Training-Free Semantic Labeling of Mobile LiDAR Using Vector HD Maps for Driving Simulation
ISPRS International Journal of Geo-Information · 09.11.2026 · 15 (11) · 503
DOI: 10.3390/ijgi15110503 ↗Kurz gefasst
Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 09.11.2026. Verfasst von Eun-Joo Suk und 3 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Agency for Infrastructure Technology Advancement.
Abstract (Originalsprache)
Driving simulation needs labeled 3D scenes, but mobile mapping system (MMS) light detection and ranging (LiDAR) is often delivered unclassified, without point-wise labels for training. We present a training-free pipeline that transfers the semantics of a vector high-definition (HD) map, the Korean precision road map, onto MMS LiDAR and outputs a labeled 0.5 m voxel scene, and we analyze what limits its accuracy. Each voxel takes the label of the nearest map feature whose category-specific radius and elevation window it satisfies, with elevations measured from a ground model built from the map’s 3D vertices. The pipeline needs no training data but requires a 3D vector map. On an expressway interchange, the ground model reached a median error of 6.6 cm, on par with inverse-distance weighting (IDW), triangulated irregular network (TIN), and local-plane interpolation. A blind, stratified random sample of 695 cells and a blind review of all 91 output objects showed that 98.0% [95.8, 99.5] of the output voxels are static solid structure and 73% [63, 81] of the objects are the mapped facility; the cell-level macro-F1 over six categories was 0.44 [0.39, 0.52] (guardrail 0.73, tunnel 0.94, sign 0.14). Errors were concentrated: four tunnel-mounted signals labeled the tunnel ceiling, and the radii of signs and posts captured roadside vegetation. The results show where map-based labels are reliable for simulation and which map content needs treatment.
Förderung
- Korea Agency for Infrastructure Technology Advancement
Zitieren
APA
Suk, E., Han, Y., We, G., & Moon, J. (2026). Training-Free Semantic Labeling of Mobile LiDAR Using Vector HD Maps for Driving Simulation. ISPRS International Journal of Geo-Information, 15(11), 503. https://doi.org/10.3390/ijgi15110503
Vancouver
Suk E, Han Y, We G, Moon J. Training-Free Semantic Labeling of Mobile LiDAR Using Vector HD Maps for Driving Simulation. ISPRS International Journal of Geo-Information. 2026;15(11):503. doi:10.3390/ijgi15110503
BibTeX
@article{Suk2026,
author = {Suk, Eun-Joo and Han, Yo-Han and We, Gwang-Jae and Moon, Ju-Hwan},
title = {Training-Free Semantic Labeling of Mobile LiDAR Using Vector HD Maps for Driving Simulation},
journal = {ISPRS International Journal of Geo-Information},
year = {2026},
volume = {15},
number = {11},
pages = {503},
doi = {10.3390/ijgi15110503}
}
EUVIMED