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

Kosuke Okusa, Toshinari Kamakura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationInternational MultiConference of Engineers and Computer Scientists, IMECS 2012
EditorsJon Burgstone, S. I. Ao, Craig Douglas, W. S. Grundfest
PublisherNewswood Limited
Pages443-448
Number of pages6
ISBN (Electronic)9789881925169
ISBN (Print)9789881925114
Publication statusPublished - Jan 1 2012
Externally publishedYes
Event2012 World Congress on Engineering and Computer Science, WCECS 2012 - San Francisco, United States
Duration: Oct 24 2012Oct 26 2012

Publication series

NameLecture Notes in Engineering and Computer Science
Volume1
ISSN (Print)2078-0958

Other

Other2012 World Congress on Engineering and Computer Science, WCECS 2012
CountryUnited States
CitySan Francisco
Period10/24/1210/26/12

All Science Journal Classification (ASJC) codes

  • Computer Science (miscellaneous)

Fingerprint Dive into the research topics of 'Normal/abnormal gait analysis based on the statistical registration and modeling of the frontal view gait data'. Together they form a unique fingerprint.

Cite this