Zobrazit v EDS

FrictionSegNet: Simultaneous Semantic Segmentation and Friction Estimation Using Hierarchical Latent Variable Models

Uloženo v:
Podrobná bibliografie
Název: FrictionSegNet: Simultaneous Semantic Segmentation and Friction Estimation Using Hierarchical Latent Variable Models
Autoři: Otoofi, Mohammad, Laine, Leo, 1972, Henderson, Leon, 1986, Midgley, William J. B., Justham, Laura, Fleming, James
Zdroj: IEEE Transactions on Intelligent Transportation Systems. 25(12):19785-19795
Témata: Roads, variational auto-encoders, Training, Snow, deep neural networks, Real-time systems, Semantic segmentation, Friction, Ice, Computational modeling, Tyre-road friction coefficient, latent variable model, Semantics, Estimation
Popis: This paper presents an end-to-end approach, named FrictionSegNet, for jointly estimating tyre-road friction coefficient and identifying road surfaces in real time from on board camera data. FrictionSegNet combines semantic segmentation and friction estimation by learning a shared latent space that encompasses both semantic segmentation and friction coefficient information. An objective function is designed for this task and minimised using *geco to train the model, providing the ability to control the balance between improved predictions and uncertainty measurement. To the best of our knowledge, this study is the first attempt to jointly estimate tyre-road friction and surface type by learning the joint latent space of semantic segmentation and friction coefficient information. The results suggest that it is possible to identify low-friction surfaces, e.g. snow or ice, and estimate upcoming road friction in real time from a camera only. As it is of interest to develop techniques that require less training data, numerical experiments were performed using transfer learning from a dataset consisting of images of various road surfaces. This led to better performance and faster convergence during training. FrictionSegNet achieved per-pixel accuracies of 97% and 95% when identifying snow and ice respectively, and RMS errors of 0.04 - 0.09 when estimating mu values achievable by a truck anti-lock braking system (ABS) on gravel, dry and wet asphalt, snow, and ice surfaces.
Přístupová URL adresa: https://research.chalmers.se/publication/543319
Databáze: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=15249050&ISBN=&volume=25&issue=12&date=20240101&spage=19785&pages=19785-19795&title=IEEE Transactions on Intelligent Transportation Systems&atitle=FrictionSegNet%3A%20Simultaneous%20Semantic%20Segmentation%20and%20Friction%20Estimation%20Using%20Hierarchical%20Latent%20Variable%20Models&aulast=Otoofi%2C%20Mohammad&id=DOI:10.1109/TITS.2024.3463952
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Otoofi%20M
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.6d0094b0.8cf4.41be.892a.b3103f244156
RelevancyScore: 964
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 964.415405273438
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: FrictionSegNet: Simultaneous Semantic Segmentation and Friction Estimation Using Hierarchical Latent Variable Models
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Otoofi%2C+Mohammad%22">Otoofi, Mohammad</searchLink><br /><searchLink fieldCode="AR" term="%22Laine%2C+Leo%22">Laine, Leo</searchLink>, 1972<br /><searchLink fieldCode="AR" term="%22Henderson%2C+Leon%22">Henderson, Leon</searchLink>, 1986<br /><searchLink fieldCode="AR" term="%22Midgley%2C+William+J%2E+B%2E%22">Midgley, William J. B.</searchLink><br /><searchLink fieldCode="AR" term="%22Justham%2C+Laura%22">Justham, Laura</searchLink><br /><searchLink fieldCode="AR" term="%22Fleming%2C+James%22">Fleming, James</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>IEEE Transactions on Intelligent Transportation Systems</i>. 25(12):19785-19795
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Roads%22">Roads</searchLink><br /><searchLink fieldCode="DE" term="%22variational+auto-encoders%22">variational auto-encoders</searchLink><br /><searchLink fieldCode="DE" term="%22Training%22">Training</searchLink><br /><searchLink fieldCode="DE" term="%22Snow%22">Snow</searchLink><br /><searchLink fieldCode="DE" term="%22deep+neural+networks%22">deep neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Real-time+systems%22">Real-time systems</searchLink><br /><searchLink fieldCode="DE" term="%22Semantic+segmentation%22">Semantic segmentation</searchLink><br /><searchLink fieldCode="DE" term="%22Friction%22">Friction</searchLink><br /><searchLink fieldCode="DE" term="%22Ice%22">Ice</searchLink><br /><searchLink fieldCode="DE" term="%22Computational+modeling%22">Computational modeling</searchLink><br /><searchLink fieldCode="DE" term="%22Tyre-road+friction+coefficient%22">Tyre-road friction coefficient</searchLink><br /><searchLink fieldCode="DE" term="%22latent+variable+model%22">latent variable model</searchLink><br /><searchLink fieldCode="DE" term="%22Semantics%22">Semantics</searchLink><br /><searchLink fieldCode="DE" term="%22Estimation%22">Estimation</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: This paper presents an end-to-end approach, named FrictionSegNet, for jointly estimating tyre-road friction coefficient and identifying road surfaces in real time from on board camera data. FrictionSegNet combines semantic segmentation and friction estimation by learning a shared latent space that encompasses both semantic segmentation and friction coefficient information. An objective function is designed for this task and minimised using *geco to train the model, providing the ability to control the balance between improved predictions and uncertainty measurement. To the best of our knowledge, this study is the first attempt to jointly estimate tyre-road friction and surface type by learning the joint latent space of semantic segmentation and friction coefficient information. The results suggest that it is possible to identify low-friction surfaces, e.g. snow or ice, and estimate upcoming road friction in real time from a camera only. As it is of interest to develop techniques that require less training data, numerical experiments were performed using transfer learning from a dataset consisting of images of various road surfaces. This led to better performance and faster convergence during training. FrictionSegNet achieved per-pixel accuracies of 97% and 95% when identifying snow and ice respectively, and RMS errors of 0.04 - 0.09 when estimating mu values achievable by a truck anti-lock braking system (ABS) on gravel, dry and wet asphalt, snow, and ice surfaces.
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/543319" linkWindow="_blank">https://research.chalmers.se/publication/543319</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.6d0094b0.8cf4.41be.892a.b3103f244156
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TITS.2024.3463952
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 19785
    Subjects:
      – SubjectFull: Roads
        Type: general
      – SubjectFull: variational auto-encoders
        Type: general
      – SubjectFull: Training
        Type: general
      – SubjectFull: Snow
        Type: general
      – SubjectFull: deep neural networks
        Type: general
      – SubjectFull: Real-time systems
        Type: general
      – SubjectFull: Semantic segmentation
        Type: general
      – SubjectFull: Friction
        Type: general
      – SubjectFull: Ice
        Type: general
      – SubjectFull: Computational modeling
        Type: general
      – SubjectFull: Tyre-road friction coefficient
        Type: general
      – SubjectFull: latent variable model
        Type: general
      – SubjectFull: Semantics
        Type: general
      – SubjectFull: Estimation
        Type: general
    Titles:
      – TitleFull: FrictionSegNet: Simultaneous Semantic Segmentation and Friction Estimation Using Hierarchical Latent Variable Models
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Otoofi, Mohammad
      – PersonEntity:
          Name:
            NameFull: Laine, Leo
      – PersonEntity:
          Name:
            NameFull: Henderson, Leon
      – PersonEntity:
          Name:
            NameFull: Midgley, William J. B.
      – PersonEntity:
          Name:
            NameFull: Justham, Laura
      – PersonEntity:
          Name:
            NameFull: Fleming, James
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 15249050
            – Type: issn-print
              Value: 15580016
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 25
            – Type: issue
              Value: 12
          Titles:
            – TitleFull: IEEE Transactions on Intelligent Transportation Systems
              Type: main
ResultId 1