<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "Novel learning-based techniques for dense fluid motion measurements"^^ . "In this thesis novel learning-based approaches are presented for the estimation of\r\ndense fluid flow velocity fields from particle image sequences. The developed methods apply\r\nprior knowledge in form of typical spatio-temporal motion models. These motion models are\r\nobtained with methods of unsupervised learning using proper orthogonal decomposition (POD).\r\nThe POD modes reveal dominant flow structures and contain relevant information of complex\r\nrelations between neighboring flow vectors. The first high-energy POD modes obtained from\r\nappropriate training vector fields are used as typical motion models. Meaningful local flow\r\nstructures can be expressed in the orthogonal space spanned by the motion models. Additional\r\ninformation about dominant flow events is gained by the motion models and related parameters.\r\nThe proposed approaches are embedded in well-established local parametric and variational\r\noptical flow frameworks but are contrasted with these common techniques by the inclusion of\r\nprior knowledge. Further extensions of the methods use available information, which is generally\r\ndiscarded in other methods, to obtain robust motion estimations. The methods can easily\r\nbe tuned for different flow applications by choice of training data and, thus, are universally\r\napplicable. Beyond their simple implementation, the approaches are very efficient, accurate and\r\neasily adaptable to all types of flow situations. All methods were tested on synthetic and real\r\nparticle image sequences and the influence of the relevant parameters was investigated. For\r\ntypical use cases of optical flow, such as small image displacements, they were more accurate\r\ncompared to all competing methods including particle image velocimetry (PIV) and common\r\noptical flow techniques."^^ . "2015" . . . . . . . "Julian"^^ . "Stapf"^^ . "Julian Stapf"^^ . . . . . . "Novel learning-based techniques for dense fluid motion measurements (PDF)"^^ . . . "Julian_Stapf_Diss.pdf"^^ . . . "Novel learning-based techniques for dense fluid motion measurements (Other)"^^ . . . . . . "indexcodes.txt"^^ . . . "Novel learning-based techniques for dense fluid motion measurements (Other)"^^ . . . . . . "lightbox.jpg"^^ . . . "Novel learning-based techniques for dense fluid motion measurements (Other)"^^ . . . . . . "preview.jpg"^^ . . . "Novel learning-based techniques for dense fluid motion measurements (Other)"^^ . . . . . . "medium.jpg"^^ . . . "Novel learning-based techniques for dense fluid motion measurements (Other)"^^ . . . . . . "small.jpg"^^ . . "HTML Summary of #18116 \n\nNovel learning-based techniques for dense fluid motion measurements\n\n" . "text/html" . .