Matches in SemOpenAlex for { <https://semopenalex.org/work/W2979667069> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2979667069 abstract "Automatic building segmentation from remote sensing images is critical in the remote sensing image semantic segmentation. The success of deep neural networks has led to advances in using fully convolutional neural networks (FCN) to extract buildings from the high-resolution image. However, the downsampling processing inevitably leads to loss of details of the segmentation results. To solve this problem, some methods try to refine the results of FCN by using probability graph models such as fully connected CRF (Conditional Random Fields). Nevertheless, many fully connected CRF based methods are too time-consuming and not suitable for building segmentation tasks in some situations. In this paper, we propose a novel time-efficient end-to-end CRF model with the domain transform algorithm called DT-CRF. In the proposed model, in order to accelerate the message passing in the mean-field approximate inference algorithm, we take the edge maps as the joint image for DT-CRF and use the domain transformation algorithm to calculate the pair-wise potential instead of the Gaussian kernel function. Meanwhile, we design a multi-task network which can generate masks and edges simultaneously, and the network can make the DT-CRF to easily optimize the segmentation results using model information. The evaluation of remote sensing image datasets verifies the time and space efficiency of the proposed DTCRF and demonstrates a distinct improvement." @default.
- W2979667069 created "2019-10-18" @default.
- W2979667069 creator A5005741067 @default.
- W2979667069 creator A5046402362 @default.
- W2979667069 creator A5064849217 @default.
- W2979667069 creator A5089132290 @default.
- W2979667069 date "2019-10-11" @default.
- W2979667069 modified "2023-10-16" @default.
- W2979667069 title "Building segmentation of remote sensing images using deep neural networks and domain transform CRF" @default.
- W2979667069 cites W1903029394 @default.
- W2979667069 cites W2124592697 @default.
- W2979667069 cites W2412782625 @default.
- W2979667069 cites W2609402060 @default.
- W2979667069 cites W2623490820 @default.
- W2979667069 cites W2787614951 @default.
- W2979667069 cites W2790741584 @default.
- W2979667069 cites W2795635230 @default.
- W2979667069 cites W2885628263 @default.
- W2979667069 cites W2888889084 @default.
- W2979667069 cites W2890072312 @default.
- W2979667069 cites W2900629394 @default.
- W2979667069 cites W2906217354 @default.
- W2979667069 cites W2908320224 @default.
- W2979667069 cites W2915731581 @default.
- W2979667069 cites W2963995737 @default.
- W2979667069 cites W4238603956 @default.
- W2979667069 cites W4226512252 @default.
- W2979667069 doi "https://doi.org/10.1117/12.2532662" @default.
- W2979667069 hasPublicationYear "2019" @default.
- W2979667069 type Work @default.
- W2979667069 sameAs 2979667069 @default.
- W2979667069 citedByCount "1" @default.
- W2979667069 countsByYear W29796670692022 @default.
- W2979667069 crossrefType "proceedings-article" @default.
- W2979667069 hasAuthorship W2979667069A5005741067 @default.
- W2979667069 hasAuthorship W2979667069A5046402362 @default.
- W2979667069 hasAuthorship W2979667069A5064849217 @default.
- W2979667069 hasAuthorship W2979667069A5089132290 @default.
- W2979667069 hasConcept C108583219 @default.
- W2979667069 hasConcept C110384440 @default.
- W2979667069 hasConcept C114614502 @default.
- W2979667069 hasConcept C115961682 @default.
- W2979667069 hasConcept C124504099 @default.
- W2979667069 hasConcept C152565575 @default.
- W2979667069 hasConcept C153180895 @default.
- W2979667069 hasConcept C154945302 @default.
- W2979667069 hasConcept C31972630 @default.
- W2979667069 hasConcept C33923547 @default.
- W2979667069 hasConcept C41008148 @default.
- W2979667069 hasConcept C50644808 @default.
- W2979667069 hasConcept C65885262 @default.
- W2979667069 hasConcept C74193536 @default.
- W2979667069 hasConcept C81363708 @default.
- W2979667069 hasConcept C89600930 @default.
- W2979667069 hasConceptScore W2979667069C108583219 @default.
- W2979667069 hasConceptScore W2979667069C110384440 @default.
- W2979667069 hasConceptScore W2979667069C114614502 @default.
- W2979667069 hasConceptScore W2979667069C115961682 @default.
- W2979667069 hasConceptScore W2979667069C124504099 @default.
- W2979667069 hasConceptScore W2979667069C152565575 @default.
- W2979667069 hasConceptScore W2979667069C153180895 @default.
- W2979667069 hasConceptScore W2979667069C154945302 @default.
- W2979667069 hasConceptScore W2979667069C31972630 @default.
- W2979667069 hasConceptScore W2979667069C33923547 @default.
- W2979667069 hasConceptScore W2979667069C41008148 @default.
- W2979667069 hasConceptScore W2979667069C50644808 @default.
- W2979667069 hasConceptScore W2979667069C65885262 @default.
- W2979667069 hasConceptScore W2979667069C74193536 @default.
- W2979667069 hasConceptScore W2979667069C81363708 @default.
- W2979667069 hasConceptScore W2979667069C89600930 @default.
- W2979667069 hasLocation W29796670691 @default.
- W2979667069 hasOpenAccess W2979667069 @default.
- W2979667069 hasPrimaryLocation W29796670691 @default.
- W2979667069 hasRelatedWork W10828093 @default.
- W2979667069 hasRelatedWork W11130107 @default.
- W2979667069 hasRelatedWork W12703013 @default.
- W2979667069 hasRelatedWork W14128562 @default.
- W2979667069 hasRelatedWork W2233117 @default.
- W2979667069 hasRelatedWork W2366400 @default.
- W2979667069 hasRelatedWork W274842 @default.
- W2979667069 hasRelatedWork W2777938 @default.
- W2979667069 hasRelatedWork W4608154 @default.
- W2979667069 hasRelatedWork W9828492 @default.
- W2979667069 isParatext "false" @default.
- W2979667069 isRetracted "false" @default.
- W2979667069 magId "2979667069" @default.
- W2979667069 workType "article" @default.