FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362587308> ?p ?o ?g. }

• W4362587308 endingPage "1365" @default.
• W4362587308 startingPage "1365" @default.
• W4362587308 abstract "Flow motion with complex patterns, such as vortex, stagnant flow, and seepage, put forward higher spatial resolution requirements for particle image velocimetry (PIV). With the development of deep learning technology in optical flow estimation, many attempts have been made to introduce deep learning-based optical flow (DLOF) into PIV. Compared with the traditional optical flow method, the DLOF method has the advantages of higher precision, faster calculation speed, and avoiding manual parameter adjustment. However, DLOF research is generally developed based on the basic characteristics of rigid body motion, and its key loss function part still generally uses the L1 (mean absolute error, MAE, L1) or L2 (mean square error, MSE, L2) loss functions, which lack consideration of fluid motion characteristics. Therefore, the current DLOF research has the problems of large angular error and serious curl-divergence loss in fluid motion estimation scenarios with smaller spatial scales than rigid bodies. Based on the prior knowledge of the traditional fluid motion characteristics, this study proposes a fluid loss function for describing the fluid motion characteristics, and combines this loss function with Flownet2. The compound loss (CL) function is combined with the displacement error, angular error, and div-curl smooth loss. The method combined with the loss function in this paper is called FlowNet2-CL-PIV. In order to verify that the compound loss function proposed in this study has a positive impact on the model training results, this paper uses the cosine similarity measure to demonstrate its effectiveness. In addition, the parameter selection of the compound loss function is analyzed and compared, and it is verified that the best training effect can be achieved by adjusting the parameter so that the order of magnitude of each part of the compound loss function is consistent. In order to test the calculation effect of the Flownet2-CL-PIV method proposed in this study, synthetic particle images are used for model training and performance analysis. Simulation results in various flow fields show that the root mean square error (RMSE) and average angular error (AAE) of Flownet2-CL-PIV reach 0.182 pixels and 1.7°, which are 10% and 54% higher than the original model, respectively." @default.
• W4362587308 created "2023-04-06" @default.
• W4362587308 creator A5032327375 @default.
• W4362587308 creator A5038899867 @default.
• W4362587308 creator A5078143614 @default.
• W4362587308 creator A5085236573 @default.
• W4362587308 date "2023-04-01" @default.
• W4362587308 modified "2023-10-03" @default.
• W4362587308 title "Deep Learning Optical Flow with Compound Loss for Dense Fluid Motion Estimation" @default.
• W4362587308 cites W1578285471 @default.
• W4362587308 cites W1964443992 @default.
• W4362587308 cites W2005067064 @default.
• W4362587308 cites W2116082861 @default.
• W4362587308 cites W2147253850 @default.
• W4362587308 cites W2560474170 @default.
• W4362587308 cites W2742175846 @default.
• W4362587308 cites W2770660451 @default.
• W4362587308 cites W2900732181 @default.
• W4362587308 cites W2904718222 @default.
• W4362587308 cites W2917818392 @default.
• W4362587308 cites W2963782415 @default.
• W4362587308 cites W2964156315 @default.
• W4362587308 cites W2967686751 @default.
• W4362587308 cites W3049103587 @default.
• W4362587308 cites W3177813886 @default.
• W4362587308 cites W3187838476 @default.
• W4362587308 cites W4225014337 @default.
• W4362587308 cites W4235494105 @default.
• W4362587308 cites W764651262 @default.
• W4362587308 doi "https://doi.org/10.3390/w15071365" @default.
• W4362587308 hasPublicationYear "2023" @default.
• W4362587308 type Work @default.
• W4362587308 citedByCount "0" @default.
• W4362587308 crossrefType "journal-article" @default.
• W4362587308 hasAuthorship W4362587308A5032327375 @default.
• W4362587308 hasAuthorship W4362587308A5038899867 @default.
• W4362587308 hasAuthorship W4362587308A5078143614 @default.
• W4362587308 hasAuthorship W4362587308A5085236573 @default.
• W4362587308 hasBestOaLocation W43625873081 @default.
• W4362587308 hasConcept C10161872 @default.
• W4362587308 hasConcept C105795698 @default.
• W4362587308 hasConcept C107551265 @default.
• W4362587308 hasConcept C11413529 @default.
• W4362587308 hasConcept C115961682 @default.
• W4362587308 hasConcept C121332964 @default.
• W4362587308 hasConcept C139945424 @default.
• W4362587308 hasConcept C147663694 @default.
• W4362587308 hasConcept C154945302 @default.
• W4362587308 hasConcept C155542232 @default.
• W4362587308 hasConcept C15744967 @default.
• W4362587308 hasConcept C196558001 @default.
• W4362587308 hasConcept C199360897 @default.
• W4362587308 hasConcept C207857233 @default.
• W4362587308 hasConcept C33923547 @default.
• W4362587308 hasConcept C41008148 @default.
• W4362587308 hasConcept C542102704 @default.
• W4362587308 hasConcept C57879066 @default.
• W4362587308 hasConcept C90278072 @default.
• W4362587308 hasConceptScore W4362587308C10161872 @default.
• W4362587308 hasConceptScore W4362587308C105795698 @default.
• W4362587308 hasConceptScore W4362587308C107551265 @default.
• W4362587308 hasConceptScore W4362587308C11413529 @default.
• W4362587308 hasConceptScore W4362587308C115961682 @default.
• W4362587308 hasConceptScore W4362587308C121332964 @default.
• W4362587308 hasConceptScore W4362587308C139945424 @default.
• W4362587308 hasConceptScore W4362587308C147663694 @default.
• W4362587308 hasConceptScore W4362587308C154945302 @default.
• W4362587308 hasConceptScore W4362587308C155542232 @default.
• W4362587308 hasConceptScore W4362587308C15744967 @default.
• W4362587308 hasConceptScore W4362587308C196558001 @default.
• W4362587308 hasConceptScore W4362587308C199360897 @default.
• W4362587308 hasConceptScore W4362587308C207857233 @default.
• W4362587308 hasConceptScore W4362587308C33923547 @default.
• W4362587308 hasConceptScore W4362587308C41008148 @default.
• W4362587308 hasConceptScore W4362587308C542102704 @default.
• W4362587308 hasConceptScore W4362587308C57879066 @default.
• W4362587308 hasConceptScore W4362587308C90278072 @default.
• W4362587308 hasIssue "7" @default.
• W4362587308 hasLocation W43625873081 @default.
• W4362587308 hasOpenAccess W4362587308 @default.
• W4362587308 hasPrimaryLocation W43625873081 @default.
• W4362587308 hasRelatedWork W2105101328 @default.
• W4362587308 hasRelatedWork W2108168258 @default.
• W4362587308 hasRelatedWork W2112456472 @default.
• W4362587308 hasRelatedWork W2123374136 @default.
• W4362587308 hasRelatedWork W2154099615 @default.
• W4362587308 hasRelatedWork W2347220252 @default.
• W4362587308 hasRelatedWork W2352338927 @default.
• W4362587308 hasRelatedWork W2798573714 @default.
• W4362587308 hasRelatedWork W4281553171 @default.
• W4362587308 hasRelatedWork W4362587308 @default.
• W4362587308 hasVolume "15" @default.
• W4362587308 isParatext "false" @default.
• W4362587308 isRetracted "false" @default.
• W4362587308 workType "article" @default.