Cluster-Based Alignment of RGB Labels and LiDAR Point Clouds for Semantic Navigation of an Autonomous Rover
Received: 06 Oct 2026 Revised: 16 Oct 2026 Accepted: 23 Oct 2026
Published: 2026, vol. 30, issue 4, pp. 373–376
Abstract
We transfer hard labels from quantized RGB segmentation to LiDAR, aggregate them by geometric clusters, and refine them with an MRF using distance, normals, and curvature. RELLIS-3D mIoU on valid projections is 48.9%.
Keywords: semantic segmentation, autonomous rover, LiDAR, RGB image, U-Net, EfficientNet, quantization, DBSCAN, Markov random field, alpha-expansion.
BibTeX
@article{IS-Lomovskii-Kumskov2026,
author = {Lomovskii, Roman Evgenievich and Kumskov, Mikhail Ivanovich},
title = {{Cluster-Based Alignment of RGB Labels and LiDAR Point Clouds for Semantic Navigation of an Autonomous Rover}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {373--376},
}
AMSBIB
\Bibitem{IS-Lomovskii-Kumskov2026}
\by R.\,E.~Lomovskii, M.\,I.~Kumskov
\paper Cluster-Based Alignment of RGB Labels and LiDAR Point Clouds for Semantic Navigation of an Autonomous Rover
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 373--376
\lang In Russian
Published under
Creative Commons Attribution 4.0 International (CC BY 4.0)
RU