View in EDS HTML Full Text PDF Full Text

DustNet++: Deep Learning-Based Visual Regression for Dust Density Estimation.

Saved in:
Bibliographic Details
Title: DustNet++: Deep Learning-Based Visual Regression for Dust Density Estimation.
Authors: Michel, Andreas1,2 (AUTHOR) andreas.michel@iosb.fraunhofer.de, Weinmann, Martin2 (AUTHOR) martin.weinmann@kit.edu, Kuester, Jannick1 (AUTHOR) jannick.kuester@iosb.fraunhofer.de, AlNasser, Faisal3 (AUTHOR) alnasser@mit.edu, Gomez, Tomas4 (AUTHOR) tomas@meteodata.cl, Falvey, Mark4 (AUTHOR) falvey@meteodata.cl, Schmitz, Rainer4 (AUTHOR) schmitzr@meteodata.cl, Middelmann, Wolfgang1 (AUTHOR) wolfgang.middelmann@iosb.fraunhofer.de, Hinz, Stefan2 (AUTHOR) stefan.hinz@kit.edu
Source: International Journal of Computer Vision. Jul2025, Vol. 133 Issue 7, p4220-4244. 25p.
Subjects: Sustainable construction, Visual learning, Dust, Machine learning, Monoculars
Abstract: Detecting airborne dust in standard RGB images presents significant challenges. Nevertheless, the monitoring of airborne dust holds substantial potential benefits for climate protection, environmentally sustainable construction, scientific research, and various other fields. To develop an efficient and robust algorithm for airborne dust monitoring, several hurdles have to be addressed. Airborne dust can be opaque or translucent, exhibit considerable variation in density, and possess indistinct boundaries. Moreover, distinguishing dust from other atmospheric phenomena, such as fog or clouds, can be particularly challenging. To meet the demand for a high-performing and reliable method for monitoring airborne dust, we introduce DustNet++, a neural network designed for dust density estimation. DustNet++ leverages feature maps from multiple resolution scales and semantic levels through window and grid attention mechanisms to maintain a sparse, globally effective receptive field with linear complexity. To validate our approach, we benchmark the performance of DustNet++ against existing methods from the domains of crowd counting and monocular depth estimation using the Meteodata airborne dust dataset and the URDE binary dust segmentation dataset. Our findings demonstrate that DustNet++ surpasses comparative methodologies in terms of regression and localization capabilities. [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
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 185781622
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: DustNet++: Deep Learning-Based Visual Regression for Dust Density Estimation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Michel%2C+Andreas%22">Michel, Andreas</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> andreas.michel@iosb.fraunhofer.de</i><br /><searchLink fieldCode="AR" term="%22Weinmann%2C+Martin%22">Weinmann, Martin</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> martin.weinmann@kit.edu</i><br /><searchLink fieldCode="AR" term="%22Kuester%2C+Jannick%22">Kuester, Jannick</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jannick.kuester@iosb.fraunhofer.de</i><br /><searchLink fieldCode="AR" term="%22AlNasser%2C+Faisal%22">AlNasser, Faisal</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> alnasser@mit.edu</i><br /><searchLink fieldCode="AR" term="%22Gomez%2C+Tomas%22">Gomez, Tomas</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> tomas@meteodata.cl</i><br /><searchLink fieldCode="AR" term="%22Falvey%2C+Mark%22">Falvey, Mark</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> falvey@meteodata.cl</i><br /><searchLink fieldCode="AR" term="%22Schmitz%2C+Rainer%22">Schmitz, Rainer</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> schmitzr@meteodata.cl</i><br /><searchLink fieldCode="AR" term="%22Middelmann%2C+Wolfgang%22">Middelmann, Wolfgang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wolfgang.middelmann@iosb.fraunhofer.de</i><br /><searchLink fieldCode="AR" term="%22Hinz%2C+Stefan%22">Hinz, Stefan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> stefan.hinz@kit.edu</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Computer+Vision%22">International Journal of Computer Vision</searchLink>. Jul2025, Vol. 133 Issue 7, p4220-4244. 25p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Sustainable+construction%22">Sustainable construction</searchLink><br /><searchLink fieldCode="DE" term="%22Visual+learning%22">Visual learning</searchLink><br /><searchLink fieldCode="DE" term="%22Dust%22">Dust</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Monoculars%22">Monoculars</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Detecting airborne dust in standard RGB images presents significant challenges. Nevertheless, the monitoring of airborne dust holds substantial potential benefits for climate protection, environmentally sustainable construction, scientific research, and various other fields. To develop an efficient and robust algorithm for airborne dust monitoring, several hurdles have to be addressed. Airborne dust can be opaque or translucent, exhibit considerable variation in density, and possess indistinct boundaries. Moreover, distinguishing dust from other atmospheric phenomena, such as fog or clouds, can be particularly challenging. To meet the demand for a high-performing and reliable method for monitoring airborne dust, we introduce DustNet++, a neural network designed for dust density estimation. DustNet++ leverages feature maps from multiple resolution scales and semantic levels through window and grid attention mechanisms to maintain a sparse, globally effective receptive field with linear complexity. To validate our approach, we benchmark the performance of DustNet++ against existing methods from the domains of crowd counting and monocular depth estimation using the Meteodata airborne dust dataset and the URDE binary dust segmentation dataset. Our findings demonstrate that DustNet++ surpasses comparative methodologies in terms of regression and localization capabilities. [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=185781622
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11263-025-02376-9
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 25
        StartPage: 4220
    Subjects:
      – SubjectFull: Sustainable construction
        Type: general
      – SubjectFull: Visual learning
        Type: general
      – SubjectFull: Dust
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Monoculars
        Type: general
    Titles:
      – TitleFull: DustNet++: Deep Learning-Based Visual Regression for Dust Density Estimation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Michel, Andreas
      – PersonEntity:
          Name:
            NameFull: Weinmann, Martin
      – PersonEntity:
          Name:
            NameFull: Kuester, Jannick
      – PersonEntity:
          Name:
            NameFull: AlNasser, Faisal
      – PersonEntity:
          Name:
            NameFull: Gomez, Tomas
      – PersonEntity:
          Name:
            NameFull: Falvey, Mark
      – PersonEntity:
          Name:
            NameFull: Schmitz, Rainer
      – PersonEntity:
          Name:
            NameFull: Middelmann, Wolfgang
      – PersonEntity:
          Name:
            NameFull: Hinz, Stefan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 09205691
          Numbering:
            – Type: volume
              Value: 133
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: International Journal of Computer Vision
              Type: main
ResultId 1