Matches in SemOpenAlex for { <https://semopenalex.org/work/W3005395280> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3005395280 abstract "In this paper, we tackle the challenge for VSLAM of handling non-static environments. We propose to include semantic information obtained by deep learning methods in the traditional geometric pipeline. Specifically, we compute a confidence measure for each map point as a function of its semantic class (car, person, building, etc.) and its detection consistency over time. The confidence is then applied to guide the usage of each point in the mapping and localization stage. Points with high confidence are used to verify points with low confidence in order to select the final set of points for pose computation and mapping. Furthermore, we can handle map points whose state may change between static and dynamic (a car can be parked or in motion). Evaluating our method on public datasets, we show that it can successfully solve challenging situations in dynamic environments which cause state-of-the-art baseline VSLAM algorithms to fail and that it maintains performance on static scenes. Code is available at github.com/mthz/slamantic" @default.
- W3005395280 created "2020-02-14" @default.
- W3005395280 creator A5018565644 @default.
- W3005395280 creator A5026627076 @default.
- W3005395280 creator A5039062863 @default.
- W3005395280 creator A5050722856 @default.
- W3005395280 creator A5070076119 @default.
- W3005395280 date "2019-10-01" @default.
- W3005395280 modified "2023-10-02" @default.
- W3005395280 title "SLAMANTIC - Leveraging Semantics to Improve VSLAM in Dynamic Environments" @default.
- W3005395280 cites W2020310389 @default.
- W3005395280 cites W2021851106 @default.
- W3005395280 cites W2053740312 @default.
- W3005395280 cites W2076756823 @default.
- W3005395280 cites W2076917298 @default.
- W3005395280 cites W2150066425 @default.
- W3005395280 cites W2151290401 @default.
- W3005395280 cites W2340897893 @default.
- W3005395280 cites W2396274919 @default.
- W3005395280 cites W2412846155 @default.
- W3005395280 cites W2474281075 @default.
- W3005395280 cites W2556215627 @default.
- W3005395280 cites W2564632156 @default.
- W3005395280 cites W2606794968 @default.
- W3005395280 cites W2735010494 @default.
- W3005395280 cites W2745859992 @default.
- W3005395280 cites W2774058387 @default.
- W3005395280 cites W2788608285 @default.
- W3005395280 cites W2888816914 @default.
- W3005395280 cites W2897828525 @default.
- W3005395280 cites W2950629728 @default.
- W3005395280 cites W2950989657 @default.
- W3005395280 cites W2963150697 @default.
- W3005395280 cites W2963170338 @default.
- W3005395280 cites W2963323244 @default.
- W3005395280 cites W3103648783 @default.
- W3005395280 cites W3106458387 @default.
- W3005395280 cites W3124420883 @default.
- W3005395280 cites W4230766380 @default.
- W3005395280 cites W4246614213 @default.
- W3005395280 doi "https://doi.org/10.1109/iccvw.2019.00468" @default.
- W3005395280 hasPublicationYear "2019" @default.
- W3005395280 type Work @default.
- W3005395280 sameAs 3005395280 @default.
- W3005395280 citedByCount "15" @default.
- W3005395280 countsByYear W30053952802020 @default.
- W3005395280 countsByYear W30053952802021 @default.
- W3005395280 countsByYear W30053952802022 @default.
- W3005395280 countsByYear W30053952802023 @default.
- W3005395280 crossrefType "proceedings-article" @default.
- W3005395280 hasAuthorship W3005395280A5018565644 @default.
- W3005395280 hasAuthorship W3005395280A5026627076 @default.
- W3005395280 hasAuthorship W3005395280A5039062863 @default.
- W3005395280 hasAuthorship W3005395280A5050722856 @default.
- W3005395280 hasAuthorship W3005395280A5070076119 @default.
- W3005395280 hasConcept C154945302 @default.
- W3005395280 hasConcept C184337299 @default.
- W3005395280 hasConcept C199360897 @default.
- W3005395280 hasConcept C31972630 @default.
- W3005395280 hasConcept C41008148 @default.
- W3005395280 hasConceptScore W3005395280C154945302 @default.
- W3005395280 hasConceptScore W3005395280C184337299 @default.
- W3005395280 hasConceptScore W3005395280C199360897 @default.
- W3005395280 hasConceptScore W3005395280C31972630 @default.
- W3005395280 hasConceptScore W3005395280C41008148 @default.
- W3005395280 hasLocation W30053952801 @default.
- W3005395280 hasOpenAccess W3005395280 @default.
- W3005395280 hasPrimaryLocation W30053952801 @default.
- W3005395280 hasRelatedWork W1891287906 @default.
- W3005395280 hasRelatedWork W1969923398 @default.
- W3005395280 hasRelatedWork W2021592657 @default.
- W3005395280 hasRelatedWork W2036807459 @default.
- W3005395280 hasRelatedWork W2058170566 @default.
- W3005395280 hasRelatedWork W2110717643 @default.
- W3005395280 hasRelatedWork W2229312674 @default.
- W3005395280 hasRelatedWork W2755342338 @default.
- W3005395280 hasRelatedWork W2772917594 @default.
- W3005395280 hasRelatedWork W3116076068 @default.
- W3005395280 isParatext "false" @default.
- W3005395280 isRetracted "false" @default.
- W3005395280 magId "3005395280" @default.
- W3005395280 workType "article" @default.