EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PLY-SLAM: Semantic Visual SLAM Integrating Point–Line Features with YOLOv8-seg in Dynamic Scenes

Huan Mao, Jingwen Luo iD

Sensors · 07.06.2025 · 25 (12) · 3597

DOI: 10.3390/s25123597 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.06.2025. Verfasst von Huan Mao und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Yunnan Normal University, Kunming 650500, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Nature Science Foundation of China, 'Xingdian Talent Support Program' Youth Talent Special Project of Yunnan Province, Basic Research Program of Yunnan Province - Key Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In dynamic and low texture environments, traditional point-feature-based visual SLAM (vSLAM) often faces the challenges of poor robustness and low localization accuracy. To this end, this paper proposes a semantic vSLAM approach that fuses point-line features with YOLOv8-seg. First, we designed a high-performance 3D line-segment extraction method that determines the number of points to be sampled for each line-segment in terms of the length of the 2D line-segments extracted from the image, and back-projects these sampled points combined with the depth image to obtain the 3D point set of the line-segments. On this basis, accurate 3D line-segment fitting is realized in combination with the RANSAC algorithm. Subsequently, we introduce Delaunay triangulation to construct the geometric relationships between map points, detect dynamic feature points by matching changes in the topological structure of feature points in adjacent frames, and combine them with the instance labels provided by the YOLOv8-seg to accurately remove dynamic feature points. Finally, a loop-closure detection mechanism that fuses point–line features with instance-level matching is designed to calculate a normalized similarity score by combining the positional similarity of the instances, the scale similarity, and the spatial consistency of the static instances. A series of simulations and experiments demonstrate the superior performance of our method.

Schlagwörter

Stichwörter der Autor:innen

YOLOv8-segdynamic sceneloop-closure detectionpoint-line featuressemantic visual SLAM

Autor:innen und Institutionen

  • School of Information Science and Technology, Yunnan Normal University, Kunming 650500, China.
  • Engineering Research Center of Computer Vision and Intelligent Control Technology, Department of Education of Yunnan Province, Kunming 650500, China.

ORCID-Profile: Jingwen Luo

Förderung

  • National Nature Science Foundation of China
  • 'Xingdian Talent Support Program' Youth Talent Special Project of Yunnan Province
  • Basic Research Program of Yunnan Province - Key Project
  • ‘Xingdian Talent Support Program’ Youth Talent Special Project of Yunnan Province
  • Basic Research Program of Yunnan Province—Key Project

Zitieren

APA

Mao, H., & Luo, J. (2025). PLY-SLAM: Semantic Visual SLAM Integrating Point–Line Features with YOLOv8-seg in Dynamic Scenes. Sensors, 25(12), 3597. https://doi.org/10.3390/s25123597

Vancouver

Mao H, Luo J. PLY-SLAM: Semantic Visual SLAM Integrating Point–Line Features with YOLOv8-seg in Dynamic Scenes. Sensors. 2025;25(12):3597. doi:10.3390/s25123597

BibTeX
@article{Mao2025,
  author = {Mao, Huan and Luo, Jingwen},
  title = {PLY-SLAM: Semantic Visual SLAM Integrating Point–Line Features with YOLOv8-seg in Dynamic Scenes},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {12},
  pages = {3597},
  doi = {10.3390/s25123597}
}
Kostenlos starten →