MOT-Assisted Object-Level Point Cloud Extraction from Multi-View Observations
Sensors · 07.08.2026 · 26 (16) · 5032
DOI: 10.3390/s26165032 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 07.08.2026. Verfasst von Cheng Ju und 4 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Engineering, Chiba University, 1-33 Yayoicho, Inage-ku, Chiba 263-8522, Japan. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Science and Technology Agency, Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Object-level point cloud extraction is relevant to robotic perception and may provide useful object-centric observations for mapping and SLAM. Many existing methods rely on per-frame instance segmentation, resulting in high computational cost and limited ability to extract multiple objects simultaneously in multi-object scenarios. This paper proposes an efficient MOT-assisted pipeline for multi-view object point cloud extraction. The pipeline first employs 2D multi-object tracking (MOT) to establish consistent object correspondences across views, and then combines monocular depth-based reconstruction with multi-view geometric association to estimate coarse object locations. An adaptive spherical proposal and a density-based refinement strategy are further introduced to extract clean object-specific point clouds while suppressing background noise and outliers. Experiments on the DTU, MVImgNet, and ScanNet++ datasets demonstrate the effectiveness of the proposed method. Relative to the unprocessed scene-level point cloud, the Chamfer Distance is reduced from 90.97 mm to 12.52 mm and Precision increases from 0.2998 to 0.8776 on DTU dataset Sequence 30. On MVImgNet, the Chamfer Distance decreases from 1.23 m to 0.46 m and Precision increases from 0.4777 to 0.9337, demonstrating effective removal of non-target scene points under real-world viewing conditions. Moreover, the proposed method reduces the cost of object-level association and provides competitive object-level extraction quality under the tested settings. Compared with the closely matched segmentation-based extraction, the proposed method provides lower measured object extraction runtime and built-in cross-view Track-ID association, while sacrificing some boundary accuracy.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Engineering, Chiba University, 1-33 Yayoicho, Inage-ku, Chiba 263-8522, Japan.
ORCID-Profile: Cheng Ju, Zejing Zhao, Chaowen Shen, Xuantong Li, Akio Namiki
Förderung
- Japan Science and Technology Agency
- Japan Society for the Promotion of Science
Zitieren
APA
Ju, C., Zhao, Z., Shen, C., Li, X., & Namiki, A. (2026). MOT-Assisted Object-Level Point Cloud Extraction from Multi-View Observations. Sensors, 26(16), 5032. https://doi.org/10.3390/s26165032
Vancouver
Ju C, Zhao Z, Shen C, Li X, Namiki A. MOT-Assisted Object-Level Point Cloud Extraction from Multi-View Observations. Sensors. 2026;26(16):5032. doi:10.3390/s26165032
BibTeX
@article{Ju2026,
author = {Ju, Cheng and Zhao, Zejing and Shen, Chaowen and Li, Xuantong and Namiki, Akio},
title = {MOT-Assisted Object-Level Point Cloud Extraction from Multi-View Observations},
journal = {Sensors},
year = {2026},
volume = {26},
number = {16},
pages = {5032},
doi = {10.3390/s26165032}
}
EUVIMED