elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Peak-CNN: improved particle image localization using single-stage CNNs

Godbersen, Philipp und Schanz, Daniel und Schröder, Andreas (2024) Peak-CNN: improved particle image localization using single-stage CNNs. Experiments in Fluids, 65 (10), 1 - 19. Springer Nature. doi: 10.1007/s00348-024-03884-z. ISSN 0723-4864.

[img] PDF - Verlagsversion (veröffentlichte Fassung)
1MB

Offizielle URL: https://doi.org/10.1007/s00348-024-03884-z

Kurzfassung

An important step in the application of Lagrangian particle tracking (LPT) or in general for image-based single particle identification techniques is the detection of particle image locations on the measurement images and their sub-pixel accurate position estimation. In case of volumetric measurements, this constitutes the first step in the process of recovering 3D particle positions, which is usually performed by triangulation procedures. For two-component 2D measurements, the particle localization results directly serve as input to the tracking algorithm. Depending on the quality of the image, the shape and size of the particle images and the amount of particle image overlap, it can be difficult to find all, or even only the majority, of the projected particle locations in a measurement image. Advanced strategies for 3D particle position reconstruction, such as iterative particle reconstruction (IPR), are designed to work with incomplete 2D particle detection abilities but even they can greatly benefit from a more complete detection as ambiguities and position errors are reduced. We introduce a convolutional neural network (CNN) based particle image detection scheme that significantly outperforms current conventional approaches, both on synthetic and experimental data, and enables particle image localization with a vastly higher completeness even at high image densities.

elib-URL des Eintrags:https://elib.dlr.de/207905/
Dokumentart:Zeitschriftenbeitrag
Zusätzliche Informationen:article number 153, Electronic ISSN 1432-1114, Print ISSN 0723-4864
Titel:Peak-CNN: improved particle image localization using single-stage CNNs
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Godbersen, Philippphilipp.godbersen (at) dlr.dehttps://orcid.org/0000-0002-0917-4897NICHT SPEZIFIZIERT
Schanz, Danieldaniel.schanz (at) dlr.dehttps://orcid.org/0000-0003-1400-4224NICHT SPEZIFIZIERT
Schröder, Andreasandreas.schröder (at) dlr.dehttps://orcid.org/0000-0002-6971-9262172131107
Datum:8 Oktober 2024
Erschienen in:Experiments in Fluids
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Ja
Band:65
DOI:10.1007/s00348-024-03884-z
Seitenbereich:1 - 19
Verlag:Springer Nature
Name der Reihe:Springer Nature
ISSN:0723-4864
Status:veröffentlicht
Stichwörter:Lagrangian particle tracking (LPT), convolutional neural network (CNN), iterative particle reconstruction (IPR), improved particle image localization, 3D particle position reconstruction, Shake-The-Box algorithm
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Luftfahrt
HGF - Programmthema:Effizientes Luftfahrzeug
DLR - Schwerpunkt:Luftfahrt
DLR - Forschungsgebiet:L EV - Effizientes Luftfahrzeug
DLR - Teilgebiet (Projekt, Vorhaben):L - Virtuelles Flugzeug und Validierung
Standort: Göttingen
Institute & Einrichtungen:Institut für Aerodynamik und Strömungstechnik > Experimentelle Verfahren, GO
Hinterlegt von: Micknaus, Ilka
Hinterlegt am:20 Nov 2024 15:29
Letzte Änderung:20 Nov 2024 15:29

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.