Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891377414> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2891377414 abstract "Loop closure detection is essential and important in visual simultaneous localization and mapping (SLAM) systems. Most existing methods typically utilize a separate feature extraction part and a similarity metric part. Compared to these methods, an end-to-end network is proposed in this paper to jointly optimize the two parts in a unified framework for further enhancing the interworking between these two parts. First, a two-branch siamese network is designed to learn respective features for each scene of an image pair. Then a hierarchical weighted distance (HWD) layer is proposed to fuse the multi-scale features of each convolutional module and calculate the distance between the image pair. Finally, by using the contrastive loss in the training process, the effective feature representation and similarity metric can be learned simultaneously. Experiments on several open datasets illustrate the superior performance of our approach and demonstrate that the end-to-end network is feasible to conduct the loop closure detection in real time and provides an implementable method for visual SLAM systems." @default.
- W2891377414 created "2018-09-27" @default.
- W2891377414 creator A5032675026 @default.
- W2891377414 creator A5046393276 @default.
- W2891377414 creator A5055675902 @default.
- W2891377414 creator A5078160191 @default.
- W2891377414 date "2018-04-01" @default.
- W2891377414 modified "2023-10-14" @default.
- W2891377414 title "An End-To-End Siamese Convolutional Neural Network for Loop Closure Detection in Visual Slam System" @default.
- W2891377414 cites W1703761565 @default.
- W2891377414 cites W1989174032 @default.
- W2891377414 cites W1989484209 @default.
- W2891377414 cites W1996035538 @default.
- W2891377414 cites W2131846894 @default.
- W2891377414 cites W2135442311 @default.
- W2891377414 cites W2144824356 @default.
- W2891377414 cites W2146881125 @default.
- W2891377414 cites W2162536300 @default.
- W2891377414 cites W2163922914 @default.
- W2891377414 cites W2165213665 @default.
- W2891377414 cites W2183341477 @default.
- W2891377414 cites W2290577462 @default.
- W2891377414 cites W2327482370 @default.
- W2891377414 cites W3103648783 @default.
- W2891377414 doi "https://doi.org/10.1109/icassp.2018.8462426" @default.
- W2891377414 hasPublicationYear "2018" @default.
- W2891377414 type Work @default.
- W2891377414 sameAs 2891377414 @default.
- W2891377414 citedByCount "9" @default.
- W2891377414 countsByYear W28913774142019 @default.
- W2891377414 countsByYear W28913774142020 @default.
- W2891377414 countsByYear W28913774142021 @default.
- W2891377414 countsByYear W28913774142022 @default.
- W2891377414 crossrefType "proceedings-article" @default.
- W2891377414 hasAuthorship W2891377414A5032675026 @default.
- W2891377414 hasAuthorship W2891377414A5046393276 @default.
- W2891377414 hasAuthorship W2891377414A5055675902 @default.
- W2891377414 hasAuthorship W2891377414A5078160191 @default.
- W2891377414 hasConcept C114614502 @default.
- W2891377414 hasConcept C146834321 @default.
- W2891377414 hasConcept C154945302 @default.
- W2891377414 hasConcept C162324750 @default.
- W2891377414 hasConcept C184670325 @default.
- W2891377414 hasConcept C19966478 @default.
- W2891377414 hasConcept C31972630 @default.
- W2891377414 hasConcept C33923547 @default.
- W2891377414 hasConcept C34447519 @default.
- W2891377414 hasConcept C41008148 @default.
- W2891377414 hasConcept C74296488 @default.
- W2891377414 hasConcept C81363708 @default.
- W2891377414 hasConcept C86369673 @default.
- W2891377414 hasConcept C90509273 @default.
- W2891377414 hasConceptScore W2891377414C114614502 @default.
- W2891377414 hasConceptScore W2891377414C146834321 @default.
- W2891377414 hasConceptScore W2891377414C154945302 @default.
- W2891377414 hasConceptScore W2891377414C162324750 @default.
- W2891377414 hasConceptScore W2891377414C184670325 @default.
- W2891377414 hasConceptScore W2891377414C19966478 @default.
- W2891377414 hasConceptScore W2891377414C31972630 @default.
- W2891377414 hasConceptScore W2891377414C33923547 @default.
- W2891377414 hasConceptScore W2891377414C34447519 @default.
- W2891377414 hasConceptScore W2891377414C41008148 @default.
- W2891377414 hasConceptScore W2891377414C74296488 @default.
- W2891377414 hasConceptScore W2891377414C81363708 @default.
- W2891377414 hasConceptScore W2891377414C86369673 @default.
- W2891377414 hasConceptScore W2891377414C90509273 @default.
- W2891377414 hasLocation W28913774141 @default.
- W2891377414 hasOpenAccess W2891377414 @default.
- W2891377414 hasPrimaryLocation W28913774141 @default.
- W2891377414 hasRelatedWork W2074515009 @default.
- W2891377414 hasRelatedWork W2086478527 @default.
- W2891377414 hasRelatedWork W2116298349 @default.
- W2891377414 hasRelatedWork W2154461499 @default.
- W2891377414 hasRelatedWork W2625455490 @default.
- W2891377414 hasRelatedWork W2970243024 @default.
- W2891377414 hasRelatedWork W2973077977 @default.
- W2891377414 hasRelatedWork W3013616745 @default.
- W2891377414 hasRelatedWork W4206120224 @default.
- W2891377414 hasRelatedWork W4292862563 @default.
- W2891377414 isParatext "false" @default.
- W2891377414 isRetracted "false" @default.
- W2891377414 magId "2891377414" @default.
- W2891377414 workType "article" @default.