FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3123922547> ?p ?o ?g. }

• W3123922547 endingPage "274" @default.
• W3123922547 startingPage "274" @default.
• W3123922547 abstract "The available stereo matching algorithms produce large number of false positive matches or only produce a few true-positives across oblique stereo images with large baseline. This undesired result happens due to the complex perspective deformation and radiometric distortion across the images. To address this problem, we propose a novel affine invariant feature matching algorithm with subpixel accuracy based on an end-to-end convolutional neural network (CNN). In our method, we adopt and modify a Hessian affine network, which we refer to as IHesAffNet, to obtain affine invariant Hessian regions using deep learning framework. To improve the correlation between corresponding features, we introduce an empirical weighted loss function (EWLF) based on the negative samples using K nearest neighbors, and then generate deep learning-based descriptors with high discrimination that is realized with our multiple hard network structure (MTHardNets). Following this step, the conjugate features are produced by using the Euclidean distance ratio as the matching metric, and the accuracy of matches are optimized through the deep learning transform based least square matching (DLT-LSM). Finally, experiments on Large baseline oblique stereo images acquired by ground close-range and unmanned aerial vehicle (UAV) verify the effectiveness of the proposed approach, and comprehensive comparisons demonstrate that our matching algorithm outperforms the state-of-art methods in terms of accuracy, distribution and correct ratio. The main contributions of this article are: (i) our proposed MTHardNets can generate high quality descriptors; and (ii) the IHesAffNet can produce substantial affine invariant corresponding features with reliable transform parameters." @default.
• W3123922547 created "2021-02-01" @default.
• W3123922547 creator A5002755226 @default.
• W3123922547 creator A5004597724 @default.
• W3123922547 creator A5008672128 @default.
• W3123922547 creator A5032045601 @default.
• W3123922547 creator A5036873014 @default.
• W3123922547 creator A5066716873 @default.
• W3123922547 date "2021-01-14" @default.
• W3123922547 modified "2023-10-10" @default.
• W3123922547 title "Matching Large Baseline Oblique Stereo Images Using an End-to-End Convolutional Neural Network" @default.
• W3123922547 cites W1533955188 @default.
• W3123922547 cites W1929856797 @default.
• W3123922547 cites W1971661558 @default.
• W3123922547 cites W1980911747 @default.
• W3123922547 cites W2052094314 @default.
• W3123922547 cites W2098789800 @default.
• W3123922547 cites W2115072079 @default.
• W3123922547 cites W2119605622 @default.
• W3123922547 cites W2124404372 @default.
• W3123922547 cites W2126060993 @default.
• W3123922547 cites W2148179360 @default.
• W3123922547 cites W2151103935 @default.
• W3123922547 cites W2152235937 @default.
• W3123922547 cites W2172188317 @default.
• W3123922547 cites W2177274842 @default.
• W3123922547 cites W2263386426 @default.
• W3123922547 cites W2320444803 @default.
• W3123922547 cites W2345643369 @default.
• W3123922547 cites W2559871160 @default.
• W3123922547 cites W2737260104 @default.
• W3123922547 cites W2749224737 @default.
• W3123922547 cites W2884088147 @default.
• W3123922547 cites W2884354140 @default.
• W3123922547 cites W2898538166 @default.
• W3123922547 cites W2948182274 @default.
• W3123922547 cites W2950600620 @default.
• W3123922547 cites W2963059198 @default.
• W3123922547 cites W2963235042 @default.
• W3123922547 cites W2963775347 @default.
• W3123922547 cites W2965729937 @default.
• W3123922547 cites W2969574023 @default.
• W3123922547 cites W2973665503 @default.
• W3123922547 cites W2981799316 @default.
• W3123922547 cites W2989650831 @default.
• W3123922547 cites W3043075211 @default.
• W3123922547 cites W3092233714 @default.
• W3123922547 cites W3103648783 @default.
• W3123922547 doi "https://doi.org/10.3390/rs13020274" @default.
• W3123922547 hasPublicationYear "2021" @default.
• W3123922547 type Work @default.
• W3123922547 sameAs 3123922547 @default.
• W3123922547 citedByCount "8" @default.
• W3123922547 countsByYear W31239225472021 @default.
• W3123922547 countsByYear W31239225472022 @default.
• W3123922547 countsByYear W31239225472023 @default.
• W3123922547 crossrefType "journal-article" @default.
• W3123922547 hasAuthorship W3123922547A5002755226 @default.
• W3123922547 hasAuthorship W3123922547A5004597724 @default.
• W3123922547 hasAuthorship W3123922547A5008672128 @default.
• W3123922547 hasAuthorship W3123922547A5032045601 @default.
• W3123922547 hasAuthorship W3123922547A5036873014 @default.
• W3123922547 hasAuthorship W3123922547A5066716873 @default.
• W3123922547 hasBestOaLocation W31239225471 @default.
• W3123922547 hasConcept C105795698 @default.
• W3123922547 hasConcept C153180895 @default.
• W3123922547 hasConcept C154945302 @default.
• W3123922547 hasConcept C165064840 @default.
• W3123922547 hasConcept C2524010 @default.
• W3123922547 hasConcept C31972630 @default.
• W3123922547 hasConcept C33923547 @default.
• W3123922547 hasConcept C41008148 @default.
• W3123922547 hasConcept C81363708 @default.
• W3123922547 hasConcept C92757383 @default.
• W3123922547 hasConceptScore W3123922547C105795698 @default.
• W3123922547 hasConceptScore W3123922547C153180895 @default.
• W3123922547 hasConceptScore W3123922547C154945302 @default.
• W3123922547 hasConceptScore W3123922547C165064840 @default.
• W3123922547 hasConceptScore W3123922547C2524010 @default.
• W3123922547 hasConceptScore W3123922547C31972630 @default.
• W3123922547 hasConceptScore W3123922547C33923547 @default.
• W3123922547 hasConceptScore W3123922547C41008148 @default.
• W3123922547 hasConceptScore W3123922547C81363708 @default.
• W3123922547 hasConceptScore W3123922547C92757383 @default.
• W3123922547 hasFunder F4320321001 @default.
• W3123922547 hasIssue "2" @default.
• W3123922547 hasLocation W31239225471 @default.
• W3123922547 hasOpenAccess W3123922547 @default.
• W3123922547 hasPrimaryLocation W31239225471 @default.
• W3123922547 hasRelatedWork W2038416447 @default.
• W3123922547 hasRelatedWork W2364151838 @default.
• W3123922547 hasRelatedWork W2811106690 @default.
• W3123922547 hasRelatedWork W2936819511 @default.
• W3123922547 hasRelatedWork W2947043951 @default.
• W3123922547 hasRelatedWork W4239306820 @default.
• W3123922547 hasRelatedWork W4293226380 @default.
• W3123922547 hasRelatedWork W4313906399 @default.
• W3123922547 hasRelatedWork W4321444604 @default.

• next