Matches in SemOpenAlex for { <https://semopenalex.org/work/W2777524605> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2777524605 abstract "We introduce a method to classify imagery using a convo- lutional neural network (CNN) on multi-view image pro- jections. The power of our method comes from using pro- jections of multiple images at multiple depth planes near the reconstructed surface. This enables classification of categories whose salient aspect is appearance change un- der different viewpoints, such as water, trees, and other materials with complex reflection/light response proper- ties. Our method does not require boundary labelling in images and works on pixel-level classification with a small (few pixels) context, which simplifies the cre- ation of a training set. We demonstrate this application on large-scale aerial imagery collections, and extend the per-pixel classification to robustly create a consistent 2D classification which can be used to fill the gaps in non- reconstructible water regions. We also apply our method to classify tree regions. In both cases, the training data can quickly be generated using a small number of manually- created polygons on a map. We show that even with a very simple and standard network our CNN outperforms the state-of-the-art image classification, the Inception-V3 model retrained from a large collection of aerial images." @default.
- W2777524605 created "2018-01-05" @default.
- W2777524605 creator A5057431334 @default.
- W2777524605 creator A5083406288 @default.
- W2777524605 creator A5088483236 @default.
- W2777524605 date "2017-12-26" @default.
- W2777524605 modified "2023-09-27" @default.
- W2777524605 title "Large-Scale 3D Scene Classification With Multi-View Volumetric CNN" @default.
- W2777524605 cites W1677182931 @default.
- W2777524605 cites W1686810756 @default.
- W2777524605 cites W1783315696 @default.
- W2777524605 cites W1931270512 @default.
- W2777524605 cites W1980287119 @default.
- W2777524605 cites W2095705004 @default.
- W2777524605 cites W2097117768 @default.
- W2777524605 cites W2112796928 @default.
- W2777524605 cites W2150134683 @default.
- W2777524605 cites W2160014001 @default.
- W2777524605 cites W2169374938 @default.
- W2777524605 cites W2949605076 @default.
- W2777524605 cites W2952632681 @default.
- W2777524605 cites W611457968 @default.
- W2777524605 hasPublicationYear "2017" @default.
- W2777524605 type Work @default.
- W2777524605 sameAs 2777524605 @default.
- W2777524605 citedByCount "0" @default.
- W2777524605 crossrefType "posted-content" @default.
- W2777524605 hasAuthorship W2777524605A5057431334 @default.
- W2777524605 hasAuthorship W2777524605A5083406288 @default.
- W2777524605 hasAuthorship W2777524605A5088483236 @default.
- W2777524605 hasConcept C115961682 @default.
- W2777524605 hasConcept C134306372 @default.
- W2777524605 hasConcept C153180895 @default.
- W2777524605 hasConcept C154945302 @default.
- W2777524605 hasConcept C160633673 @default.
- W2777524605 hasConcept C166957645 @default.
- W2777524605 hasConcept C177264268 @default.
- W2777524605 hasConcept C199360897 @default.
- W2777524605 hasConcept C205649164 @default.
- W2777524605 hasConcept C2778755073 @default.
- W2777524605 hasConcept C2779343474 @default.
- W2777524605 hasConcept C2780719617 @default.
- W2777524605 hasConcept C31972630 @default.
- W2777524605 hasConcept C33923547 @default.
- W2777524605 hasConcept C41008148 @default.
- W2777524605 hasConcept C58640448 @default.
- W2777524605 hasConcept C62354387 @default.
- W2777524605 hasConcept C75294576 @default.
- W2777524605 hasConceptScore W2777524605C115961682 @default.
- W2777524605 hasConceptScore W2777524605C134306372 @default.
- W2777524605 hasConceptScore W2777524605C153180895 @default.
- W2777524605 hasConceptScore W2777524605C154945302 @default.
- W2777524605 hasConceptScore W2777524605C160633673 @default.
- W2777524605 hasConceptScore W2777524605C166957645 @default.
- W2777524605 hasConceptScore W2777524605C177264268 @default.
- W2777524605 hasConceptScore W2777524605C199360897 @default.
- W2777524605 hasConceptScore W2777524605C205649164 @default.
- W2777524605 hasConceptScore W2777524605C2778755073 @default.
- W2777524605 hasConceptScore W2777524605C2779343474 @default.
- W2777524605 hasConceptScore W2777524605C2780719617 @default.
- W2777524605 hasConceptScore W2777524605C31972630 @default.
- W2777524605 hasConceptScore W2777524605C33923547 @default.
- W2777524605 hasConceptScore W2777524605C41008148 @default.
- W2777524605 hasConceptScore W2777524605C58640448 @default.
- W2777524605 hasConceptScore W2777524605C62354387 @default.
- W2777524605 hasConceptScore W2777524605C75294576 @default.
- W2777524605 hasLocation W27775246051 @default.
- W2777524605 hasOpenAccess W2777524605 @default.
- W2777524605 hasPrimaryLocation W27775246051 @default.
- W2777524605 hasRelatedWork W1143616857 @default.
- W2777524605 hasRelatedWork W1542723449 @default.
- W2777524605 hasRelatedWork W1578319277 @default.
- W2777524605 hasRelatedWork W1603728330 @default.
- W2777524605 hasRelatedWork W2344082497 @default.
- W2777524605 hasRelatedWork W2885652903 @default.
- W2777524605 hasRelatedWork W2886879646 @default.
- W2777524605 hasRelatedWork W2891871283 @default.
- W2777524605 hasRelatedWork W2950246067 @default.
- W2777524605 hasRelatedWork W2952215315 @default.
- W2777524605 hasRelatedWork W2970105043 @default.
- W2777524605 hasRelatedWork W2986248793 @default.
- W2777524605 hasRelatedWork W2991621301 @default.
- W2777524605 hasRelatedWork W3004146378 @default.
- W2777524605 hasRelatedWork W3015931058 @default.
- W2777524605 hasRelatedWork W3029996395 @default.
- W2777524605 hasRelatedWork W3093830742 @default.
- W2777524605 hasRelatedWork W3124178290 @default.
- W2777524605 hasRelatedWork W3138715326 @default.
- W2777524605 hasRelatedWork W3193809323 @default.
- W2777524605 isParatext "false" @default.
- W2777524605 isRetracted "false" @default.
- W2777524605 magId "2777524605" @default.
- W2777524605 workType "article" @default.