Matches in SemOpenAlex for { <https://semopenalex.org/work/W2979409870> ?p ?o ?g. }
- W2979409870 abstract "Localization and Mapping is an essential component to enable Autonomous Vehicles navigation, and requires an accuracy exceeding that of commercial GPS-based systems. Current odometry and mapping algorithms are able to provide this accurate information. However, the lack of robustness of these algorithms against dynamic obstacles and environmental changes, even for short time periods, forces the generation of new maps on every session without taking advantage of previously obtained ones. In this paper we propose the use of a deep learning architecture to segment movable objects from 3D LiDAR point clouds in order to obtain longer-lasting 3D maps. This will in turn allow for better, faster and more accurate re-localization and trajectoy estimation on subsequent days. We show the effectiveness of our approach in a very dynamic and cluttered scenario, a supermarket parking lot. For that, we record several sequences on different days and compare localization errors with and without our movable objects segmentation method. Results show that we are able to accurately re-locate over a filtered map, consistently reducing trajectory errors between an average of 35.1% with respect to a non-filtered map version and of 47.9% with respect to a standalone map created on the current session." @default.
- W2979409870 created "2019-10-18" @default.
- W2979409870 creator A5036092986 @default.
- W2979409870 creator A5039109392 @default.
- W2979409870 creator A5039307249 @default.
- W2979409870 creator A5041730641 @default.
- W2979409870 creator A5067862785 @default.
- W2979409870 date "2019-10-08" @default.
- W2979409870 modified "2023-09-24" @default.
- W2979409870 title "Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds" @default.
- W2979409870 cites W1677182931 @default.
- W2979409870 cites W2097144670 @default.
- W2979409870 cites W2131684180 @default.
- W2979409870 cites W2146881125 @default.
- W2979409870 cites W2150066425 @default.
- W2979409870 cites W2163605009 @default.
- W2979409870 cites W2266469970 @default.
- W2979409870 cites W2279098554 @default.
- W2979409870 cites W2295130602 @default.
- W2979409870 cites W2296228853 @default.
- W2979409870 cites W2395611524 @default.
- W2979409870 cites W2558294288 @default.
- W2979409870 cites W2560609797 @default.
- W2979409870 cites W2750632489 @default.
- W2979409870 cites W2872491670 @default.
- W2979409870 cites W2889390559 @default.
- W2979409870 cites W2962867954 @default.
- W2979409870 cites W2962912109 @default.
- W2979409870 cites W2963046720 @default.
- W2979409870 cites W2963083779 @default.
- W2979409870 cites W2963121255 @default.
- W2979409870 cites W2963438049 @default.
- W2979409870 cites W2963647876 @default.
- W2979409870 cites W2963721253 @default.
- W2979409870 cites W2963727135 @default.
- W2979409870 cites W2964062501 @default.
- W2979409870 cites W2968557240 @default.
- W2979409870 cites W3099455272 @default.
- W2979409870 cites W3124420883 @default.
- W2979409870 cites W639708223 @default.
- W2979409870 hasPublicationYear "2019" @default.
- W2979409870 type Work @default.
- W2979409870 sameAs 2979409870 @default.
- W2979409870 citedByCount "0" @default.
- W2979409870 crossrefType "posted-content" @default.
- W2979409870 hasAuthorship W2979409870A5036092986 @default.
- W2979409870 hasAuthorship W2979409870A5039109392 @default.
- W2979409870 hasAuthorship W2979409870A5039307249 @default.
- W2979409870 hasAuthorship W2979409870A5041730641 @default.
- W2979409870 hasAuthorship W2979409870A5067862785 @default.
- W2979409870 hasConcept C104317684 @default.
- W2979409870 hasConcept C108583219 @default.
- W2979409870 hasConcept C121332964 @default.
- W2979409870 hasConcept C1276947 @default.
- W2979409870 hasConcept C131979681 @default.
- W2979409870 hasConcept C13662910 @default.
- W2979409870 hasConcept C154945302 @default.
- W2979409870 hasConcept C185592680 @default.
- W2979409870 hasConcept C19966478 @default.
- W2979409870 hasConcept C205649164 @default.
- W2979409870 hasConcept C31972630 @default.
- W2979409870 hasConcept C41008148 @default.
- W2979409870 hasConcept C49441653 @default.
- W2979409870 hasConcept C51399673 @default.
- W2979409870 hasConcept C55493867 @default.
- W2979409870 hasConcept C60229501 @default.
- W2979409870 hasConcept C62649853 @default.
- W2979409870 hasConcept C63479239 @default.
- W2979409870 hasConcept C76155785 @default.
- W2979409870 hasConcept C89600930 @default.
- W2979409870 hasConcept C90509273 @default.
- W2979409870 hasConceptScore W2979409870C104317684 @default.
- W2979409870 hasConceptScore W2979409870C108583219 @default.
- W2979409870 hasConceptScore W2979409870C121332964 @default.
- W2979409870 hasConceptScore W2979409870C1276947 @default.
- W2979409870 hasConceptScore W2979409870C131979681 @default.
- W2979409870 hasConceptScore W2979409870C13662910 @default.
- W2979409870 hasConceptScore W2979409870C154945302 @default.
- W2979409870 hasConceptScore W2979409870C185592680 @default.
- W2979409870 hasConceptScore W2979409870C19966478 @default.
- W2979409870 hasConceptScore W2979409870C205649164 @default.
- W2979409870 hasConceptScore W2979409870C31972630 @default.
- W2979409870 hasConceptScore W2979409870C41008148 @default.
- W2979409870 hasConceptScore W2979409870C49441653 @default.
- W2979409870 hasConceptScore W2979409870C51399673 @default.
- W2979409870 hasConceptScore W2979409870C55493867 @default.
- W2979409870 hasConceptScore W2979409870C60229501 @default.
- W2979409870 hasConceptScore W2979409870C62649853 @default.
- W2979409870 hasConceptScore W2979409870C63479239 @default.
- W2979409870 hasConceptScore W2979409870C76155785 @default.
- W2979409870 hasConceptScore W2979409870C89600930 @default.
- W2979409870 hasConceptScore W2979409870C90509273 @default.
- W2979409870 hasOpenAccess W2979409870 @default.
- W2979409870 hasRelatedWork W2741562645 @default.
- W2979409870 hasRelatedWork W2789448087 @default.
- W2979409870 hasRelatedWork W2903928505 @default.
- W2979409870 hasRelatedWork W2907749395 @default.
- W2979409870 hasRelatedWork W2910925829 @default.
- W2979409870 hasRelatedWork W2921043432 @default.
- W2979409870 hasRelatedWork W2922315176 @default.