A new approach for classification of human gait based on time frequency feature representations.

We introduce a new and simple technique for human gait classification based on the time-frequency analysis of radar data. The focus is on the classification of arm movements to discern free vs. confined arm swinging motion. The latter may arise in hostage situation or may be indicative to carrying objects with one or both hands. The motion signatures corresponding to the arm and leg movements are both extracted from the time-frequency representation of the micro-Doppler. The time-frequency analysis is performed using the multiwindow S-method. With the Hermite functions acting as multiwindows, it is shown that the Hermite S-method provides an efficient representation of the complex Doppler associated with human walking. The proposed human gait classification technique utilizes the arm positive and negative Doppler frequencies and their relative time of occurrence. It is tested on various real radar signals and shown to provide an accurate classification.

Main Author: Orovic, Irena.
Other Authors: Stankovic, Srdjan., Amin, Moeness.
Format: Villanova Faculty Authorship
Language: English
Published: 2011
Online Access: http://ezproxy.villanova.edu/login?url=https://digital.library.villanova.edu/Item/vudl:173063
PID vudl:173063
id vudl:173063
modeltype_str_mv vudl-system:CoreModel
vudl-system:CollectionModel
vudl-system:ResourceCollection
datastream_str_mv DC
PARENT-QUERY
PARENT-LIST-RAW
PARENT-LIST
MEMBER-QUERY
MEMBER-LIST-RAW
LEGACY-METS
LICENSE
AGENTS
PROCESS-MD
THUMBNAIL
STRUCTMAP
RELS-EXT
hierarchytype
sequence_vudl_173023_str 0000000014
has_order_str no
hierarchy_top_id vudl:641262
hierarchy_top_title Villanova faculty author
hierarchy_parent_id vudl:173023
hierarchy_parent_title Amin Moeness
hierarchy_sequence 0000000014
hierarchy_first_parent_id_str vudl:173063
hierarchy_sequence_sort_str 0000000014
hierarchy_all_parents_str_mv vudl:172968
vudl:641262
vudl:173023
first_indexed 2014-01-11T21:56:57Z
last_indexed 2021-04-12T19:22:12Z
recordtype vudl
fullrecord <root> <url> http://digital.library.villanova.edu/files/vudl:173063/DC </url> <thumbnail> http://digital.library.villanova.edu/files/vudl:173063/THUMBNAIL </thumbnail> </root>
spelling
institution Villanova University
collection Digital Library
language English
dc_source_str_mv Special Issue on Fourier related time-frequency transforms for non-stationary signals, Volume 91, Issue 6, June 2011, Pages 1448- 1456.
author Orovic, Irena.
author_facet_str_mv Orovic, Irena.
Stankovic, Srdjan.
Amin, Moeness.
author_or_contributor_facet_str_mv Orovic, Irena.
Stankovic, Srdjan.
Amin, Moeness.
author_s Orovic, Irena.
spellingShingle Orovic, Irena.
A new approach for classification of human gait based on time frequency feature representations.
author-letter Orovic, Irena.
author_sort_str Orovic, Irena.
author2 Stankovic, Srdjan.
Amin, Moeness.
author2Str Stankovic, Srdjan.
Amin, Moeness.
dc_title_str A new approach for classification of human gait based on time frequency feature representations.
title A new approach for classification of human gait based on time frequency feature representations.
title_short A new approach for classification of human gait based on time frequency feature representations.
title_full A new approach for classification of human gait based on time frequency feature representations.
title_fullStr A new approach for classification of human gait based on time frequency feature representations.
title_full_unstemmed A new approach for classification of human gait based on time frequency feature representations.
collection_title_sort_str new approach for classification of human gait based on time frequency feature representations.
title_sort new approach for classification of human gait based on time frequency feature representations.
format Villanova Faculty Authorship
description We introduce a new and simple technique for human gait classification based on the time-frequency analysis of radar data. The focus is on the classification of arm movements to discern free vs. confined arm swinging motion. The latter may arise in hostage situation or may be indicative to carrying objects with one or both hands. The motion signatures corresponding to the arm and leg movements are both extracted from the time-frequency representation of the micro-Doppler. The time-frequency analysis is performed using the multiwindow S-method. With the Hermite functions acting as multiwindows, it is shown that the Hermite S-method provides an efficient representation of the complex Doppler associated with human walking. The proposed human gait classification technique utilizes the arm positive and negative Doppler frequencies and their relative time of occurrence. It is tested on various real radar signals and shown to provide an accurate classification.
publishDate 2011
normalized_sort_date 2011-01-01T00:00:00Z
dc_date_str 2011
license_str protected
REPOSITORYNAME FgsRepos
REPOSBASEURL http://hades.library.villanova.edu:8088/fedora
fgs.state Active
fgs.label A new approach for classification of human gait based on time frequency feature representations.
fgs.ownerId diglibEditor
fgs.createdDate 2013-01-22T02:30:45.058Z
fgs.lastModifiedDate 2021-04-12T19:05:09.736Z
dc.title A new approach for classification of human gait based on time frequency feature representations.
dc.creator Orovic, Irena.
Stankovic, Srdjan.
Amin, Moeness.
dc.description We introduce a new and simple technique for human gait classification based on the time-frequency analysis of radar data. The focus is on the classification of arm movements to discern free vs. confined arm swinging motion. The latter may arise in hostage situation or may be indicative to carrying objects with one or both hands. The motion signatures corresponding to the arm and leg movements are both extracted from the time-frequency representation of the micro-Doppler. The time-frequency analysis is performed using the multiwindow S-method. With the Hermite functions acting as multiwindows, it is shown that the Hermite S-method provides an efficient representation of the complex Doppler associated with human walking. The proposed human gait classification technique utilizes the arm positive and negative Doppler frequencies and their relative time of occurrence. It is tested on various real radar signals and shown to provide an accurate classification.
dc.date 2011
dc.format Villanova Faculty Authorship
dc.identifier vudl:173063
dc.source Special Issue on Fourier related time-frequency transforms for non-stationary signals, Volume 91, Issue 6, June 2011, Pages 1448- 1456.
dc.language en
license.mdRef http://digital.library.villanova.edu/copyright.html
agent.name Falvey Memorial Library, Villanova University
KHL
has_thumbnail true
THUMBNAIL_contentDigest_type MD5
THUMBNAIL_contentDigest_digest 203c69e18f4f46c81e9892448d2c07cd
THUMBNAIL_contentLocation_type INTERNAL_ID
THUMBNAIL_contentLocation_ref http://hades-vm.library.villanova.edu:8088/fedora/get/vudl:173063/THUMBNAIL/2013-01-22T02:30:47.678Z
relsext.hasModel info:fedora/vudl-system:CoreModel
info:fedora/vudl-system:CollectionModel
info:fedora/vudl-system:ResourceCollection
relsext.itemID oai:digital.library.villanova.edu:vudl:173063
relsext.isMemberOf info:fedora/vudl:173023
relsext.hasLegacyURL http://digital.library.villanova.edu/Villanova%20Digital%20Collection/Faculty%20Fulltext/Amin%20Moeness/AminMoeness-b538df84-5e8d-42f8-af3b-165130127062.xml
relsext.sortOn title
relsext.sequence vudl:173023#14
_version_ 1696863704114528256
score 14.05198
subpages