Matches in SemOpenAlex for { <https://semopenalex.org/work/W1966642287> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W1966642287 abstract "This paper describes a novel learning-based approach for improving the performance of stereo computation. It is based on the observation that whether the image matching scores lead to true or erroneous depth values is dependent on the original stereo images and the underlying scene structure. This function is learned from training data and is integrated into a depth estimation algorithm using the MAP-MRF framework. Because the resultant likelihood function is dependent on the states of a large neighboring region around each pixel, we propose to solve the high-order MRF inference problem using the simulated annealing algorithm combined with a Metropolis-Hastings sampler. A segmentation-based approach is proposed to accelerate the computational speed and improve the performance. Preliminary experimental results show that the learning process captures common errors in SSD matching including the fattening effect, the aperture effect, and mismatches in occluded or low texture regions. It is also demonstrated that the proposed approach significantly improves the accuracy of the depth computation." @default.
- W1966642287 created "2016-06-24" @default.
- W1966642287 creator A5046193794 @default.
- W1966642287 creator A5062509638 @default.
- W1966642287 date "2004-01-01" @default.
- W1966642287 modified "2023-09-25" @default.
- W1966642287 title "A method for learning matching errors for stereo computation" @default.
- W1966642287 cites W1651266332 @default.
- W1966642287 cites W1986557010 @default.
- W1966642287 cites W1995756857 @default.
- W1966642287 cites W2050405342 @default.
- W1966642287 cites W2054536235 @default.
- W1966642287 cites W2056760934 @default.
- W1966642287 cites W2063266501 @default.
- W1966642287 cites W2101309634 @default.
- W1966642287 cites W2104974755 @default.
- W1966642287 cites W2105192278 @default.
- W1966642287 cites W2106110775 @default.
- W1966642287 cites W2106196892 @default.
- W1966642287 cites W2138309709 @default.
- W1966642287 cites W2143402564 @default.
- W1966642287 cites W2148852318 @default.
- W1966642287 cites W2160032362 @default.
- W1966642287 cites W2164117311 @default.
- W1966642287 cites W2167077256 @default.
- W1966642287 cites W2180905035 @default.
- W1966642287 cites W2561377267 @default.
- W1966642287 doi "https://doi.org/10.5244/c.18.11" @default.
- W1966642287 hasPublicationYear "2004" @default.
- W1966642287 type Work @default.
- W1966642287 sameAs 1966642287 @default.
- W1966642287 citedByCount "48" @default.
- W1966642287 countsByYear W19666422872012 @default.
- W1966642287 countsByYear W19666422872014 @default.
- W1966642287 countsByYear W19666422872015 @default.
- W1966642287 countsByYear W19666422872016 @default.
- W1966642287 countsByYear W19666422872017 @default.
- W1966642287 countsByYear W19666422872018 @default.
- W1966642287 countsByYear W19666422872019 @default.
- W1966642287 countsByYear W19666422872020 @default.
- W1966642287 countsByYear W19666422872021 @default.
- W1966642287 countsByYear W19666422872022 @default.
- W1966642287 countsByYear W19666422872023 @default.
- W1966642287 crossrefType "proceedings-article" @default.
- W1966642287 hasAuthorship W1966642287A5046193794 @default.
- W1966642287 hasAuthorship W1966642287A5062509638 @default.
- W1966642287 hasConcept C105795698 @default.
- W1966642287 hasConcept C11413529 @default.
- W1966642287 hasConcept C154945302 @default.
- W1966642287 hasConcept C165064840 @default.
- W1966642287 hasConcept C31972630 @default.
- W1966642287 hasConcept C33923547 @default.
- W1966642287 hasConcept C41008148 @default.
- W1966642287 hasConcept C45374587 @default.
- W1966642287 hasConceptScore W1966642287C105795698 @default.
- W1966642287 hasConceptScore W1966642287C11413529 @default.
- W1966642287 hasConceptScore W1966642287C154945302 @default.
- W1966642287 hasConceptScore W1966642287C165064840 @default.
- W1966642287 hasConceptScore W1966642287C31972630 @default.
- W1966642287 hasConceptScore W1966642287C33923547 @default.
- W1966642287 hasConceptScore W1966642287C41008148 @default.
- W1966642287 hasConceptScore W1966642287C45374587 @default.
- W1966642287 hasLocation W19666422871 @default.
- W1966642287 hasOpenAccess W1966642287 @default.
- W1966642287 hasPrimaryLocation W19666422871 @default.
- W1966642287 hasRelatedWork W1891287906 @default.
- W1966642287 hasRelatedWork W1969923398 @default.
- W1966642287 hasRelatedWork W1995188412 @default.
- W1966642287 hasRelatedWork W2036807459 @default.
- W1966642287 hasRelatedWork W2166024367 @default.
- W1966642287 hasRelatedWork W2391245565 @default.
- W1966642287 hasRelatedWork W2755342338 @default.
- W1966642287 hasRelatedWork W2772917594 @default.
- W1966642287 hasRelatedWork W2775347418 @default.
- W1966642287 hasRelatedWork W2786306966 @default.
- W1966642287 isParatext "false" @default.
- W1966642287 isRetracted "false" @default.
- W1966642287 magId "1966642287" @default.
- W1966642287 workType "article" @default.