BROWSE

Related Scientist

cnir's photo.

cnir
뇌과학이미징연구단
more info

ITEM VIEW & DOWNLOAD

Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames

DC Field Value Language
dc.contributor.authorLee, Jinkyu-
dc.contributor.authorBack, Muhyun-
dc.contributor.authorHwang, Sung Soo-
dc.contributor.authorIl Yong Chun-
dc.date.accessioned2023-04-04T22:08:09Z-
dc.date.available2023-04-04T22:08:09Z-
dc.date.created2023-01-27-
dc.date.issued2023-03-
dc.identifier.issn1524-9050-
dc.identifier.urihttps://pr.ibs.re.kr/handle/8788114/13127-
dc.description.abstractMonocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. To achieve the real-time execution of the proposed method, we apply semantic segmentation only to downsampled keyframes in parallel with mapping processes. In addition, the proposed method corrects scales of camera poses and three-dimensional (3D) points, using estimated ground plane from road-labeled 3D points and the real camera height. The proposed method also removes inappropriate corner features labeled as moving objects and low parallax areas. Experiments with eight video sequences demonstrate that the proposed monocular SLAM system achieves significantly improved and comparable trajectory tracking accuracy, compared to existing state-of-the-art monocular and stereo SLAM systems, respectively. The proposed system can achieve real-time tracking on a standard CPU potentially with a standard GPU support, whereas existing segmentation-aided monocular SLAM does not.-
dc.language영어-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.titleImproved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames-
dc.typeArticle-
dc.type.rimsART-
dc.identifier.wosid000903544000001-
dc.identifier.scopusid2-s2.0-85146252027-
dc.identifier.rimsid79772-
dc.contributor.affiliatedAuthorIl Yong Chun-
dc.identifier.doi10.1109/TITS.2022.3228525-
dc.identifier.bibliographicCitationIEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, v.24, no.3, pp.2800 - 2813-
dc.relation.isPartOfIEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS-
dc.citation.titleIEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS-
dc.citation.volume24-
dc.citation.number3-
dc.citation.startPage2800-
dc.citation.endPage2813-
dc.type.docTypeArticle-
dc.description.journalClass1-
dc.description.journalClass1-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaEngineering-
dc.relation.journalResearchAreaTransportation-
dc.relation.journalWebOfScienceCategoryEngineering, Civil-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.relation.journalWebOfScienceCategoryTransportation Science & Technology-
dc.subject.keywordAuthorVisual simultaneous localization and mapping (SLAM)-
dc.subject.keywordAuthormonocular SLAM-
dc.subject.keywordAuthorkeyframes-
dc.subject.keywordAuthordeep semantic segmentation-
dc.subject.keywordAuthorscale correction-
dc.subject.keywordAuthoradvanced driver assistance systems (ADAS)-
dc.subject.keywordAuthorautonomous driving-
Appears in Collections:
Center for Neuroscience Imaging Research (뇌과학 이미징 연구단) > 1. Journal Papers (저널논문)
Files in This Item:
There are no files associated with this item.

qrcode

  • facebook

    twitter

  • Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
해당 아이템을 이메일로 공유하기 원하시면 인증을 거치시기 바랍니다.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse