View in EDS PDF Full Text

Excessive Noise Injection Training of Neural Networks for Markerless Tracking in Obscured and Segmented Environments.

Saved in:
Bibliographic Details
Title: Excessive Noise Injection Training of Neural Networks for Markerless Tracking in Obscured and Segmented Environments.
Authors: Unsworth, C. P., Coghill, G.
Source: Neural Computation. Sep2006, Vol. 18 Issue 9, p2122-2145. 24p.
Subjects: Artificial neural networks, Error detection & recovery in robotics, Blocking (Motion pictures), Real-time control, Optical images, Object monitors (Computer software), Extension (Logic)
Abstract: In this letter, we demonstrate that the generalization properties of a neural network (NN) can be extended to encompass objects that obscure or segment the original image in its foreground or background. We achieve this by piloting an extension of the noise injection training technique, which we term excessive noise injection (ENI), on a simple feedforward multilayer perceptron (MLP) network with vanilla backward error propagation to achieve this aim. Six tests are reported that show the ability of an NN to distinguish six similar states of motion of a simplified human figure that has become obscured by moving vertical and horizontal bars and random blocks for different levels of obscuration. Four more extensive tests are then reported to determine the bounds of the technique. The results from the ENI network were compared to results from the same NN trained on clean states only. The results pilot strong evidence that it is possible to track a human subject behind objects using this technique, and thus this technique lends itself to a real-time markerless tracking system from a single video stream. [ABSTRACT FROM AUTHOR]
Copyright of Neural Computation is the property of MIT Press 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: Psychology and Behavioral Sciences Collection
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: pbh
DbLabel: Psychology and Behavioral Sciences Collection
An: 21711412
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Excessive Noise Injection Training of Neural Networks for Markerless Tracking in Obscured and Segmented Environments.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Unsworth%2C+C%2E+P%2E%22">Unsworth, C. P.</searchLink><br /><searchLink fieldCode="AR" term="%22Coghill%2C+G%2E%22">Coghill, G.</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Computation%22">Neural Computation</searchLink>. Sep2006, Vol. 18 Issue 9, p2122-2145. 24p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Error+detection+%26+recovery+in+robotics%22">Error detection & recovery in robotics</searchLink><br /><searchLink fieldCode="DE" term="%22Blocking+%28Motion+pictures%29%22">Blocking (Motion pictures)</searchLink><br /><searchLink fieldCode="DE" term="%22Real-time+control%22">Real-time control</searchLink><br /><searchLink fieldCode="DE" term="%22Optical+images%22">Optical images</searchLink><br /><searchLink fieldCode="DE" term="%22Object+monitors+%28Computer+software%29%22">Object monitors (Computer software)</searchLink><br /><searchLink fieldCode="DE" term="%22Extension+%28Logic%29%22">Extension (Logic)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In this letter, we demonstrate that the generalization properties of a neural network (NN) can be extended to encompass objects that obscure or segment the original image in its foreground or background. We achieve this by piloting an extension of the noise injection training technique, which we term excessive noise injection (ENI), on a simple feedforward multilayer perceptron (MLP) network with vanilla backward error propagation to achieve this aim. Six tests are reported that show the ability of an NN to distinguish six similar states of motion of a simplified human figure that has become obscured by moving vertical and horizontal bars and random blocks for different levels of obscuration. Four more extensive tests are then reported to determine the bounds of the technique. The results from the ENI network were compared to results from the same NN trained on clean states only. The results pilot strong evidence that it is possible to track a human subject behind objects using this technique, and thus this technique lends itself to a real-time markerless tracking system from a single video stream. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Neural Computation is the property of MIT Press 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=pbh&AN=21711412
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1162/neco.2006.18.9.2122
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 2122
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Error detection & recovery in robotics
        Type: general
      – SubjectFull: Blocking (Motion pictures)
        Type: general
      – SubjectFull: Real-time control
        Type: general
      – SubjectFull: Optical images
        Type: general
      – SubjectFull: Object monitors (Computer software)
        Type: general
      – SubjectFull: Extension (Logic)
        Type: general
    Titles:
      – TitleFull: Excessive Noise Injection Training of Neural Networks for Markerless Tracking in Obscured and Segmented Environments.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Unsworth, C. P.
      – PersonEntity:
          Name:
            NameFull: Coghill, G.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2006
              Type: published
              Y: 2006
          Identifiers:
            – Type: issn-print
              Value: 08997667
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: Neural Computation
              Type: main
ResultId 1