Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890003176> ?p ?o ?g. }
- W2890003176 endingPage "452" @default.
- W2890003176 startingPage "445" @default.
- W2890003176 abstract "In this work, we research and evaluate end-to-end learning of monocular semantic-metric occupancy grid mapping from weak binocular ground truth. The network learns to predict four classes, as well as a camera to bird's eye view mapping. At the core, it utilizes a variational encoder-decoder network that encodes the front-view visual information of the driving scene and subsequently decodes it into a 2-D top-view Cartesian coordinate system. The evaluations on Cityscapes show that the end-to-end learning of semantic-metric occupancy grids outperforms the deterministic mapping approach with flat-plane assumption by more than 12% mean IoU. Furthermore, we show that the variational sampling with a relatively small embedding vector brings robustness against vehicle dynamic perturbations, and generalizability for unseen KITTI data. Our network achieves real-time inference rates of approx. 35 Hz for an input image with a resolution of 256x512 pixels and an output map with 64x64 occupancy grid cells using a Titan V GPU." @default.
- W2890003176 created "2018-09-27" @default.
- W2890003176 creator A5024010116 @default.
- W2890003176 creator A5036722855 @default.
- W2890003176 creator A5037248049 @default.
- W2890003176 date "2019-04-01" @default.
- W2890003176 modified "2023-10-18" @default.
- W2890003176 title "Monocular Semantic Occupancy Grid Mapping With Convolutional Variational Encoder–Decoder Networks" @default.
- W2890003176 cites W1536680647 @default.
- W2890003176 cites W1971618559 @default.
- W2890003176 cites W1993871896 @default.
- W2890003176 cites W2033979122 @default.
- W2890003176 cites W2102605133 @default.
- W2890003176 cites W2115579991 @default.
- W2890003176 cites W2117248802 @default.
- W2890003176 cites W2117539524 @default.
- W2890003176 cites W2124592697 @default.
- W2890003176 cites W2157536205 @default.
- W2890003176 cites W2167687475 @default.
- W2890003176 cites W2194775991 @default.
- W2890003176 cites W2340897893 @default.
- W2890003176 cites W2395611524 @default.
- W2890003176 cites W2412782625 @default.
- W2890003176 cites W2470820246 @default.
- W2890003176 cites W2517188359 @default.
- W2890003176 cites W2520707372 @default.
- W2890003176 cites W2523049145 @default.
- W2890003176 cites W2560023338 @default.
- W2890003176 cites W2606794968 @default.
- W2890003176 cites W2609883120 @default.
- W2890003176 cites W2618530766 @default.
- W2890003176 cites W2736636266 @default.
- W2890003176 cites W2963150697 @default.
- W2890003176 cites W2963324085 @default.
- W2890003176 cites W2963632154 @default.
- W2890003176 cites W2963787264 @default.
- W2890003176 cites W2963881378 @default.
- W2890003176 cites W3100388886 @default.
- W2890003176 cites W639708223 @default.
- W2890003176 cites W801273237 @default.
- W2890003176 doi "https://doi.org/10.1109/lra.2019.2891028" @default.
- W2890003176 hasPublicationYear "2019" @default.
- W2890003176 type Work @default.
- W2890003176 sameAs 2890003176 @default.
- W2890003176 citedByCount "75" @default.
- W2890003176 countsByYear W28900031762019 @default.
- W2890003176 countsByYear W28900031762020 @default.
- W2890003176 countsByYear W28900031762021 @default.
- W2890003176 countsByYear W28900031762022 @default.
- W2890003176 countsByYear W28900031762023 @default.
- W2890003176 crossrefType "journal-article" @default.
- W2890003176 hasAuthorship W2890003176A5024010116 @default.
- W2890003176 hasAuthorship W2890003176A5036722855 @default.
- W2890003176 hasAuthorship W2890003176A5037248049 @default.
- W2890003176 hasBestOaLocation W28900031762 @default.
- W2890003176 hasConcept C104317684 @default.
- W2890003176 hasConcept C111919701 @default.
- W2890003176 hasConcept C11413529 @default.
- W2890003176 hasConcept C115051666 @default.
- W2890003176 hasConcept C118505674 @default.
- W2890003176 hasConcept C146849305 @default.
- W2890003176 hasConcept C154945302 @default.
- W2890003176 hasConcept C185592680 @default.
- W2890003176 hasConcept C187691185 @default.
- W2890003176 hasConcept C19966478 @default.
- W2890003176 hasConcept C2524010 @default.
- W2890003176 hasConcept C31972630 @default.
- W2890003176 hasConcept C33923547 @default.
- W2890003176 hasConcept C41008148 @default.
- W2890003176 hasConcept C41608201 @default.
- W2890003176 hasConcept C55493867 @default.
- W2890003176 hasConcept C57077369 @default.
- W2890003176 hasConcept C63479239 @default.
- W2890003176 hasConcept C65909025 @default.
- W2890003176 hasConcept C76155785 @default.
- W2890003176 hasConcept C90509273 @default.
- W2890003176 hasConceptScore W2890003176C104317684 @default.
- W2890003176 hasConceptScore W2890003176C111919701 @default.
- W2890003176 hasConceptScore W2890003176C11413529 @default.
- W2890003176 hasConceptScore W2890003176C115051666 @default.
- W2890003176 hasConceptScore W2890003176C118505674 @default.
- W2890003176 hasConceptScore W2890003176C146849305 @default.
- W2890003176 hasConceptScore W2890003176C154945302 @default.
- W2890003176 hasConceptScore W2890003176C185592680 @default.
- W2890003176 hasConceptScore W2890003176C187691185 @default.
- W2890003176 hasConceptScore W2890003176C19966478 @default.
- W2890003176 hasConceptScore W2890003176C2524010 @default.
- W2890003176 hasConceptScore W2890003176C31972630 @default.
- W2890003176 hasConceptScore W2890003176C33923547 @default.
- W2890003176 hasConceptScore W2890003176C41008148 @default.
- W2890003176 hasConceptScore W2890003176C41608201 @default.
- W2890003176 hasConceptScore W2890003176C55493867 @default.
- W2890003176 hasConceptScore W2890003176C57077369 @default.
- W2890003176 hasConceptScore W2890003176C63479239 @default.
- W2890003176 hasConceptScore W2890003176C65909025 @default.
- W2890003176 hasConceptScore W2890003176C76155785 @default.
- W2890003176 hasConceptScore W2890003176C90509273 @default.
- W2890003176 hasFunder F4320321651 @default.