An analysis and speedup of the FALDOI method for Optical Flow estimation

Mostra el registre complet Registre parcial de l'ítem

  • dc.contributor.author Gamonal, Ferran P.
  • dc.contributor.author Ballester, Coloma
  • dc.contributor.author Haro Ortega, Gloria
  • dc.contributor.author Meinhardt Llopis, Enric
  • dc.contributor.author Palomares, Roberto P.
  • dc.date.accessioned 2019-04-10T18:15:53Z
  • dc.date.available 2019-04-10T18:15:53Z
  • dc.date.issued 2019
  • dc.description.abstract We present a detailed analysis of FALDOI, a large displacement optical flow method proposed by P. Palomares et al. This method requires a set of discrete matches, which can be extremely sparse, and an energy functional which locally guides the interpolation from the matches. It follows a two-step minimization method at the finest scale which is very robust to the outliers of the sparse matcher and can capture large displacements of small objects. The results shown in the original paper consistently outperformed the coarse-to-fine approaches and achieved good qualitative and quantitative performance on the standard optical flow benchmarks. In this paper we revise the proposed method and the changes done to significantly reduce its execution time while reporting nearly the same accuracy. Finally, we also compare it against the current state-of-the-art to assess its performance.en
  • dc.description.sponsorship The authors acknowledge support by TIN2015-70410-C2-1-R(MINECO/FEDER, UE) project and by H2020-MSCA-RISE-2017 project, reference 777826 NoMADS.
  • dc.format.mimetype application/pdf
  • dc.identifier.citation Gamonal FP, Ballester C, Haro G, Meinhardt-Llopis E, Palomares RP. An analysis and speedup of the FALDOI method for Optical Flow estimation. Image Processing On Line. 2019;9:94-123. DOI: 10.5201/ipol.2019.238
  • dc.identifier.doi http://dx.doi.org/10.5201/ipol.2019.238
  • dc.identifier.issn 2105–1232
  • dc.identifier.uri http://hdl.handle.net/10230/37086
  • dc.language.iso eng
  • dc.publisher Editor Image Processing On Line
  • dc.relation.ispartof Image Processing On Line. 2019;9:94-123.
  • dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/777826
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/1PE/TIN2015-70410-C2-1-R
  • dc.rights © 2019 IPOL & the authors CC–BY–NC–SA
  • dc.rights.accessRights info:eu-repo/semantics/openAccess
  • dc.rights.uri https://creativecommons.org/licenses/by-nc-sa/3.0/
  • dc.subject.keyword Optical flowen
  • dc.subject.keyword Variational methodsen
  • dc.subject.keyword Coordinate descent methodsen
  • dc.subject.keyword Sparse matchesen
  • dc.subject.keyword Parallelizationen
  • dc.title An analysis and speedup of the FALDOI method for Optical Flow estimation
  • dc.type info:eu-repo/semantics/article
  • dc.type.version info:eu-repo/semantics/publishedVersion