FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201495010> ?p ?o ?g. }

• W3201495010 endingPage "6061" @default.
• W3201495010 startingPage "6061" @default.
• W3201495010 abstract "Depth estimation based on light field imaging is a new methodology that has succeeded the traditional binocular stereo matching and depth from monocular images. Significant progress has been made in light-field depth estimation. Nevertheless, the balance between computational time and the accuracy of depth estimation is still worth exploring. The geometry in light field imaging is the basis of depth estimation, and the abundant light-field data provides convenience for applying deep learning algorithms. The Epipolar Plane Image (EPI) generated from the light-field data has a line texture containing geometric information. The slope of the line is proportional to the depth of the corresponding object. Considering the light field depth estimation as a spatial density prediction task, we design a convolutional neural network (ESTNet) to estimate the accurate depth quickly. Inspired by the strong image feature extraction ability of convolutional neural networks, especially for texture images, we propose to generate EPI synthetic images from light field data as the input of ESTNet to improve the effect of feature extraction and depth estimation. The architecture of ESTNet is characterized by three input streams, encoding-decoding structure, and skipconnections. The three input streams receive horizontal EPI synthetic image (EPIh), vertical EPI synthetic image (EPIv), and central view image (CV), respectively. EPIh and EPIv contain rich texture and depth cues, while CV provides pixel position association information. ESTNet consists of two stages: encoding and decoding. The encoding stage includes several convolution modules, and correspondingly, the decoding stage embodies some transposed convolution modules. In addition to the forward propagation of the network ESTNet, some skip-connections are added between the convolution module and the corresponding transposed convolution module to fuse the shallow local and deep semantic features. ESTNet is trained on one part of a synthetic light-field dataset and then tested on another part of the synthetic light-field dataset and real light-field dataset. Ablation experiments show that our ESTNet structure is reasonable. Experiments on the synthetic light-field dataset and real light-field dataset show that our ESTNet can balance the accuracy of depth estimation and computational time." @default.
• W3201495010 created "2021-09-27" @default.
• W3201495010 creator A5024881268 @default.
• W3201495010 creator A5028800902 @default.
• W3201495010 creator A5083815471 @default.
• W3201495010 creator A5086314063 @default.
• W3201495010 date "2021-09-10" @default.
• W3201495010 modified "2023-09-26" @default.
• W3201495010 title "Depth Estimation from Light Field Geometry Using Convolutional Neural Networks" @default.
• W3201495010 cites W1540131840 @default.
• W3201495010 cites W1803059841 @default.
• W3201495010 cites W2007165614 @default.
• W3201495010 cites W2057495213 @default.
• W3201495010 cites W2607448793 @default.
• W3201495010 cites W2782651872 @default.
• W3201495010 cites W2808349714 @default.
• W3201495010 cites W2809808960 @default.
• W3201495010 cites W2894317039 @default.
• W3201495010 cites W2935161635 @default.
• W3201495010 cites W2976735205 @default.
• W3201495010 cites W4210527669 @default.
• W3201495010 doi "https://doi.org/10.3390/s21186061" @default.
• W3201495010 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8471881" @default.
• W3201495010 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34577268" @default.
• W3201495010 hasPublicationYear "2021" @default.
• W3201495010 type Work @default.
• W3201495010 sameAs 3201495010 @default.
• W3201495010 citedByCount "3" @default.
• W3201495010 countsByYear W32014950102021 @default.
• W3201495010 countsByYear W32014950102022 @default.
• W3201495010 crossrefType "journal-article" @default.
• W3201495010 hasAuthorship W3201495010A5024881268 @default.
• W3201495010 hasAuthorship W3201495010A5028800902 @default.
• W3201495010 hasAuthorship W3201495010A5083815471 @default.
• W3201495010 hasAuthorship W3201495010A5086314063 @default.
• W3201495010 hasBestOaLocation W32014950101 @default.
• W3201495010 hasConcept C11413529 @default.
• W3201495010 hasConcept C115961682 @default.
• W3201495010 hasConcept C138885662 @default.
• W3201495010 hasConcept C153180895 @default.
• W3201495010 hasConcept C154945302 @default.
• W3201495010 hasConcept C160633673 @default.
• W3201495010 hasConcept C23379248 @default.
• W3201495010 hasConcept C2776401178 @default.
• W3201495010 hasConcept C31972630 @default.
• W3201495010 hasConcept C41008148 @default.
• W3201495010 hasConcept C41895202 @default.
• W3201495010 hasConcept C45347329 @default.
• W3201495010 hasConcept C48983235 @default.
• W3201495010 hasConcept C50644808 @default.
• W3201495010 hasConcept C52622490 @default.
• W3201495010 hasConcept C57273362 @default.
• W3201495010 hasConcept C81363708 @default.
• W3201495010 hasConceptScore W3201495010C11413529 @default.
• W3201495010 hasConceptScore W3201495010C115961682 @default.
• W3201495010 hasConceptScore W3201495010C138885662 @default.
• W3201495010 hasConceptScore W3201495010C153180895 @default.
• W3201495010 hasConceptScore W3201495010C154945302 @default.
• W3201495010 hasConceptScore W3201495010C160633673 @default.
• W3201495010 hasConceptScore W3201495010C23379248 @default.
• W3201495010 hasConceptScore W3201495010C2776401178 @default.
• W3201495010 hasConceptScore W3201495010C31972630 @default.
• W3201495010 hasConceptScore W3201495010C41008148 @default.
• W3201495010 hasConceptScore W3201495010C41895202 @default.
• W3201495010 hasConceptScore W3201495010C45347329 @default.
• W3201495010 hasConceptScore W3201495010C48983235 @default.
• W3201495010 hasConceptScore W3201495010C50644808 @default.
• W3201495010 hasConceptScore W3201495010C52622490 @default.
• W3201495010 hasConceptScore W3201495010C57273362 @default.
• W3201495010 hasConceptScore W3201495010C81363708 @default.
• W3201495010 hasFunder F4320321001 @default.
• W3201495010 hasIssue "18" @default.
• W3201495010 hasLocation W32014950101 @default.
• W3201495010 hasLocation W32014950102 @default.
• W3201495010 hasLocation W32014950103 @default.
• W3201495010 hasLocation W32014950104 @default.
• W3201495010 hasOpenAccess W3201495010 @default.
• W3201495010 hasPrimaryLocation W32014950101 @default.
• W3201495010 hasRelatedWork W1841847813 @default.
• W3201495010 hasRelatedWork W2059299633 @default.
• W3201495010 hasRelatedWork W2090093270 @default.
• W3201495010 hasRelatedWork W2197810677 @default.
• W3201495010 hasRelatedWork W2732542196 @default.
• W3201495010 hasRelatedWork W2760085659 @default.
• W3201495010 hasRelatedWork W2897307500 @default.
• W3201495010 hasRelatedWork W2940977206 @default.
• W3201495010 hasRelatedWork W2107154006 @default.
• W3201495010 hasRelatedWork W2113283186 @default.
• W3201495010 hasVolume "21" @default.
• W3201495010 isParatext "false" @default.
• W3201495010 isRetracted "false" @default.
• W3201495010 magId "3201495010" @default.
• W3201495010 workType "article" @default.