EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

6D Pose Estimation of Reflective and Textureless Object with Improved Accuracy through Multi-view Scanning Using Mobile and Stationary Cameras

Pung Kyu Lee, Seongwon Jang, Chang-Ju Kim, Gyuho Kim, Huitaek Yun

International Journal of Precision Engineering and Manufacturing · 2026-06 · 27 (6) · 2345-2362

DOI: 10.1007/s12541-026-01488-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Precision Engineering and Manufacturing, online erschienen am 09.04.2026. Verfasst von Pung Kyu Lee und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Advanced Institute of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

6D object pose estimation is an important component of robotic bin picking in cluttered space for autonomous manufacturing, with various methods being researched to improve its accuracy. However, single-depth camera systems struggle to achieve the millimeter-level precision required in manufacturing, and objects with reflective surfaces and low features further complicate pose estimation. This study proposes a technique that improves the accuracy of pose estimation at graspable objects by integrating and analyzing multi-view point clouds obtained from a stationary depth camera and a mobile RGB-D camera mounted on an end-effector of a manipulator. After retrieving pointcloud of the mostly graspable object by YOLOv8, multiple shots are taken as planned using the manipulator, then the pointclouds are merged and filtered using Random Sample Consensus (RANSAC) and Farthest Point Sampling (FPS) algorithm. The reconstructed pointcloud is compared to the reference to estimate the pose of the object. Experimental results demonstrate that the approach achieves a positional error of less than 2mm along the z-axis and an angular error below 2 degrees for reflective and textureless objects by utilizing twelve multi-view data than using single camera. This research presents a cost-effective and accurate 6D object pose estimation solution, highlighting its potential to contribute to high-precision automation systems in manufacturing.

Förderung

  • Korea Advanced Institute of Science and Technology

Zitieren

APA

Lee, P. K., Jang, S., Kim, C., Kim, G., & Yun, H. (2026). 6D Pose Estimation of Reflective and Textureless Object with Improved Accuracy through Multi-view Scanning Using Mobile and Stationary Cameras. International Journal of Precision Engineering and Manufacturing, 27(6), 2345-2362. https://doi.org/10.1007/s12541-026-01488-7

Vancouver

Lee PK, Jang S, Kim C, Kim G, Yun H. 6D Pose Estimation of Reflective and Textureless Object with Improved Accuracy through Multi-view Scanning Using Mobile and Stationary Cameras. International Journal of Precision Engineering and Manufacturing. 2026;27(6):2345-2362. doi:10.1007/s12541-026-01488-7

BibTeX
@article{Lee2026,
  author = {Lee, Pung Kyu and Jang, Seongwon and Kim, Chang-Ju and Kim, Gyuho and Yun, Huitaek},
  title = {6D Pose Estimation of Reflective and Textureless Object with Improved Accuracy through Multi-view Scanning Using Mobile and Stationary Cameras},
  journal = {International Journal of Precision Engineering and Manufacturing},
  year = {2026},
  volume = {27},
  number = {6},
  pages = {2345--2362},
  doi = {10.1007/s12541-026-01488-7}
}
Kostenlos starten →