Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898690910> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2898690910 abstract "Detection of buildings and other objects from aerial images has various applications in urban planning and map making. For human experts, manual extraction of objects from aerial imagery is a time-consuming and expensive task. However, aerial images are often prone to varying lighting conditions, shadows and occlusions.Aerial images also differ quite significantly from region to region. In order to offer both robust and reliable building detection, we use Convolutional Neural Networks (CNN) to account for these variations. We train detection from RGB-D images to obtain a segmented mask by employing the CNN architecture DenseNet. To improve the performance of the model, we apply the statistical re-sampling technique called Bootstrapping. Through Bootstrapping, we demonstrate that more informative examples are retained that improves the results. Finally, the proposed methodology outperforms the non-bootstrapped DenseNet by utilizing only one-sixth of the original training data and it obtains a precision-recall break-even point at 95.10% score on our aerial imagery dataset." @default.
- W2898690910 created "2018-11-09" @default.
- W2898690910 creator A5022348485 @default.
- W2898690910 creator A5026038554 @default.
- W2898690910 creator A5044355120 @default.
- W2898690910 date "2017-05-01" @default.
- W2898690910 modified "2023-09-27" @default.
- W2898690910 title "Bootstrapping CNNs for building segmentation in aerial imagery with depth" @default.
- W2898690910 hasPublicationYear "2017" @default.
- W2898690910 type Work @default.
- W2898690910 sameAs 2898690910 @default.
- W2898690910 citedByCount "0" @default.
- W2898690910 crossrefType "journal-article" @default.
- W2898690910 hasAuthorship W2898690910A5022348485 @default.
- W2898690910 hasAuthorship W2898690910A5026038554 @default.
- W2898690910 hasAuthorship W2898690910A5044355120 @default.
- W2898690910 hasConcept C108583219 @default.
- W2898690910 hasConcept C115961682 @default.
- W2898690910 hasConcept C127413603 @default.
- W2898690910 hasConcept C149782125 @default.
- W2898690910 hasConcept C153180895 @default.
- W2898690910 hasConcept C154945302 @default.
- W2898690910 hasConcept C201995342 @default.
- W2898690910 hasConcept C207609745 @default.
- W2898690910 hasConcept C2524010 @default.
- W2898690910 hasConcept C2776429412 @default.
- W2898690910 hasConcept C2780451532 @default.
- W2898690910 hasConcept C28719098 @default.
- W2898690910 hasConcept C2987819851 @default.
- W2898690910 hasConcept C31972630 @default.
- W2898690910 hasConcept C33923547 @default.
- W2898690910 hasConcept C41008148 @default.
- W2898690910 hasConcept C81363708 @default.
- W2898690910 hasConcept C82990744 @default.
- W2898690910 hasConcept C89600930 @default.
- W2898690910 hasConceptScore W2898690910C108583219 @default.
- W2898690910 hasConceptScore W2898690910C115961682 @default.
- W2898690910 hasConceptScore W2898690910C127413603 @default.
- W2898690910 hasConceptScore W2898690910C149782125 @default.
- W2898690910 hasConceptScore W2898690910C153180895 @default.
- W2898690910 hasConceptScore W2898690910C154945302 @default.
- W2898690910 hasConceptScore W2898690910C201995342 @default.
- W2898690910 hasConceptScore W2898690910C207609745 @default.
- W2898690910 hasConceptScore W2898690910C2524010 @default.
- W2898690910 hasConceptScore W2898690910C2776429412 @default.
- W2898690910 hasConceptScore W2898690910C2780451532 @default.
- W2898690910 hasConceptScore W2898690910C28719098 @default.
- W2898690910 hasConceptScore W2898690910C2987819851 @default.
- W2898690910 hasConceptScore W2898690910C31972630 @default.
- W2898690910 hasConceptScore W2898690910C33923547 @default.
- W2898690910 hasConceptScore W2898690910C41008148 @default.
- W2898690910 hasConceptScore W2898690910C81363708 @default.
- W2898690910 hasConceptScore W2898690910C82990744 @default.
- W2898690910 hasConceptScore W2898690910C89600930 @default.
- W2898690910 hasLocation W28986909101 @default.
- W2898690910 hasOpenAccess W2898690910 @default.
- W2898690910 hasPrimaryLocation W28986909101 @default.
- W2898690910 hasRelatedWork W1966108089 @default.
- W2898690910 hasRelatedWork W2241051737 @default.
- W2898690910 hasRelatedWork W2787757385 @default.
- W2898690910 hasRelatedWork W2793276759 @default.
- W2898690910 hasRelatedWork W2889700547 @default.
- W2898690910 hasRelatedWork W2894081147 @default.
- W2898690910 hasRelatedWork W2897981157 @default.
- W2898690910 hasRelatedWork W2908221889 @default.
- W2898690910 hasRelatedWork W2945887186 @default.
- W2898690910 hasRelatedWork W2948648905 @default.
- W2898690910 hasRelatedWork W2954896312 @default.
- W2898690910 hasRelatedWork W2971730281 @default.
- W2898690910 hasRelatedWork W2981007796 @default.
- W2898690910 hasRelatedWork W3048218390 @default.
- W2898690910 hasRelatedWork W3104252902 @default.
- W2898690910 hasRelatedWork W3124067401 @default.
- W2898690910 hasRelatedWork W3152515884 @default.
- W2898690910 hasRelatedWork W3174570424 @default.
- W2898690910 hasRelatedWork W3213616908 @default.
- W2898690910 hasRelatedWork W73112891 @default.
- W2898690910 isParatext "false" @default.
- W2898690910 isRetracted "false" @default.
- W2898690910 magId "2898690910" @default.
- W2898690910 workType "article" @default.