Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311725564> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4311725564 abstract "Abstract We devise a novel Lightweight Image Matching Architecture (LIMA), which is designed and optimized for Particle Image Velocimetry (PIV). LIMA is a convolutional neural network (CNN) that performs symmetric image matching and employs an iterative residual refinement strategy, which allows us to optimize the total number of refinement steps to balance accuracy and computational efficiency. The network is trained on kinematic datasets with a loss function that penalizes larger gradients. We consider a six- (LIMA-6) and a four-level (LIMA-4) version of the network and demonstrate that they are considerably leaner and faster than a state-of-the-art network designed for optical flow (PWCIRR). LIMA-6 reconstructs the velocity field from synthetic and experimental PIV images with an accuracy comparable or superior both to PWCIRR as well as to state-of-the-art cross-correlation methods (i.e., a commercial implementation of WIDIM). Although less accurate, LIMA-4 allows a significant reduction of the computational costs with respect to any other method considered. All CNNs prove more robust than WIDIM with respect to particle loss and allow effective error reduction by increasing the particle seeding density. Thanks to reduced computational cost and memory requirement, we envision the deployment of LIMA on low-cost devices to provide affordable, real-time inference of the flow field during PIV measurements." @default.
- W4311725564 created "2022-12-28" @default.
- W4311725564 creator A5058591095 @default.
- W4311725564 creator A5072372061 @default.
- W4311725564 creator A5078880549 @default.
- W4311725564 date "2022-12-16" @default.
- W4311725564 modified "2023-10-18" @default.
- W4311725564 title "A lightweight neural network designed for fluid velocimetry" @default.
- W4311725564 doi "https://doi.org/10.21203/rs.3.rs-2360944/v1" @default.
- W4311725564 hasPublicationYear "2022" @default.
- W4311725564 type Work @default.
- W4311725564 citedByCount "1" @default.
- W4311725564 countsByYear W43117255642023 @default.
- W4311725564 crossrefType "posted-content" @default.
- W4311725564 hasAuthorship W4311725564A5058591095 @default.
- W4311725564 hasAuthorship W4311725564A5072372061 @default.
- W4311725564 hasAuthorship W4311725564A5078880549 @default.
- W4311725564 hasBestOaLocation W43117255641 @default.
- W4311725564 hasConcept C105795698 @default.
- W4311725564 hasConcept C111335779 @default.
- W4311725564 hasConcept C113775141 @default.
- W4311725564 hasConcept C11413529 @default.
- W4311725564 hasConcept C115961682 @default.
- W4311725564 hasConcept C121332964 @default.
- W4311725564 hasConcept C154945302 @default.
- W4311725564 hasConcept C155512373 @default.
- W4311725564 hasConcept C155542232 @default.
- W4311725564 hasConcept C165064840 @default.
- W4311725564 hasConcept C196558001 @default.
- W4311725564 hasConcept C207857233 @default.
- W4311725564 hasConcept C2524010 @default.
- W4311725564 hasConcept C33923547 @default.
- W4311725564 hasConcept C41008148 @default.
- W4311725564 hasConcept C45347329 @default.
- W4311725564 hasConcept C50644808 @default.
- W4311725564 hasConcept C81363708 @default.
- W4311725564 hasConcept C97355855 @default.
- W4311725564 hasConceptScore W4311725564C105795698 @default.
- W4311725564 hasConceptScore W4311725564C111335779 @default.
- W4311725564 hasConceptScore W4311725564C113775141 @default.
- W4311725564 hasConceptScore W4311725564C11413529 @default.
- W4311725564 hasConceptScore W4311725564C115961682 @default.
- W4311725564 hasConceptScore W4311725564C121332964 @default.
- W4311725564 hasConceptScore W4311725564C154945302 @default.
- W4311725564 hasConceptScore W4311725564C155512373 @default.
- W4311725564 hasConceptScore W4311725564C155542232 @default.
- W4311725564 hasConceptScore W4311725564C165064840 @default.
- W4311725564 hasConceptScore W4311725564C196558001 @default.
- W4311725564 hasConceptScore W4311725564C207857233 @default.
- W4311725564 hasConceptScore W4311725564C2524010 @default.
- W4311725564 hasConceptScore W4311725564C33923547 @default.
- W4311725564 hasConceptScore W4311725564C41008148 @default.
- W4311725564 hasConceptScore W4311725564C45347329 @default.
- W4311725564 hasConceptScore W4311725564C50644808 @default.
- W4311725564 hasConceptScore W4311725564C81363708 @default.
- W4311725564 hasConceptScore W4311725564C97355855 @default.
- W4311725564 hasLocation W43117255641 @default.
- W4311725564 hasOpenAccess W4311725564 @default.
- W4311725564 hasPrimaryLocation W43117255641 @default.
- W4311725564 hasRelatedWork W2610482638 @default.
- W4311725564 hasRelatedWork W2755240195 @default.
- W4311725564 hasRelatedWork W2766634277 @default.
- W4311725564 hasRelatedWork W2896066979 @default.
- W4311725564 hasRelatedWork W2939136205 @default.
- W4311725564 hasRelatedWork W2961623865 @default.
- W4311725564 hasRelatedWork W3159196814 @default.
- W4311725564 hasRelatedWork W3160916081 @default.
- W4311725564 hasRelatedWork W3206466808 @default.
- W4311725564 hasRelatedWork W4312417841 @default.
- W4311725564 isParatext "false" @default.
- W4311725564 isRetracted "false" @default.
- W4311725564 workType "article" @default.