DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Ue-Hwan | ko |
dc.contributor.author | Kim, Se-Ho | ko |
dc.contributor.author | Kim, Jong-Hwan | ko |
dc.date.accessioned | 2022-04-13T06:47:37Z | - |
dc.date.available | 2022-04-13T06:47:37Z | - |
dc.date.created | 2022-04-04 | - |
dc.date.created | 2022-04-04 | - |
dc.date.created | 2022-04-04 | - |
dc.date.issued | 2022-04 | - |
dc.identifier.citation | IEEE ROBOTICS AND AUTOMATION LETTERS, v.7, no.2, pp.4244 - 4251 | - |
dc.identifier.issn | 2377-3766 | - |
dc.identifier.uri | http://hdl.handle.net/10203/292557 | - |
dc.description.abstract | Accurate estimation of 3D geometry and camera motion enables a wide range of tasks in robotics and autonomous vehicles. However, the lack of semantics and the performance degradation due to dynamic objects hinder its application to real-world scenarios. To overcome these limitations, we design a novel neural semantic visual odometry (VO) architecture on top of the simultaneous VO, object detection and instance segmentation (SimVODIS) network. Next, we propose an attentive pose estimation architecture with a multi-task learning formulation for handling dynamic objects and VO performance enhancement. The extensive experiments conducted in our work attest that the proposed SimVODIS++ improves the VO performance in dynamic environments. Further, SimVODIS++ focuses on salient regions while excluding feature-less regions. Performing the experiments, we have discovered and fixed the data leakage problem in the conventional experiment setting followed by numerous previous works-which we claim as one of our contributions. We make the source code public. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | SimVODIS++: Neural Semantic Visual Odometry in Dynamic Environments | - |
dc.type | Article | - |
dc.identifier.wosid | 000761228500003 | - |
dc.identifier.scopusid | 2-s2.0-85124836170 | - |
dc.type.rims | ART | - |
dc.citation.volume | 7 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 4244 | - |
dc.citation.endingpage | 4251 | - |
dc.citation.publicationname | IEEE ROBOTICS AND AUTOMATION LETTERS | - |
dc.identifier.doi | 10.1109/LRA.2022.3150854 | - |
dc.contributor.localauthor | Kim, Jong-Hwan | - |
dc.contributor.nonIdAuthor | Kim, Ue-Hwan | - |
dc.contributor.nonIdAuthor | Kim, Se-Ho | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Semantics | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Dynamics | - |
dc.subject.keywordAuthor | Pose estimation | - |
dc.subject.keywordAuthor | Cameras | - |
dc.subject.keywordAuthor | Vehicle dynamics | - |
dc.subject.keywordAuthor | Computer architecture | - |
dc.subject.keywordAuthor | Semantic scene understanding | - |
dc.subject.keywordAuthor | visual odometry (VO) | - |
dc.subject.keywordAuthor | semantic SLAM | - |
dc.subject.keywordAuthor | semantic VO | - |
dc.subject.keywordAuthor | dynamic objects | - |
dc.subject.keywordAuthor | robotics | - |
dc.subject.keywordAuthor | autonomous vehicles | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.