Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366207218> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4366207218 abstract "The localization of objects is a crucial task in various applications such as robotics, virtual and augmented reality, and the transportation of goods in warehouses. Recent advances in deep learning have enabled the localization using monocular visual cameras. While structure from motion (SfM) predicts the absolute pose from a point cloud, absolute pose regression (APR) methods learn a semantic understanding of the environment through neural networks. However, both fields face challenges caused by the environment such as motion blur, lighting changes, repetitive patterns, and feature-less structures. This study aims to address these challenges by incorporating additional information and regularizing the absolute pose using relative pose regression (RPR) methods. RPR methods suffer under different challenges, i.e., motion blur. The optical flow between consecutive images is computed using the Lucas-Kanade algorithm, and the relative pose is predicted using an auxiliary small recurrent convolutional network. The fusion of absolute and relative poses is a complex task due to the mismatch between the global and local coordinate systems. State-of-the-art methods fusing absolute and relative poses use pose graph optimization (PGO) to regularize the absolute pose predictions using relative poses. In this work, we propose recurrent fusion networks to optimally align absolute and relative pose predictions to improve the absolute pose prediction. We evaluate eight different recurrent units and construct a simulation environment to pre-train the APR and RPR networks for better generalized training. Additionally, we record a large database of different scenarios in a challenging large-scale indoor environment that mimics a warehouse with transportation robots. We conduct hyperparameter searches and experiments to show the effectiveness of our recurrent fusion method compared to PGO." @default.
- W4366207218 created "2023-04-19" @default.
- W4366207218 creator A5023277657 @default.
- W4366207218 creator A5067248213 @default.
- W4366207218 creator A5069072700 @default.
- W4366207218 creator A5073940195 @default.
- W4366207218 creator A5087349227 @default.
- W4366207218 date "2023-04-14" @default.
- W4366207218 modified "2023-09-30" @default.
- W4366207218 title "Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments" @default.
- W4366207218 doi "https://doi.org/10.48550/arxiv.2304.07250" @default.
- W4366207218 hasPublicationYear "2023" @default.
- W4366207218 type Work @default.
- W4366207218 citedByCount "0" @default.
- W4366207218 crossrefType "posted-content" @default.
- W4366207218 hasAuthorship W4366207218A5023277657 @default.
- W4366207218 hasAuthorship W4366207218A5067248213 @default.
- W4366207218 hasAuthorship W4366207218A5069072700 @default.
- W4366207218 hasAuthorship W4366207218A5073940195 @default.
- W4366207218 hasAuthorship W4366207218A5087349227 @default.
- W4366207218 hasBestOaLocation W43662072181 @default.
- W4366207218 hasConcept C104114177 @default.
- W4366207218 hasConcept C105795698 @default.
- W4366207218 hasConcept C108583219 @default.
- W4366207218 hasConcept C115961682 @default.
- W4366207218 hasConcept C119857082 @default.
- W4366207218 hasConcept C121332964 @default.
- W4366207218 hasConcept C131979681 @default.
- W4366207218 hasConcept C146159030 @default.
- W4366207218 hasConcept C154945302 @default.
- W4366207218 hasConcept C155542232 @default.
- W4366207218 hasConcept C22100474 @default.
- W4366207218 hasConcept C2779265950 @default.
- W4366207218 hasConcept C31441030 @default.
- W4366207218 hasConcept C31972630 @default.
- W4366207218 hasConcept C33923547 @default.
- W4366207218 hasConcept C34413123 @default.
- W4366207218 hasConcept C36613465 @default.
- W4366207218 hasConcept C41008148 @default.
- W4366207218 hasConcept C52102323 @default.
- W4366207218 hasConcept C65909025 @default.
- W4366207218 hasConcept C81363708 @default.
- W4366207218 hasConcept C83546350 @default.
- W4366207218 hasConcept C90509273 @default.
- W4366207218 hasConcept C97355855 @default.
- W4366207218 hasConceptScore W4366207218C104114177 @default.
- W4366207218 hasConceptScore W4366207218C105795698 @default.
- W4366207218 hasConceptScore W4366207218C108583219 @default.
- W4366207218 hasConceptScore W4366207218C115961682 @default.
- W4366207218 hasConceptScore W4366207218C119857082 @default.
- W4366207218 hasConceptScore W4366207218C121332964 @default.
- W4366207218 hasConceptScore W4366207218C131979681 @default.
- W4366207218 hasConceptScore W4366207218C146159030 @default.
- W4366207218 hasConceptScore W4366207218C154945302 @default.
- W4366207218 hasConceptScore W4366207218C155542232 @default.
- W4366207218 hasConceptScore W4366207218C22100474 @default.
- W4366207218 hasConceptScore W4366207218C2779265950 @default.
- W4366207218 hasConceptScore W4366207218C31441030 @default.
- W4366207218 hasConceptScore W4366207218C31972630 @default.
- W4366207218 hasConceptScore W4366207218C33923547 @default.
- W4366207218 hasConceptScore W4366207218C34413123 @default.
- W4366207218 hasConceptScore W4366207218C36613465 @default.
- W4366207218 hasConceptScore W4366207218C41008148 @default.
- W4366207218 hasConceptScore W4366207218C52102323 @default.
- W4366207218 hasConceptScore W4366207218C65909025 @default.
- W4366207218 hasConceptScore W4366207218C81363708 @default.
- W4366207218 hasConceptScore W4366207218C83546350 @default.
- W4366207218 hasConceptScore W4366207218C90509273 @default.
- W4366207218 hasConceptScore W4366207218C97355855 @default.
- W4366207218 hasLocation W43662072181 @default.
- W4366207218 hasOpenAccess W4366207218 @default.
- W4366207218 hasPrimaryLocation W43662072181 @default.
- W4366207218 hasRelatedWork W1968716783 @default.
- W4366207218 hasRelatedWork W1970467378 @default.
- W4366207218 hasRelatedWork W2025164974 @default.
- W4366207218 hasRelatedWork W2115571026 @default.
- W4366207218 hasRelatedWork W2128635338 @default.
- W4366207218 hasRelatedWork W2129348295 @default.
- W4366207218 hasRelatedWork W2144760288 @default.
- W4366207218 hasRelatedWork W2891001608 @default.
- W4366207218 hasRelatedWork W3102636071 @default.
- W4366207218 hasRelatedWork W4247709045 @default.
- W4366207218 isParatext "false" @default.
- W4366207218 isRetracted "false" @default.
- W4366207218 workType "article" @default.