Real-time action detection and classification

The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring si...

Full description

Saved in:
Bibliographic Details
Main Authors CHENG HUI, XIAO JIANGJIAN, GUO YANLIN, SAWHNEY HARPREET SINGH, JUNG SANG-HACK, HAN FENG, KUMAR RAKESH
Format Patent
LanguageEnglish
Published 21.01.2014
Subjects
Online AccessGet full text

Cover

Loading…
Abstract The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.
AbstractList The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.
Author HAN FENG
JUNG SANG-HACK
KUMAR RAKESH
CHENG HUI
XIAO JIANGJIAN
GUO YANLIN
SAWHNEY HARPREET SINGH
Author_xml – fullname: CHENG HUI
– fullname: XIAO JIANGJIAN
– fullname: GUO YANLIN
– fullname: SAWHNEY HARPREET SINGH
– fullname: JUNG SANG-HACK
– fullname: HAN FENG
– fullname: KUMAR RAKESH
BookMark eNrjYmDJy89L5WTQDUpNzNEtycxNVUhMLsnMz1NISS1JhbAS81IUknMSi4sz0zKTE0FCPAysaYk5xam8UJqbQcHNNcTZQze1ID8-tbggMTk1L7UkPjTYwszYxMzYwsnImAglAGb-K8w
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US8634638B2
GroupedDBID EVB
ID FETCH-epo_espacenet_US8634638B23
IEDL.DBID EVB
IngestDate Fri Jul 19 15:04:09 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US8634638B23
Notes Application Number: US20090488911
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20140121&DB=EPODOC&CC=US&NR=8634638B2
ParticipantIDs epo_espacenet_US8634638B2
PublicationCentury 2000
PublicationDate 20140121
PublicationDateYYYYMMDD 2014-01-21
PublicationDate_xml – month: 01
  year: 2014
  text: 20140121
  day: 21
PublicationDecade 2010
PublicationYear 2014
RelatedCompanies HAN FENG
JUNG SANG-HACK
KUMAR RAKESH
CHENG HUI
XIAO JIANGJIAN
GUO YANLIN
SAWHNEY HARPREET SINGH
SRI INTERNATIONAL
RelatedCompanies_xml – name: GUO YANLIN
– name: KUMAR RAKESH
– name: SRI INTERNATIONAL
– name: JUNG SANG-HACK
– name: XIAO JIANGJIAN
– name: HAN FENG
– name: SAWHNEY HARPREET SINGH
– name: CHENG HUI
Score 2.912306
Snippet The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Title Real-time action detection and classification
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20140121&DB=EPODOC&locale=&CC=US&NR=8634638B2
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1La8MwDBale962bGPdixxGbmbYdZrmEAbNgzLog7YZvZXEdqCXtCwZ-_uT3bTbZbsZG4Rk_OlhSzLAM3rAbsZ4TrjHM8L7VJBMeIxQiQsFWlQmde3waNwbpvxt6S5bsN7Xwpg-oV-mOSIiSiDea6Ovtz-XWJHJraxe8jVObV6TRRA5TXSsowVGnWgQxNNJNAmdMAzSuTOeBf1el-NRG6C2PtJetG6zH78PdFHK9rdFSS7geIrEyvoSWqq04Czcf7xmwemoee-24MQkaIoKJxsQVldAZujcEf0pvL2rSrClqtVulJXSFtoh1hlARo5rsJN4EQ4JcrA6SLtK5wdeuzfQLjelugWbKpVLoTJXFYrT3PclFX7BWeFzxKTndqDzJ5m7f9bu4Vxvm75UYPQB2vXHp3pEM1vnT2aDvgG2UoHH
link.rule.ids 230,309,786,891,25594,76906
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8MwDLam8Rg3KCDGswfUW4TSpet6qJDabhqwl7YW7Va1aSrt0k20iL-Pk3WDC9yiRLLsKJ8fie0APKIHbCUmSwmzWUJYj3KScNskNMOFHC2qmcna4fGkO4zY69JaNmC1q4VRfUK_VHNERBRHvFdKX29-LrEClVtZPqUrnFo_D0I3MOroWEYLJjUCz-3PpsHUN3zfjRbGZO72uh2GR81DbX1gy-a80nN692RRyua3RRmcwuEMiRXVGTREoUHL3328psHxuH7v1uBIJWjyEidrEJbnQObo3BH5Kby-rUrQM1GJ7SgpMp1Lh1hmACk5LkAf9EN_SJCDeC9tHC32vHYuoVmsC3EFOhUizbhILJELRlPHySh3cmbmDkNM2lYb2n-Suf5n7QFaw3A8ikcvk7cbOJFbKC8YTHoLzerjU9yhya3Se7VZ3_C0hLQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Real-time+action+detection+and+classification&rft.inventor=CHENG+HUI&rft.inventor=XIAO+JIANGJIAN&rft.inventor=GUO+YANLIN&rft.inventor=SAWHNEY+HARPREET+SINGH&rft.inventor=JUNG+SANG-HACK&rft.inventor=HAN+FENG&rft.inventor=KUMAR+RAKESH&rft.date=2014-01-21&rft.externalDBID=B2&rft.externalDocID=US8634638B2