Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201569612> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3201569612 abstract "We present a generic framework for scale-aware direct monocular odometry based on depth prediction from a deep neural network. In contrast with previous methods where depth information is only partially exploited, we formulate a novel depth prediction residual which allows us to incorporate multi-view depth information. In addition, we propose to use a truncated robust cost function which prevents considering inconsistent depth estimations. The photometric and depth-prediction measurements are integrated into a tightly-coupled optimization leading to a scale-aware monocular system which does not accumulate scale drift. Our proposal does not particularize for a concrete neural network, being able to work along with the vast majority of the existing depth prediction solutions. We demonstrate the validity and generality of our proposal evaluating it on the KITTI odometry dataset, using two publicly available neural networks and comparing it with similar approaches and the state-of-the-art for monocular and stereo SLAM. Experiments show that our proposal largely outperforms classic monocular SLAM, being 5 to 9 times more precise, beating similar approaches and having an accuracy which is closer to that of stereo systems." @default.
- W3201569612 created "2021-09-27" @default.
- W3201569612 creator A5030733231 @default.
- W3201569612 creator A5063782759 @default.
- W3201569612 date "2022-10-23" @default.
- W3201569612 modified "2023-10-16" @default.
- W3201569612 title "Scale-aware direct monocular odometry" @default.
- W3201569612 cites W1539091696 @default.
- W3201569612 cites W2021851106 @default.
- W3201569612 cites W2035379092 @default.
- W3201569612 cites W2115579991 @default.
- W3201569612 cites W2118428504 @default.
- W3201569612 cites W2474281075 @default.
- W3201569612 cites W2606794968 @default.
- W3201569612 cites W2928601293 @default.
- W3201569612 cites W2973258311 @default.
- W3201569612 cites W2985775862 @default.
- W3201569612 cites W3035056458 @default.
- W3201569612 cites W3091687063 @default.
- W3201569612 cites W3102327032 @default.
- W3201569612 cites W3103648783 @default.
- W3201569612 cites W3165610079 @default.
- W3201569612 cites W4236769309 @default.
- W3201569612 doi "https://doi.org/10.1109/iros47612.2022.9982173" @default.
- W3201569612 hasPublicationYear "2022" @default.
- W3201569612 type Work @default.
- W3201569612 sameAs 3201569612 @default.
- W3201569612 citedByCount "3" @default.
- W3201569612 countsByYear W32015696122022 @default.
- W3201569612 countsByYear W32015696122023 @default.
- W3201569612 crossrefType "proceedings-article" @default.
- W3201569612 hasAuthorship W3201569612A5030733231 @default.
- W3201569612 hasAuthorship W3201569612A5063782759 @default.
- W3201569612 hasBestOaLocation W32015696122 @default.
- W3201569612 hasConcept C121332964 @default.
- W3201569612 hasConcept C13280743 @default.
- W3201569612 hasConcept C154945302 @default.
- W3201569612 hasConcept C15744967 @default.
- W3201569612 hasConcept C185798385 @default.
- W3201569612 hasConcept C19966478 @default.
- W3201569612 hasConcept C205649164 @default.
- W3201569612 hasConcept C2778755073 @default.
- W3201569612 hasConcept C2780767217 @default.
- W3201569612 hasConcept C31972630 @default.
- W3201569612 hasConcept C41008148 @default.
- W3201569612 hasConcept C49441653 @default.
- W3201569612 hasConcept C50644808 @default.
- W3201569612 hasConcept C542102704 @default.
- W3201569612 hasConcept C5799516 @default.
- W3201569612 hasConcept C62520636 @default.
- W3201569612 hasConcept C65909025 @default.
- W3201569612 hasConcept C86369673 @default.
- W3201569612 hasConcept C90509273 @default.
- W3201569612 hasConceptScore W3201569612C121332964 @default.
- W3201569612 hasConceptScore W3201569612C13280743 @default.
- W3201569612 hasConceptScore W3201569612C154945302 @default.
- W3201569612 hasConceptScore W3201569612C15744967 @default.
- W3201569612 hasConceptScore W3201569612C185798385 @default.
- W3201569612 hasConceptScore W3201569612C19966478 @default.
- W3201569612 hasConceptScore W3201569612C205649164 @default.
- W3201569612 hasConceptScore W3201569612C2778755073 @default.
- W3201569612 hasConceptScore W3201569612C2780767217 @default.
- W3201569612 hasConceptScore W3201569612C31972630 @default.
- W3201569612 hasConceptScore W3201569612C41008148 @default.
- W3201569612 hasConceptScore W3201569612C49441653 @default.
- W3201569612 hasConceptScore W3201569612C50644808 @default.
- W3201569612 hasConceptScore W3201569612C542102704 @default.
- W3201569612 hasConceptScore W3201569612C5799516 @default.
- W3201569612 hasConceptScore W3201569612C62520636 @default.
- W3201569612 hasConceptScore W3201569612C65909025 @default.
- W3201569612 hasConceptScore W3201569612C86369673 @default.
- W3201569612 hasConceptScore W3201569612C90509273 @default.
- W3201569612 hasLocation W32015696121 @default.
- W3201569612 hasLocation W32015696122 @default.
- W3201569612 hasOpenAccess W3201569612 @default.
- W3201569612 hasPrimaryLocation W32015696121 @default.
- W3201569612 hasRelatedWork W2003315864 @default.
- W3201569612 hasRelatedWork W2018811431 @default.
- W3201569612 hasRelatedWork W2507439537 @default.
- W3201569612 hasRelatedWork W2785664508 @default.
- W3201569612 hasRelatedWork W2971051170 @default.
- W3201569612 hasRelatedWork W2998859698 @default.
- W3201569612 hasRelatedWork W3039617376 @default.
- W3201569612 hasRelatedWork W3110752836 @default.
- W3201569612 hasRelatedWork W4386822182 @default.
- W3201569612 hasRelatedWork W813170165 @default.
- W3201569612 isParatext "false" @default.
- W3201569612 isRetracted "false" @default.
- W3201569612 magId "3201569612" @default.
- W3201569612 workType "article" @default.