KIT | KIT-Bibliothek | Impressum | Datenschutz

Particle detection by means of neural networks and synthetic training data refinement in defocusing particle tracking velocimetry

Dreisbach, Maximilian ORCID iD icon 1; Leister, Robin ORCID iD icon 1; Probst, Matthias ORCID iD icon 2; Friederich, Pascal ORCID iD icon 3,4; Stroh, Alexander 1; Kriegseis, Jochen ORCID iD icon 1
1 Institut für Strömungsmechanik (ISTM), Karlsruher Institut für Technologie (KIT)
2 Institut für Thermische Strömungsmaschinen (ITS), Karlsruher Institut für Technologie (KIT)
3 Institut für Theoretische Informatik (ITI), Karlsruher Institut für Technologie (KIT)
4 Institut für Nanotechnologie (INT), Karlsruher Institut für Technologie (KIT)


The presented work addresses the problem of particle detection with neural networks (NNs) in defocusing particle tracking velocimetry. A novel approach based on synthetic training data refinement is introduced, with the scope of revising the well documented performance gap of synthetically trained NNs, applied to experimental recordings. In particular, synthetic particle image (PI) data is enriched with image features from the experimental recordings by means of deep learning through an unsupervised image-to-image translation. It is demonstrated that this refined synthetic training data enables the neural-network-based particle detection for a simultaneous increase in detection rate and reduction in the rate of false positives, beyond the capability of conventional detection algorithms. The potential for an increased accuracy in particle detection is revealed with NNs that utilise small scale image features, which further underlines the importance of representative training data. In addition, it is demonstrated that NNs are able to resolve overlapping PIs with a higher reliability and accuracy in comparison to conventional algorithms, suggesting the possibility of an increased seeding density in real experiments. ... mehr

Verlagsausgabe §
DOI: 10.5445/IR/1000150804
Veröffentlicht am 20.09.2022
DOI: 10.1088/1361-6501/ac8a09
Zitationen: 5
Web of Science
Zitationen: 5
Zitationen: 5
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Nanotechnologie (INT)
Institut für Strömungsmechanik (ISTM)
Institut für Theoretische Informatik (ITI)
Institut für Thermische Strömungsmaschinen (ITS)
Publikationstyp Zeitschriftenaufsatz
Publikationsdatum 01.12.2022
Sprache Englisch
Identifikator ISSN: 0957-0233, 1361-6501
KITopen-ID: 1000150804
HGF-Programm 43.31.01 (POF IV, LK 01) Multifunctionality Molecular Design & Material Architecture
Erschienen in Measurement Science and Technology
Verlag Institute of Physics Publishing Ltd (IOP Publishing Ltd)
Band 33
Heft 12
Seiten Art.Nr. 124001
Vorab online veröffentlicht am 08.09.2022
Nachgewiesen in Web of Science
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page