Unsupervised clustering of people from ‘skeleton’ data

Author

Ball, Adrian ; Rye, David ; Ramos, Fabio ; Velonaki, Mari

Author_Institution

Centre for Social Robot., Univ. of Sydney, Sydney, NSW, Australia

fYear

2012

fDate

5-8 March 2012

Firstpage

225

Lastpage

226

Abstract

This paper investigates the possibility of recognising individual persons from their walking gait using three-dimensional `skeleton´ data from an inexpensive consumer-level sensor, the Microsoft `Kinect´. In an experimental pilot study it is shown that the K-means algorithm - as a candidate unsupervised clustering algorithm - is able to cluster gait samples from four persons with a nett accuracy of 43.6%.

Keywords

gait analysis; human-robot interaction; interactive devices; object recognition; pattern clustering; Microsoft Kinect; candidate unsupervised clustering algorithm; consumer-level sensor; gait sample clustering; individual person recognition; k-means algorithm; people unsupervised clustering; three-dimensional skeleton data; walking gait; Clustering algorithms; Humans; Legged locomotion; Pattern recognition; Signal processing algorithms; Skeleton; Gait analysis; HRI; unsupervised clustering;

fLanguage

English

Publisher

ieee

Conference_Titel

Human-Robot Interaction (HRI), 2012 7th ACM/IEEE International Conference on

Conference_Location

Boston, MA

ISSN

2167-2121

Print_ISBN

978-1-4503-1063-5

Electronic_ISBN

2167-2121

Type

conf

Filename

6249539

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=565554