EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mask-Guided Frequency-Aware Sparse Elevation Map Completion for Off-Road Vehicle Terrain Perception

Lu Zhang, Yuchen Zhang, Fei Gao, Yuhang Zhang, Chao Li, Xi Li

Vehicles · 04.11.2026 · 8 (11) · 289

DOI: 10.3390/vehicles8110289 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Vehicles, online erschienen am 04.11.2026. Verfasst von Lu Zhang und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Inner Mongolia Autonomous Region, Natural Science Foundation of Inner Mongolia, Inner Mongolia Autonomous Region Science and Technology Plan Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sparse sampling and occlusion limit geometric analysis of LiDAR-derived elevation maps. This study proposes MGFE-Net, a mask-guided and frequency-aware network for elevation-map completion. The method combines elevation, an observation mask, selected-return count, and height variance to represent surface geometry, measurement support, and height dispersion. A pooling-based enhancement module integrates coarse contextual features with learned residual details within a U-Net-like encoder–decoder, while mask-based backfilling retains observed input elevations. Experiments use spatially separated training, validation, and test regions of RELLIS-3D sequence 00000, with exclusion gaps and disjoint source frames. Four network variants are trained from scratch using three random seeds and evaluated against temporally screened multi-frame reference surfaces. MGFE-Net achieves a root mean square error of 0.1593 ± 0.0056 m and a gradient error of 0.1427 ± 0.0024 m/m, reducing the Base U-Net means by 6.77% and 7.95%, respectively. The completed maps increase the computability of slope, step height, and surface roughness, and result in lower mean reference-based feature errors among the evaluated variants. However, exploratory risk evaluation still identifies false-low classifications and spurious connections. These findings support improved reconstruction within the tested spatial split and reference protocol, while broader generalization and safe vehicle traversability remain unverified.

Förderung

  • Department of Science and Technology of Inner Mongolia Autonomous Region
  • Natural Science Foundation of Inner Mongolia
  • Inner Mongolia Autonomous Region Science and Technology Plan Project

Zitieren

APA

Zhang, L., Zhang, Y., Gao, F., Zhang, Y., Li, C., & Li, X. (2026). Mask-Guided Frequency-Aware Sparse Elevation Map Completion for Off-Road Vehicle Terrain Perception. Vehicles, 8(11), 289. https://doi.org/10.3390/vehicles8110289

Vancouver

Zhang L, Zhang Y, Gao F, Zhang Y, Li C, Li X. Mask-Guided Frequency-Aware Sparse Elevation Map Completion for Off-Road Vehicle Terrain Perception. Vehicles. 2026;8(11):289. doi:10.3390/vehicles8110289

BibTeX
@article{Zhang2026,
  author = {Zhang, Lu and Zhang, Yuchen and Gao, Fei and Zhang, Yuhang and Li, Chao and Li, Xi},
  title = {Mask-Guided Frequency-Aware Sparse Elevation Map Completion for Off-Road Vehicle Terrain Perception},
  journal = {Vehicles},
  year = {2026},
  volume = {8},
  number = {11},
  pages = {289},
  doi = {10.3390/vehicles8110289}
}
Kostenlos starten →