EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Plane Segmentation in Sensor-Acquired 3D Point Clouds Using Supervoxel-Based Geometric Constraints

Xiaohua Ran, Xu Ning, Qing An iD, Xijiang Chen iD

Sensors · 13.03.2026 · 26 (6) · 1816

DOI: 10.3390/s26061816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.03.2026. Verfasst von Xiaohua Ran und 3 weiteren Autor:innen. Beteiligte Einrichtung: East China Branch of Gezhouba Group, Shanghai 201100, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hubei Engineering Research Center for BDS-Cloud High-Precision Deformation Monitoring Open Funding.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Plane segmentation of real-world 3D point clouds captured by LiDAR or depth sensors remains challenging due to data sparsity, noise, and complex geometric configurations such as stepwise and intersecting non-coplanar structures. To address these issues inherent in sensor-acquired data, this paper proposes a geometry-aware plane segmentation method that leverages supervoxel boundary adjacency, normal coherence, and projection-line fitting constraints. Supervoxels were generated using the toward better boundary preserved supervoxel segmentation (TBBS) algorithm, and their natural adjacency relationships were constructed based on boundary points. Subsequently, the supervoxels were initially clustered according to their normal information. Finally, the projected point clouds of adjacent supervoxel were fitted with straight lines, and the fitting errors were calculated to optimize the clustering results. Experimental results demonstrate that this method performs excellently in handling stepwise non-coplanar structures, effectively segmenting planar regions with significant geometric features. It shows particular advantages in cases involving stepwise non-coplanar and intersecting planes. On benchmark datasets, the method achieves precision and recall rates of (97.7%, 94.4%, 91.2%, 80.4%, 92.3%) and (98.9%, 95.7%, 93.7%, 84.8%, 96.0%), respectively, highlighting its effectiveness and robustness for practical 3D sensing applications.

Schlagwörter

Stichwörter der Autor:innen

plane segmentationprojection line fittingsupervoxel adjacency relationship

Autor:innen und Institutionen

  • East China Branch of Gezhouba Group, Shanghai 201100, China.
  • School of Safety Science and Emergency Management, Wuhan University of Technology, Wuhan 430070, China.
  • School of Artificial Intelligence, Wuchang University of Technology, Wuhan 430223, China.

ORCID-Profile: Qing An, Xijiang Chen

Förderung

  • National Natural Science Foundation of China
  • Hubei Engineering Research Center for BDS-Cloud High-Precision Deformation Monitoring Open Funding

Zitieren

APA

Ran, X., Ning, X., An, Q., & Chen, X. (2026). Plane Segmentation in Sensor-Acquired 3D Point Clouds Using Supervoxel-Based Geometric Constraints. Sensors, 26(6), 1816. https://doi.org/10.3390/s26061816

Vancouver

Ran X, Ning X, An Q, Chen X. Plane Segmentation in Sensor-Acquired 3D Point Clouds Using Supervoxel-Based Geometric Constraints. Sensors. 2026;26(6):1816. doi:10.3390/s26061816

BibTeX
@article{Ran2026,
  author = {Ran, Xiaohua and Ning, Xu and An, Qing and Chen, Xijiang},
  title = {Plane Segmentation in Sensor-Acquired 3D Point Clouds Using Supervoxel-Based Geometric Constraints},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {1816},
  doi = {10.3390/s26061816}
}
Kostenlos starten →