Affiliation:
1. College of Artificial Intelligence, Nankai University, Tianjin 300071, China
2. School of Informatics, University of Edinburgh, Edinburgh EH8 9YL, UK
Abstract
Point cloud registration plays a crucial role in 3D mapping and localization. Urban scene point clouds pose significant challenges for registration due to their large data volume, similar scenarios, and dynamic objects. Estimating the location by instances (bulidings, traffic lights, etc.) in urban scenes is a more humanized matter. In this paper, we propose PCRMLP (point cloud registration MLP), a novel model for urban scene point cloud registration that achieves comparable registration performance to prior learning-based methods. Compared to previous works that focused on extracting features and estimating correspondence, PCRMLP estimates transformation implicitly from concrete instances. The key innovation lies in the instance-level urban scene representation method, which leverages semantic segmentation and density-based spatial clustering of applications with noise (DBSCAN) to generate instance descriptors, enabling robust feature extraction, dynamic object filtering, and logical transformation estimation. Then, a lightweight network consisting of Multilayer Perceptrons (MLPs) is employed to obtain transformation in an encoder–decoder manner. Experimental validation on the KITTI dataset demonstrates that PCRMLP achieves satisfactory coarse transformation estimates from instance descriptors within a remarkable time of 0.0028 s. With the incorporation of an ICP refinement module, our proposed method outperforms prior learning-based approaches, yielding a rotation error of 2.01° and a translation error of 1.58 m. The experimental results highlight PCRMLP’s potential for coarse registration of urban scene point clouds, thereby paving the way for its application in instance-level semantic mapping and localization.
Funder
National Natural Science Foundation of China
Shenzhen Natural Science Foundation
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference37 articles.
1. Yan, G., Luo, Z., Liu, Z., and Li, Y. (2023). SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios. arXiv.
2. Lcdnet: Deep loop closure detection and point cloud registration for lidar slam;Cattaneo;IEEE Trans. Robot.,2022
3. Jiang, B., and Shen, S. (2023). Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation. arXiv.
4. Optimal target shape for LiDAR pose estimation;Huang;IEEE Robot. Autom. Lett.,2021
5. Wu, C.Y., Johnson, J., Malik, J., Feichtenhofer, C., and Gkioxari, G. (2023). Multiview Compressive Coding for 3D Reconstruction. arXiv.