Publications
Detailed Information
Line as a Visual Sentence: Context-Aware Line Descriptor for Visual Localization
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoon, Sungho | - |
dc.contributor.author | Kim, Ayoung | - |
dc.date.accessioned | 2023-12-11T00:42:28Z | - |
dc.date.available | 2023-12-11T00:42:28Z | - |
dc.date.created | 2021-11-08 | - |
dc.date.issued | 2021-10 | - |
dc.identifier.citation | IEEE Robotics and Automation Letters, Vol.6 No.4, pp.8726-8733 | - |
dc.identifier.issn | 2377-3766 | - |
dc.identifier.uri | https://hdl.handle.net/10371/197699 | - |
dc.description.abstract | Along with feature points for image matching, line features provide additional constraints to solve visual geometric problems in robotics and computer vision (CV). Although recent convolutional neural network (CNN)-based line descriptors are promising for viewpoint changes or dynamic environments, we claim that the CNN architecture has innate disadvantages to abstract variable line length into the fixed-dimensional descriptor. In this letter, we effectively introduce Line-Transformers dealing with variable lines. Inspired by natural language processing (NLP) tasks where sentences can be understood and abstracted well in neural nets, we view a line segment as a sentence that contains points (words). By attending to well-describable points on a line dynamically, our descriptor performs excellently on variable line length. We also propose line signature networks sharing the line's geometric attributes to neighborhoods. Performing as group descriptors, the networks enhance line descriptors by understanding lines' relative geometries. Finally, we present the proposed line descriptor and matching in a Point and Line Localization (PL-Loc). We show that the visual localization with feature points can be improved using our line features. We validate the proposed method for homography estimation and visual localization. | - |
dc.language | 영어 | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Line as a Visual Sentence: Context-Aware Line Descriptor for Visual Localization | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/LRA.2021.3111760 | - |
dc.citation.journaltitle | IEEE Robotics and Automation Letters | - |
dc.identifier.wosid | 000706821900001 | - |
dc.identifier.scopusid | 2-s2.0-85114747529 | - |
dc.citation.endpage | 8733 | - |
dc.citation.number | 4 | - |
dc.citation.startpage | 8726 | - |
dc.citation.volume | 6 | - |
dc.description.isOpenAccess | Y | - |
dc.contributor.affiliatedAuthor | Kim, Ayoung | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordAuthor | Transformers | - |
dc.subject.keywordAuthor | Visualization | - |
dc.subject.keywordAuthor | Image segmentation | - |
dc.subject.keywordAuthor | Simultaneous localization and mapping | - |
dc.subject.keywordAuthor | Location awareness | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Convolutional neural networks | - |
dc.subject.keywordAuthor | Localization | - |
dc.subject.keywordAuthor | SLAM | - |
dc.subject.keywordAuthor | deep learning for visual perception | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.