Monocular Ground Normal Prediction for the Road Ahead
IEEE Open Journal of Vehicular Technology · 2026 · 7 · 1066-1080
DOI: 10.1109/ojvt.2026.3676610 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Open Journal of Vehicular Technology, 2026. Verfasst von Norbert Markó und 3 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research, Development and Innovation Office, National Defense Cooperative Doctoral Program, European Union within the Framework of the National Laboratory for Autonomous Systems.
Abstract (Originalsprache)
Robust fusion of monocular and inertial data has the potential to offer a low-cost alternative for ground surface normal prediction ahead, compared to more expensive sensors, such as LiDAR. Yet robust camera-based prediction remains challenging, particularly for steep grades and texture-poor, homogeneous road surfaces. To address these issues, we propose an enhanced monocular camera-IMU fusion pipeline incorporating a lightweight transformer-based feature matcher for improved correspondence accuracy, and robust temporal filtering, using a spherical linear interpolation (SLERP) filter, to enhance consistency and reduce drift. To enable rigorous benchmarking and reproducibility, we also standardize the evaluation protocol and release a novel dataset containing synchronized camera, LiDAR, and IMU-derived pose data, specifically captured across diverse incline and decline scenarios. Extensive continuous validation demonstrates that our method significantly improves both accuracy and temporal stability over existing approaches, setting a new state of the art for robust, continuous ground normal estimation ahead.
Förderung
- National Research, Development and Innovation Office
- National Defense Cooperative Doctoral Program
- European Union within the Framework of the National Laboratory for Autonomous Systems
- Ministry of Culture and Innovation of Hungary from the National Research
- Development and Innovation
- János Bolyai Research Scholarship of the Hungarian Academy of Sciences
Zitieren
APA
Markó, N., Rózsa, Z., Ballagi, Á., & Szirányi, T. (2026). Monocular Ground Normal Prediction for the Road Ahead. IEEE Open Journal of Vehicular Technology, 7, 1066-1080. https://doi.org/10.1109/ojvt.2026.3676610
Vancouver
Markó N, Rózsa Z, Ballagi Á, Szirányi T. Monocular Ground Normal Prediction for the Road Ahead. IEEE Open Journal of Vehicular Technology. 2026;7:1066-1080. doi:10.1109/ojvt.2026.3676610
BibTeX
@article{Mark2026,
author = {Markó, Norbert and Rózsa, Zoltán and Ballagi, Áron and Szirányi, Tamás},
title = {Monocular Ground Normal Prediction for the Road Ahead},
journal = {IEEE Open Journal of Vehicular Technology},
year = {2026},
volume = {7},
pages = {1066--1080},
doi = {10.1109/ojvt.2026.3676610}
}
EUVIMED