EUVIMEDEUVIMED entdecken
Crossref

OL-Reg: Registration of Image and Sparse LiDAR Point Cloud With Object-Level Dense Correspondences

Pei An, Xuzhong Hu, Junfeng Ding, Jun Zhang, Jie Ma, You Yang, Qiong Liu

IEEE Transactions on Circuits and Systems for Video Technology · 2024-08 · 34 (8) · 7523-7536

DOI: 10.1109/tcsvt.2024.3374723 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-08. Verfasst von Pei An und 6 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Equipment Pre-Research Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image and point cloud registration (2D-3D registration) is an essential prerequisite for multi-modal feature fusion. However, due to the significant feature difference of point cloud and image, it is challenging to establish 2D-3D correspondences. Targeting for the background of autonomous driving, we propose 2D-3D registration method with object-level correspondence (OL-Reg) in this paper. Object-level correspondence consists of object bounding box and object contour in 2D image and 3D space. The first step is to match 2D-3D objects. Due to sensor pose and field of view (FoV) difference, object shape and occlusion is different in image and point cloud, causing the difficulty of object matching. To solve this issue, we represent object as 3D bounding box, and design 2D-3D object matching with 3D box projection (Box-Proj) constraint. It aligns object 3D bounding box in image and point cloud. After that, the next step is to build 2D-3D correspondence from the matched objects. To extract correspondence from object with irregular shape, we notice the distance constraint of object surface and rays back-projected from object contour, and present projection based iterative closest point (Proj-ICP). Towards the stability of Proj-ICP, object-level regularization term is designed. Experiment is conducted in KITTI object and odometry dataset. With the pre-trained 3D object detector, results suggest that OL-Reg has the better performance than current approaches in tasks of re-localization and extrinsic calibration. Source code will be released at https://github.com/anpei96/ol-reg-demo.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Equipment Pre-Research Project
  • Major Project of Fundamental Research on Frontier Leading Technology of Jiangsu Province

Zitieren

APA

An, P., Hu, X., Ding, J., Zhang, J., Ma, J., Yang, Y., & Liu, Q. (2024). OL-Reg: Registration of Image and Sparse LiDAR Point Cloud With Object-Level Dense Correspondences. IEEE Transactions on Circuits and Systems for Video Technology, 34(8), 7523-7536. https://doi.org/10.1109/tcsvt.2024.3374723

Vancouver

An P, Hu X, Ding J, Zhang J, Ma J, Yang Y, et al. OL-Reg: Registration of Image and Sparse LiDAR Point Cloud With Object-Level Dense Correspondences. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(8):7523-7536. doi:10.1109/tcsvt.2024.3374723

BibTeX
@article{An2024,
  author = {An, Pei and Hu, Xuzhong and Ding, Junfeng and Zhang, Jun and Ma, Jie and Yang, You and Liu, Qiong},
  title = {OL-Reg: Registration of Image and Sparse LiDAR Point Cloud With Object-Level Dense Correspondences},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2024},
  volume = {34},
  number = {8},
  pages = {7523--7536},
  doi = {10.1109/tcsvt.2024.3374723}
}
Kostenlos starten →