View in EDS PDF Full Text

Multi-modal RGB-Depth-Thermal Human Body Segmentation.

Saved in:
Bibliographic Details
Title: Multi-modal RGB-Depth-Thermal Human Body Segmentation.
Authors: Palmero, Cristina c.palmero.cantarino@gmail.com, Clapés, Albert aclapes@cvc.uab.cat, Bahnsen, Chris1 cb@create.aau.dk, Møgelmose, Andreas1 am@create.aau.dk, Moeslund, Thomas1 tbmg@create.aau.dk, Escalera, Sergio sergio@maia.ub.es
Source: International Journal of Computer Vision. Jun2016, Vol. 118 Issue 2, p217-239. 23p.
Subjects: Human body, Mathematical models of human behavior, Human behavior models, Supervised learning, Boosting algorithms, Mathematical models
Abstract: This work addresses the problem of human body segmentation from multi-modal visual cues as a first stage of automatic human behavior analysis. We propose a novel RGB-depth-thermal dataset along with a multi-modal segmentation baseline. The several modalities are registered using a calibration device and a registration algorithm. Our baseline extracts regions of interest using background subtraction, defines a partitioning of the foreground regions into cells, computes a set of image features on those cells using different state-of-the-art feature extractions, and models the distribution of the descriptors per cell using probabilistic models. A supervised learning algorithm then fuses the output likelihoods over cells in a stacked feature vector representation. The baseline, using Gaussian mixture models for the probabilistic modeling and Random Forest for the stacked learning, is superior to other state-of-the-art methods, obtaining an overlap above 75 % on the novel dataset when compared to the manually annotated ground-truth of human segmentations. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 115900370
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Multi-modal RGB-Depth-Thermal Human Body Segmentation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Palmero%2C+Cristina%22">Palmero, Cristina</searchLink><i> c.palmero.cantarino@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Clapés%2C+Albert%22">Clapés, Albert</searchLink><i> aclapes@cvc.uab.cat</i><br /><searchLink fieldCode="AR" term="%22Bahnsen%2C+Chris%22">Bahnsen, Chris</searchLink><relatesTo>1</relatesTo><i> cb@create.aau.dk</i><br /><searchLink fieldCode="AR" term="%22Møgelmose%2C+Andreas%22">Møgelmose, Andreas</searchLink><relatesTo>1</relatesTo><i> am@create.aau.dk</i><br /><searchLink fieldCode="AR" term="%22Moeslund%2C+Thomas%22">Moeslund, Thomas</searchLink><relatesTo>1</relatesTo><i> tbmg@create.aau.dk</i><br /><searchLink fieldCode="AR" term="%22Escalera%2C+Sergio%22">Escalera, Sergio</searchLink><i> sergio@maia.ub.es</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Computer+Vision%22">International Journal of Computer Vision</searchLink>. Jun2016, Vol. 118 Issue 2, p217-239. 23p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Human+body%22">Human body</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+models+of+human+behavior%22">Mathematical models of human behavior</searchLink><br /><searchLink fieldCode="DE" term="%22Human+behavior+models%22">Human behavior models</searchLink><br /><searchLink fieldCode="DE" term="%22Supervised+learning%22">Supervised learning</searchLink><br /><searchLink fieldCode="DE" term="%22Boosting+algorithms%22">Boosting algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+models%22">Mathematical models</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This work addresses the problem of human body segmentation from multi-modal visual cues as a first stage of automatic human behavior analysis. We propose a novel RGB-depth-thermal dataset along with a multi-modal segmentation baseline. The several modalities are registered using a calibration device and a registration algorithm. Our baseline extracts regions of interest using background subtraction, defines a partitioning of the foreground regions into cells, computes a set of image features on those cells using different state-of-the-art feature extractions, and models the distribution of the descriptors per cell using probabilistic models. A supervised learning algorithm then fuses the output likelihoods over cells in a stacked feature vector representation. The baseline, using Gaussian mixture models for the probabilistic modeling and Random Forest for the stacked learning, is superior to other state-of-the-art methods, obtaining an overlap above 75 % on the novel dataset when compared to the manually annotated ground-truth of human segmentations. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=115900370
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11263-016-0901-x
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 23
        StartPage: 217
    Subjects:
      – SubjectFull: Human body
        Type: general
      – SubjectFull: Mathematical models of human behavior
        Type: general
      – SubjectFull: Human behavior models
        Type: general
      – SubjectFull: Supervised learning
        Type: general
      – SubjectFull: Boosting algorithms
        Type: general
      – SubjectFull: Mathematical models
        Type: general
    Titles:
      – TitleFull: Multi-modal RGB-Depth-Thermal Human Body Segmentation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Palmero, Cristina
      – PersonEntity:
          Name:
            NameFull: Clapés, Albert
      – PersonEntity:
          Name:
            NameFull: Bahnsen, Chris
      – PersonEntity:
          Name:
            NameFull: Møgelmose, Andreas
      – PersonEntity:
          Name:
            NameFull: Moeslund, Thomas
      – PersonEntity:
          Name:
            NameFull: Escalera, Sergio
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2016
              Type: published
              Y: 2016
          Identifiers:
            – Type: issn-print
              Value: 09205691
          Numbering:
            – Type: volume
              Value: 118
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: International Journal of Computer Vision
              Type: main
ResultId 1