Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312922040> ?p ?o ?g. }
- W4312922040 endingPage "1454" @default.
- W4312922040 startingPage "1447" @default.
- W4312922040 abstract "Locating the 6DoF pose of a camera in a known scene graph is a fundamental problem of SLAM. Hierarchical relocalization methods, which retrieve images first and match feature points later, have been widely studied by scholars for their high accuracy. In this paper, based on hierarchical relocalization, HAPOR (Hierarchical-features Aligned Projection Optimization for Relocalization), an end-to-end relocalization system, is proposed to combine image retrieval and iterative pose optimization. Through an attention mechanism branch, foreground dynamic objects and repeating textures are filtered out. We further design an image retrieval system (GTLGR) in HAPOR and generate an initial pose based on the co-visibility graph for subsequent iterative optimization. In addition, relying on GPS as ground truth for image retrieval training is quite inefficient, thus, we model the common visible area of two camera's view in 3D field, which significantly reduces the training time. Finally, we apply HAPOR to the ORB-SLAM2 system and obtain the state-of-the-art relocalization results." @default.
- W4312922040 created "2023-01-05" @default.
- W4312922040 creator A5008963038 @default.
- W4312922040 creator A5013648242 @default.
- W4312922040 creator A5017865816 @default.
- W4312922040 creator A5029571874 @default.
- W4312922040 creator A5033684035 @default.
- W4312922040 creator A5045294316 @default.
- W4312922040 creator A5071377574 @default.
- W4312922040 date "2023-03-01" @default.
- W4312922040 modified "2023-10-16" @default.
- W4312922040 title "HAPOR: Hierarchical-Features Aligned Projection Optimization for Relocalization" @default.
- W4312922040 cites W1608697715 @default.
- W4312922040 cites W1989476314 @default.
- W4312922040 cites W2069479606 @default.
- W4312922040 cites W2073761981 @default.
- W4312922040 cites W2200124539 @default.
- W4312922040 cites W2522940611 @default.
- W4312922040 cites W2556455135 @default.
- W4312922040 cites W2605111497 @default.
- W4312922040 cites W2771385090 @default.
- W4312922040 cites W2892865870 @default.
- W4312922040 cites W2951019013 @default.
- W4312922040 cites W2962858109 @default.
- W4312922040 cites W2963588253 @default.
- W4312922040 cites W2963856988 @default.
- W4312922040 cites W2964175348 @default.
- W4312922040 cites W2979458572 @default.
- W4312922040 cites W2982101479 @default.
- W4312922040 cites W2983230029 @default.
- W4312922040 cites W2990519439 @default.
- W4312922040 cites W2998413356 @default.
- W4312922040 cites W3003290274 @default.
- W4312922040 cites W3010479006 @default.
- W4312922040 cites W3017008958 @default.
- W4312922040 cites W3034213661 @default.
- W4312922040 cites W3034275286 @default.
- W4312922040 cites W3043075211 @default.
- W4312922040 cites W3091598621 @default.
- W4312922040 cites W3093386634 @default.
- W4312922040 cites W3099342433 @default.
- W4312922040 cites W3102327032 @default.
- W4312922040 cites W3106653913 @default.
- W4312922040 cites W3110536152 @default.
- W4312922040 cites W3173736705 @default.
- W4312922040 cites W3176602998 @default.
- W4312922040 cites W3198835173 @default.
- W4312922040 cites W4210786584 @default.
- W4312922040 cites W4306147890 @default.
- W4312922040 doi "https://doi.org/10.1109/lra.2022.3226069" @default.
- W4312922040 hasPublicationYear "2023" @default.
- W4312922040 type Work @default.
- W4312922040 citedByCount "0" @default.
- W4312922040 crossrefType "journal-article" @default.
- W4312922040 hasAuthorship W4312922040A5008963038 @default.
- W4312922040 hasAuthorship W4312922040A5013648242 @default.
- W4312922040 hasAuthorship W4312922040A5017865816 @default.
- W4312922040 hasAuthorship W4312922040A5029571874 @default.
- W4312922040 hasAuthorship W4312922040A5033684035 @default.
- W4312922040 hasAuthorship W4312922040A5045294316 @default.
- W4312922040 hasAuthorship W4312922040A5071377574 @default.
- W4312922040 hasConcept C108260229 @default.
- W4312922040 hasConcept C11413529 @default.
- W4312922040 hasConcept C115961682 @default.
- W4312922040 hasConcept C123403432 @default.
- W4312922040 hasConcept C132525143 @default.
- W4312922040 hasConcept C138885662 @default.
- W4312922040 hasConcept C153294291 @default.
- W4312922040 hasConcept C154945302 @default.
- W4312922040 hasConcept C205649164 @default.
- W4312922040 hasConcept C2776401178 @default.
- W4312922040 hasConcept C31972630 @default.
- W4312922040 hasConcept C41008148 @default.
- W4312922040 hasConcept C41895202 @default.
- W4312922040 hasConcept C57493831 @default.
- W4312922040 hasConcept C80444323 @default.
- W4312922040 hasConceptScore W4312922040C108260229 @default.
- W4312922040 hasConceptScore W4312922040C11413529 @default.
- W4312922040 hasConceptScore W4312922040C115961682 @default.
- W4312922040 hasConceptScore W4312922040C123403432 @default.
- W4312922040 hasConceptScore W4312922040C132525143 @default.
- W4312922040 hasConceptScore W4312922040C138885662 @default.
- W4312922040 hasConceptScore W4312922040C153294291 @default.
- W4312922040 hasConceptScore W4312922040C154945302 @default.
- W4312922040 hasConceptScore W4312922040C205649164 @default.
- W4312922040 hasConceptScore W4312922040C2776401178 @default.
- W4312922040 hasConceptScore W4312922040C31972630 @default.
- W4312922040 hasConceptScore W4312922040C41008148 @default.
- W4312922040 hasConceptScore W4312922040C41895202 @default.
- W4312922040 hasConceptScore W4312922040C57493831 @default.
- W4312922040 hasConceptScore W4312922040C80444323 @default.
- W4312922040 hasIssue "3" @default.
- W4312922040 hasLocation W43129220401 @default.
- W4312922040 hasOpenAccess W4312922040 @default.
- W4312922040 hasPrimaryLocation W43129220401 @default.
- W4312922040 hasRelatedWork W1504288058 @default.
- W4312922040 hasRelatedWork W2093185295 @default.
- W4312922040 hasRelatedWork W2167293474 @default.