究成果: 著書/レポートタイプへの貢献会議での発言

2 引用 (Scopus)

抄録

We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. Our gait model is based on human gait structure and temporal-spatial relations between camera and subject. To demonstrate the effectiveness of our method, we conducted two sets of experiments, assessing the proposed method in gait analysis for young/elderly person and abnormal gait detection. In abnormal gait detection experiment, we apply K-nearestneighbor classifier, using the estimated parameters, to perform normal/abnormal gait detect, and present results from an experiment involving 120 subjects (young person), and 60 subjects (elderly person). As a result, our method shows high detection rate.

元の言語英語
ホスト出版物のタイトルInternational MultiConference of Engineers and Computer Scientists, IMECS 2012
編集者Jon Burgstone, S. I. Ao, Craig Douglas, W. S. Grundfest
出版者Newswood Limited
ページ443-448
ページ数6
ISBN(電子版)9789881925169
ISBN(印刷物)9789881925114
出版物ステータス出版済み - 1 1 2012
イベント2012 World Congress on Engineering and Computer Science, WCECS 2012 - San Francisco, 米国
継続期間: 10 24 201210 26 2012

出版物シリーズ

名前Lecture Notes in Engineering and Computer Science
1
ISSN(印刷物)2078-0958

その他

その他2012 World Congress on Engineering and Computer Science, WCECS 2012
米国
San Francisco
期間10/24/1210/26/12

Fingerprint

Gait analysis
Experiments
Classifiers
Cameras

All Science Journal Classification (ASJC) codes

  • Computer Science (miscellaneous)

これを引用

Okusa, K., & Kamakura, T. (2012). Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data. : J. Burgstone, S. I. Ao, C. Douglas, & W. S. Grundfest (版), International MultiConference of Engineers and Computer Scientists, IMECS 2012 (pp. 443-448). (Lecture Notes in Engineering and Computer Science; 巻数 1). Newswood Limited.

Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data. / Okusa, Kosuke; Kamakura, Toshinari.

International MultiConference of Engineers and Computer Scientists, IMECS 2012. 版 / Jon Burgstone; S. I. Ao; Craig Douglas; W. S. Grundfest. Newswood Limited, 2012. p. 443-448 (Lecture Notes in Engineering and Computer Science; 巻 1).

研究成果: 著書/レポートタイプへの貢献会議での発言

Okusa, K & Kamakura, T 2012, Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data. : J Burgstone, SI Ao, C Douglas & WS Grundfest (版), International MultiConference of Engineers and Computer Scientists, IMECS 2012. Lecture Notes in Engineering and Computer Science, 巻. 1, Newswood Limited, pp. 443-448, 2012 World Congress on Engineering and Computer Science, WCECS 2012, San Francisco, 米国, 10/24/12.
Okusa K, Kamakura T. Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data. : Burgstone J, Ao SI, Douglas C, Grundfest WS, 編集者, International MultiConference of Engineers and Computer Scientists, IMECS 2012. Newswood Limited. 2012. p. 443-448. (Lecture Notes in Engineering and Computer Science).
Okusa, Kosuke ; Kamakura, Toshinari. / Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data. International MultiConference of Engineers and Computer Scientists, IMECS 2012. 編集者 / Jon Burgstone ; S. I. Ao ; Craig Douglas ; W. S. Grundfest. Newswood Limited, 2012. pp. 443-448 (Lecture Notes in Engineering and Computer Science).
@inproceedings{a1db98c6d627495497dd7f907c6531b0,
title = "Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data",
abstract = "We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. Our gait model is based on human gait structure and temporal-spatial relations between camera and subject. To demonstrate the effectiveness of our method, we conducted two sets of experiments, assessing the proposed method in gait analysis for young/elderly person and abnormal gait detection. In abnormal gait detection experiment, we apply K-nearestneighbor classifier, using the estimated parameters, to perform normal/abnormal gait detect, and present results from an experiment involving 120 subjects (young person), and 60 subjects (elderly person). As a result, our method shows high detection rate.",
author = "Kosuke Okusa and Toshinari Kamakura",
year = "2012",
month = "1",
day = "1",
language = "English",
isbn = "9789881925114",
series = "Lecture Notes in Engineering and Computer Science",
publisher = "Newswood Limited",
pages = "443--448",
editor = "Jon Burgstone and Ao, {S. I.} and Craig Douglas and Grundfest, {W. S.}",
booktitle = "International MultiConference of Engineers and Computer Scientists, IMECS 2012",

}

TY - GEN

T1 - Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data

AU - Okusa, Kosuke

AU - Kamakura, Toshinari

PY - 2012/1/1

Y1 - 2012/1/1

N2 - We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. Our gait model is based on human gait structure and temporal-spatial relations between camera and subject. To demonstrate the effectiveness of our method, we conducted two sets of experiments, assessing the proposed method in gait analysis for young/elderly person and abnormal gait detection. In abnormal gait detection experiment, we apply K-nearestneighbor classifier, using the estimated parameters, to perform normal/abnormal gait detect, and present results from an experiment involving 120 subjects (young person), and 60 subjects (elderly person). As a result, our method shows high detection rate.

AB - We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. Our gait model is based on human gait structure and temporal-spatial relations between camera and subject. To demonstrate the effectiveness of our method, we conducted two sets of experiments, assessing the proposed method in gait analysis for young/elderly person and abnormal gait detection. In abnormal gait detection experiment, we apply K-nearestneighbor classifier, using the estimated parameters, to perform normal/abnormal gait detect, and present results from an experiment involving 120 subjects (young person), and 60 subjects (elderly person). As a result, our method shows high detection rate.

UR - http://www.scopus.com/inward/record.url?scp=84874835909&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874835909&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84874835909

SN - 9789881925114

T3 - Lecture Notes in Engineering and Computer Science

SP - 443

EP - 448

BT - International MultiConference of Engineers and Computer Scientists, IMECS 2012

A2 - Burgstone, Jon

A2 - Ao, S. I.

A2 - Douglas, Craig

A2 - Grundfest, W. S.

PB - Newswood Limited

ER -