EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EdgeDenseCalib: Targetless Camera–LiDAR Calibration via Enhanced Edge Feature Densification

Zhiyu He, Zhiwei Cao, Ning Xu, Zhipeng Zhao, Junyi Zhao, Zhao Sheng iD, Xiaoyu Zhao

Sensors · 26.04.2026 · 26 (9) · 2690

DOI: 10.3390/s26092690 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.04.2026. Verfasst von Zhiyu He und 6 weiteren Autor:innen. Beteiligte Einrichtung: Signal and Communication Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the State Key Laboratory of Advanced Rail Autonomous Operation, the Science and Technology Research Project of China Railway, State Key Laboratory of Advanced Rail Autonomous Operation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate camera–LiDAR calibration is a fundamental prerequisite for reliable perception in autonomous systems. However, traditional methods typically rely on manual intervention or specific calibration targets, which restrict their flexibility and scalability in dynamic, real-world environments. To address the challenge of targetless calibration, we propose EdgeDenseCalib, a novel approach driven by enhanced edge feature densification. A key innovation lies in a two-stage process designed to densify the inherently sparse edge features in LiDAR data, thereby making them highly comparable to the fine-grained edges present in images. Consequently, this facilitates more reliable feature matching between the two cross-modal data sources. An optimization algorithm is subsequently employed to refine the alignment and minimize the reprojection error. Experiments on the KITTI dataset show our method achieves accurate calibration results of 0.105° in mean rotation error and 0.903 cm in mean translation error. Compared to state-of-the-art edge-based methods, our approach significantly improves the rotation accuracy by 33.1% to 89.9%. This work provides a practical and automatic calibration solution, contributing to the development of more robust perception systems for autonomous applications.

Schlagwörter

Stichwörter der Autor:innen

camera–LiDAR calibrationdepth discontinuityedge feature enhancementextrinsic parameterssensor fusion

Autor:innen und Institutionen

  • Signal and Communication Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China.
  • State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing 100044, China.

ORCID-Profile: Zhao Sheng

Förderung

  • the State Key Laboratory of Advanced Rail Autonomous Operation
  • the Science and Technology Research Project of China Railway
  • State Key Laboratory of Advanced Rail Autonomous Operation
  • Science and Technology Research Project of China Railway

Zitieren

APA

He, Z., Cao, Z., Xu, N., Zhao, Z., Zhao, J., Sheng, Z., & Zhao, X. (2026). EdgeDenseCalib: Targetless Camera–LiDAR Calibration via Enhanced Edge Feature Densification. Sensors, 26(9), 2690. https://doi.org/10.3390/s26092690

Vancouver

He Z, Cao Z, Xu N, Zhao Z, Zhao J, Sheng Z, et al. EdgeDenseCalib: Targetless Camera–LiDAR Calibration via Enhanced Edge Feature Densification. Sensors. 2026;26(9):2690. doi:10.3390/s26092690

BibTeX
@article{He2026,
  author = {He, Zhiyu and Cao, Zhiwei and Xu, Ning and Zhao, Zhipeng and Zhao, Junyi and Sheng, Zhao and Zhao, Xiaoyu},
  title = {EdgeDenseCalib: Targetless Camera–LiDAR Calibration via Enhanced Edge Feature Densification},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2690},
  doi = {10.3390/s26092690}
}
Kostenlos starten →