SegFusion: Segmenting, Tracking, and Mapping of Multiple Unknown Moving Objects in Dynamic SLAM
IEEE Access · 2026 · 14 · 47453-47466
DOI: 10.1109/access.2026.3678119 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Yanming Wu und 1 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Creating dense, object-level 3D reconstructions of dynamic scenes is a key challenge in SLAM, enabling applications in robotics and augmented reality. To address this, we present SegFusion, a dynamic RGB-D SLAM system that jointly segments, tracks, and reconstructs previously unseen moving objects, while simultaneously mapping the static background. To achieve low-drift tracking, our framework combines sparse keypoint correspondences with dense geometric alignment in a pose graph optimization. For segmentation, we propose a hybrid strategy that uses motion inconsistency to prompt the Segment Anything Model (SAM), enabling accurate, category-agnostic instance masks. Temporal consistency is ensured through XMem, a long-term video object segmentation network. Unlike prior dense systems that depend on predefined semantic classes, SegFusion requires no prior knowledge of object categories. Evaluations on three public dynamic SLAM benchmarks demonstrate that SegFusion achieves strong tracking accuracy, segmentation quality, and reconstruction accuracy compared to existing dynamic object-level SLAM methods.
Zitieren
APA
Wu, Y., & Demeester, E. (2026). SegFusion: Segmenting, Tracking, and Mapping of Multiple Unknown Moving Objects in Dynamic SLAM. IEEE Access, 14, 47453-47466. https://doi.org/10.1109/access.2026.3678119
Vancouver
Wu Y, Demeester E. SegFusion: Segmenting, Tracking, and Mapping of Multiple Unknown Moving Objects in Dynamic SLAM. IEEE Access. 2026;14:47453-47466. doi:10.1109/access.2026.3678119
BibTeX
@article{Wu2026,
author = {Wu, Yanming and Demeester, Eric},
title = {SegFusion: Segmenting, Tracking, and Mapping of Multiple Unknown Moving Objects in Dynamic SLAM},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {47453--47466},
doi = {10.1109/access.2026.3678119}
}
EUVIMED