Distinguishing foreground and background with inframed imaging

An initial candidate foreground region is identified within an infrared image that includes pixels exhibiting infrared intensity values within a pre-defined range. A depth of surfaces within the initial candidate foreground region is estimated based on infrared intensity values the pixels of the ini...

Full description

Saved in:
Bibliographic Details
Format Patent
LanguageEnglish
Published 24.04.2018
Online AccessGet full text

Cover

Abstract An initial candidate foreground region is identified within an infrared image that includes pixels exhibiting infrared intensity values within a pre-defined range. A depth of surfaces within the initial candidate foreground region is estimated based on infrared intensity values the pixels of the initial candidate foreground region. The initial candidate foreground region is expanded to an expanded candidate foreground region based on a body-model estimate. The body model estimate is seeded with one or more of the initial candidate foreground region, the depth of surfaces, and/or a face of a human subject identified by facial recognition. Each pixel of the infrared image is identified as either a foreground pixel or a background pixel based on a distance of that pixel relative to the expanded candidate foreground region. Pixels identified as background pixels may be modified within a corresponding visible light image.
AbstractList An initial candidate foreground region is identified within an infrared image that includes pixels exhibiting infrared intensity values within a pre-defined range. A depth of surfaces within the initial candidate foreground region is estimated based on infrared intensity values the pixels of the initial candidate foreground region. The initial candidate foreground region is expanded to an expanded candidate foreground region based on a body-model estimate. The body model estimate is seeded with one or more of the initial candidate foreground region, the depth of surfaces, and/or a face of a human subject identified by facial recognition. Each pixel of the infrared image is identified as either a foreground pixel or a background pixel based on a distance of that pixel relative to the expanded candidate foreground region. Pixels identified as background pixels may be modified within a corresponding visible light image.
BookMark eNrjYmDJy89L5WSwc8ksLsnMSy_NLM4AUgpp-UWp6UX5pXkpColAnJSYnA3llmeWZChk5qUVJeampihk5iamA9XzMLCmJeYUp_JCaW4GBTfXEGcP3dLigsSS1LyS4vj0okQQZWBpaWpqaGJgTIQSAHzXM8g
ContentType Patent
CorporateAuthor MICROSOFT TECHNOLOGY LICENSING, LLC
CorporateAuthor_xml – name: MICROSOFT TECHNOLOGY LICENSING, LLC
DBID EFH
DatabaseName USPTO Issued Patents
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EFH
  name: USPTO Issued Patents
  url: http://www.uspto.gov/patft/index.html
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
ExternalDocumentID 09955140
GroupedDBID EFH
ID FETCH-uspatents_grants_099551403
IEDL.DBID EFH
IngestDate Sun Mar 05 22:37:18 EST 2023
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-uspatents_grants_099551403
OpenAccessLink https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/9955140
ParticipantIDs uspatents_grants_09955140
PatentNumber 9955140
PublicationCentury 2000
PublicationDate 20180424
PublicationDateYYYYMMDD 2018-04-24
PublicationDate_xml – month: 04
  year: 2018
  text: 20180424
  day: 24
PublicationDecade 2010
PublicationYear 2018
References Raghoebardajal (2015/0054734) 20150200
Black (2010/0111370) 20100500
Adeyoola (2014/0176565) 20140600
Lin (9055186) 20150600
Booms (2013/0222246) 20130800
Gray (9367951) 20160600
Everitt (2014/0282275) 20140900
Stroetmann (2015/0189256) 20150700
Uomori (6587183) 20030700
Dedhia (2013/0287257) 20131000
Cutler et al. (2014/0176663) 20140600
Sundstrom (8260131) 20120900
Steinberg et al. (8593542) 20131100
Holz (2014/0369558) 20141200
Raheman et al. (2014/0178029) 20140600
(2667066) 20101100
Karakotsios (8902198) 20141200
Ricci (2014/0309868) 20141000
Schinker (8823807) 20140900
Hummel (2013/0342671) 20131200
Lin (2015/0029294) 20150100
Zhang et al. (7783075) 20100800
Perlman (2013/0038766) 20130200
References_xml – year: 20141200
  ident: 8902198
– year: 20140600
  ident: 2014/0176565
– year: 20131100
  ident: 8593542
– year: 20140600
  ident: 2014/0178029
– year: 20030700
  ident: 6587183
– year: 20141200
  ident: 2014/0369558
– year: 20150600
  ident: 9055186
– year: 20140600
  ident: 2014/0176663
– year: 20150200
  ident: 2015/0054734
– year: 20131000
  ident: 2013/0287257
– year: 20130800
  ident: 2013/0222246
– year: 20101100
  ident: 2667066
– year: 20160600
  ident: 9367951
– year: 20131200
  ident: 2013/0342671
– year: 20150100
  ident: 2015/0029294
– year: 20120900
  ident: 8260131
– year: 20140900
  ident: 2014/0282275
– year: 20141000
  ident: 2014/0309868
– year: 20100800
  ident: 7783075
– year: 20130200
  ident: 2013/0038766
– year: 20140900
  ident: 8823807
– year: 20100500
  ident: 2010/0111370
– year: 20150700
  ident: 2015/0189256
Score 3.0681188
Snippet An initial candidate foreground region is identified within an infrared image that includes pixels exhibiting infrared intensity values within a pre-defined...
SourceID uspatents
SourceType Open Access Repository
Title Distinguishing foreground and background with inframed imaging
URI https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/9955140
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfVxLT8MwDLbGhAScQIAYL-XANVBa93XZZVBVSKAdQNptSvPYAcimtdX-PnY7TVzgmIccK47z2Y5jgDuMbBgpW8lMKc3RqkeZ6dzJWKeKEDF1qqul9_qWlB_4MotnAyh3f2G-SY3kinip79t61Sy75Eq63nvBy774M9cI9Fx9YOO_lspMjXvIc8Z-ct736ISxWVSUR3BAJMhk8039CzSKY9ifdr0nMLD-FMZPrE5-0fZRH0HWouU_Fd4I8uZFpfTntsmxUUGS57wpI5hXmn8Gonh-n5Ryt9h8seYklnmwZSo6hyE58_YCRJKi1iFWTqsAMaZrL1HoEjRBmhOK4AhGf5K5_GfsCg4JyjN-5wjxGobNurU3BJdNddvtxQ-kXXca
linkProvider USPTO
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfVxLT8MwDLamgXicQIAYzxy4Bkqbvi67bKvKa-oBpN2qNEl3gGXT2oq_j91OExc45iHHiuN8sWMb4E54xvWkKXgkpSJv1SOPVFxyX4USETEsZVtL720apB_ieebPepBuc2EWqEZ8hbxU9021qpdtcCVe753geVf8mWoEWqo-8G2_llJnunyIY8J-NN538ES5pKKTJD2EfSSCjzZbV79gIzmC3aztPYaesScwHJNC2XnT-X0YvhcNZVVYzdCeZ4VUn5smeUcZyp4ipzQjbnH-KbBk8j5K-XaxfL6mMJbc2bDlnUEfzXlzDiwIhVKuKEolHSF8vPgCKcpAaCeMEUfEAAZ_krn4Z-wW9rJxkr8-TV8u4QBxPaJPD1dcQb9eN-YasbMubtpt-QGYvHoK
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=Distinguishing+foreground+and+background+with+inframed+imaging&rft.number=9955140&rft.date=2018-04-24&rft.externalDBID=n%2Fa&rft.externalDocID=09955140