TU Darmstadt / ULB / TUbiblio

LLama-SLAM: Learning High-Quality Visual Landmarks for Long-Term Mapping and Localization

Luthardt, Stefan ; Willert, Volker ; Adamy, Jürgen (2019)
LLama-SLAM: Learning High-Quality Visual Landmarks for Long-Term Mapping and Localization.
2018 21st International Conference on Intelligent Transportation Systems (ITSC). Maui, Hawaii, USA (04.11. - 07.11.2018)
Konferenzveröffentlichung, Zweitveröffentlichung, Postprint

WarnungEs ist eine neuere Version dieses Eintrags verfügbar.

Kurzbeschreibung (Abstract)

The precise localization of vehicles is an important requirement for autonomous driving or advanced driver assistance systems. Using common GNSS the ego position can be measured but not with the reliability and precision necessary. An alternative approach to achieve precise localization is the usage of visual landmarks observed by a camera mounted in the vehicle. However, this raises the necessity of reliable visual landmarks that are easily recognizable and persistent. We propose a novel SLAM algorithm that focuses on learning and mapping such visual long-term landmarks (LLamas). The algorithm therefore processes stereo image streams from several recording sessions in the same spatial area. The key part within LLama-SLAM is the assessment of the landmarks with quality values that are inferred as viewpoint dependent probabilities from observation statistics. By adding solely landmarks of high quality to the final LLama Map, it can be kept compact while still allowing reliable localization. Due to the long-term evaluation of the GNSS measurement during the sessions, the landmarks can be positioned precisely in a global referenced coordinate system. For a first assessment of the algorithm's capabilities, we present some experimental results from the mapping process combining three sessions recorded over two months on the same route.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2019
Autor(en): Luthardt, Stefan ; Willert, Volker ; Adamy, Jürgen
Art des Eintrags: Zweitveröffentlichung
Titel: LLama-SLAM: Learning High-Quality Visual Landmarks for Long-Term Mapping and Localization
Sprache: Englisch
Publikationsjahr: 16 Januar 2019
Ort: Darmstadt
Publikationsdatum der Erstveröffentlichung: 2018
Verlag: IEEE
Veranstaltungstitel: 2018 21st International Conference on Intelligent Transportation Systems (ITSC)
Veranstaltungsort: Maui, Hawaii, USA
Veranstaltungsdatum: 04.11. - 07.11.2018
URL / URN: https://tuprints.ulb.tu-darmstadt.de/8357
Zugehörige Links:
Kurzbeschreibung (Abstract):

The precise localization of vehicles is an important requirement for autonomous driving or advanced driver assistance systems. Using common GNSS the ego position can be measured but not with the reliability and precision necessary. An alternative approach to achieve precise localization is the usage of visual landmarks observed by a camera mounted in the vehicle. However, this raises the necessity of reliable visual landmarks that are easily recognizable and persistent. We propose a novel SLAM algorithm that focuses on learning and mapping such visual long-term landmarks (LLamas). The algorithm therefore processes stereo image streams from several recording sessions in the same spatial area. The key part within LLama-SLAM is the assessment of the landmarks with quality values that are inferred as viewpoint dependent probabilities from observation statistics. By adding solely landmarks of high quality to the final LLama Map, it can be kept compact while still allowing reliable localization. Due to the long-term evaluation of the GNSS measurement during the sessions, the landmarks can be positioned precisely in a global referenced coordinate system. For a first assessment of the algorithm's capabilities, we present some experimental results from the mapping process combining three sessions recorded over two months on the same route.

Status: Postprint
URN: urn:nbn:de:tuda-tuprints-83575
Sachgruppe der Dewey Dezimalklassifikatin (DDC): 600 Technik, Medizin, angewandte Wissenschaften > 600 Technik
600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau
Fachbereich(e)/-gebiet(e): 18 Fachbereich Elektrotechnik und Informationstechnik
18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Automatisierungstechnik und Mechatronik
18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Automatisierungstechnik und Mechatronik > Regelungsmethoden und Robotik (ab 01.08.2022 umbenannt in Regelungsmethoden und Intelligente Systeme)
Hinterlegungsdatum: 20 Jun 2024 16:32
Letzte Änderung: 20 Jun 2024 16:32
PPN: 442892616
Export:
Suche nach Titel in: TUfind oder in Google

Verfügbare Versionen dieses Eintrags

Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen