Please use this identifier to cite or link to this item: http://dx.doi.org/10.25673/81333
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPuzyrev, Dmitry-
dc.contributor.authorHarth, Kirsten-
dc.contributor.authorTrittel, Torsten-
dc.contributor.authorStannarius, Ralf-
dc.date.accessioned2022-04-05T06:18:48Z-
dc.date.available2022-04-05T06:18:48Z-
dc.date.issued2020-
dc.date.submitted2020-
dc.identifier.urihttps://opendata.uni-halle.de//handle/1981185920/83288-
dc.identifier.urihttp://dx.doi.org/10.25673/81333-
dc.description.abstractDilute ensembles of granular matter (so-called granular gases) are nonlinear systems which exhibit fascinating dynamical behavior far from equilibrium, including non-Gaussian distributions of velocities and rotational velocities, clustering, and violation of energy equipartition. In order to understand their dynamic properties, microgravity experiments were performed in suborbital flights and drop tower experiments. Up to now, the experimental images were evaluated mostly manually. Here, we introduce an approach for automatic 3D tracking of positions and orientations of rod-like particles in a dilute ensemble, based on two-view video data analysis. A two-dimensional (2D) localization of particles is performed using a Mask R-CNN neural network trained on a custom data set. The problem of 3D matching of the particles is solved by minimization of the total reprojection error, and finally, particle trajectories are tracked so that ensemble statistics are extracted. Depending on the required accuracy, the software can work fully self-sustainingly or serve as a base for subsequent manual corrections. The approach can be extended to other 3D and 2D particle tracking problems.eng
dc.description.sponsorshipProjekt DEAL 2020-
dc.language.isoeng-
dc.relation.ispartofhttp://link.springer.com/journal/12217-
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/-
dc.subjectMachine learningeng
dc.subjectGranular gaseng
dc.subjectParticle trackingeng
dc.subjectObject detectioneng
dc.subjectMask-CNNeng
dc.subject.ddc530-
dc.titleMachine learning for 3D particle tracking in granular gaseseng
dc.typeArticle-
dc.identifier.urnurn:nbn:de:gbv:ma9:1-1981185920-832887-
local.versionTypepublishedVersion-
local.bibliographicCitation.journaltitleMicrogravity science and technology-
local.bibliographicCitation.volume32-
local.bibliographicCitation.issue5-
local.bibliographicCitation.pagestart897-
local.bibliographicCitation.pageend906-
local.bibliographicCitation.publishernameSpringer-
local.bibliographicCitation.publisherplaceHeidelberg-
local.bibliographicCitation.doi10.1007/s12217-020-09800-4-
local.openaccesstrue-
dc.identifier.ppn1725185512-
local.bibliographicCitation.year2020-
cbs.sru.importDate2022-04-05T06:15:05Z-
local.bibliographicCitationEnthalten in Microgravity science and technology - Heidelberg : Springer, 2007-
local.accessrights.dnbfree-
Appears in Collections:Fakultät für Naturwissenschaften (OA)

Files in This Item:
File Description SizeFormat 
Puzyrev et al._Machine learning_2020.pdfZweitveröffentlichung2.68 MBAdobe PDFThumbnail
View/Open