Moving Object Segmentation via 3D LiDAR Data: A Learning-Free Real-time Online Alternative

Zinuo Yi; Felix Neumann; Georg von Wichert; Darius Burschka

IROS 20250 citations

Moving Object Segmentation via 3D LiDAR Data: A Learning-Free Real-time Online Alternative

Zinuo Yi, Felix Neumann, Georg von Wichert, Darius Burschka

Abstract

Motion detection in 3D LiDAR is crucial for autonomous systems. While deep learning dominates Moving Object Segmentation (MOS), the potential of learning-free approaches remains underexplored. Unlike problems like semantic segmentation, motion can be explicitly modeled, potentially enabling efficient, interpretable, and computationally lightweight solutions. Motivated by this, we introduce a novel real-time, online, learning-free MOS method. We propose the novel Join Count Feature to extract motion cues from a local window of range images, and long-term filtering with efficient two-step association to enhance accuracy. Compared to learning-based models, we achieve superior precision and competitive IoU for saliently moving objects on SemanticKITTI. Further evaluation on HeLiMOS demonstrate stronger generalization by the proposed method across different LiDAR sensors. These results highlight the potential of learning-free methods for motion detection in 3D LiDAR data.

BibTeX

@inproceedings{iros2025_movingobjectsegm,
  title = {Moving Object Segmentation via 3D LiDAR Data: A Learning-Free Real-time Online Alternative},
  author = {Zinuo Yi and Felix Neumann and Georg von Wichert and Darius Burschka},
  booktitle = {IROS 2025},
  year = {2025}
}