A Fast Point Clouds Registration Algorithm for Laser Scanners
Source abstract
Abstract
Point clouds registration is an important step for laser scanner data processing, and there have been numerous methods. However, the existing methods often suffer from low accuracy and low speed when registering large point clouds. To meet this challenge, an improved iterative closest point (ICP) algorithm combining random sample consensus (RANSAC) algorithm, intrinsic shape signatures (ISS), and 3D shape context (3DSC) is proposed. The proposed method firstly uses voxel grid filter for down-sampling. Next, the feature points are extracted by the ISS algorithm and described by the 3DSC. Afterwards, the ISS-3DSC features are used for rough registration with the RANSAC algorithm. Finally, the ICP algorithm is used for accurate registration. The experimental results show that the proposed algorithm has faster registration speed than the compared algorithms, while maintaining high registration accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Robotics and Sensor-Based Localization · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Center for Advanced Laser Technology, School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China
Hebei Key Laboratory of Advanced Laser Technology and Equipment, School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China
MQ Photonics Research Centre, Department of Physics and Astronomy, Macquarie University, Sydney, NSW 2109, Australia
Funding
National Natural Science Foundation of China · Natural Science Foundation of Hebei Province
References (22)
Show source-provided references
1. A method for registration of 3-D shapes10.1109/34.121791 ↗
2. Hong, S., Ko, H., and Kim, J. (2010, January 3–7). VICP: Velocity updating iterative closest point algorithm. Proceedings of the 2010 IEEE International Conference on Robotics and Automation, Anchorage, AK, USA.
3. Generalized-ICP
4. Yang, J., Li, H., and Jia, Y. (2013, January 1–8). Go-ICP: Solving 3D registration efficiently and globally optimally. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Australia.10.1109/ICCV.2013.184 ↗
5. Censi, A. (2008, January 19–23). An ICP variant using a point-to-line metric. Proceedings of the 2008 IEEE International Conference on Robotics and Automation, Pasadena, CA, USA.10.1109/ROBOT.2008.4543181 ↗
6. Scan registration for autonomous mining vehicles using 3D-NDT10.1002/rob.20204 ↗
7. Graph-matching-based correspondence search for nonrigid point cloud registration10.1016/j.cviu.2019.102899 ↗
8. Shui, W., and Zhou, M. (2010, January 23–25). An approach for model reconstruction based on multi-view scans registration. Proceedings of the 2010 International Conference on Audio, Language and Image Processing, Shanghai, China.10.1109/ICALIP.2010.5685033 ↗
9. Point cloud registration algorithm based on overlapping region extraction10.1088/1742-6596/1634/1/012012 ↗
10. Mohamad, M., Ahmed, M.T., Rappaport, D., and Greenspan, M. (2015, January 19–22). Super generalized 4PCS for 3D registration. Proceedings of the 2015 International Conference on 3D Vision, Lyon, France.10.1109/3DV.2015.74 ↗
11. He, Y., and Lee, C.-H. (2020, January 20–23). An improved ICP registration algorithm by combining PointNet++ and ICP algorithm. Proceedings of the 2020 6th International Conference on Control, Automation and Robotics (ICCAR), Singapore.10.1109/ICCAR49639.2020.9108032 ↗
12. Kamencay, P., Sinko, M., Hudec, R., Benco, M., and Radil, R. (2019, January 1–3). Improved feature point algorithm for 3D point cloud registration. Proceedings of the 2019 42nd International Conference on Telecommunications and Signal Processing (TSP), Budapest, Hungary.10.1109/TSP.2019.8769057 ↗
13. A local feature descriptor based on rotational volume for pairwise registration of point clouds10.1109/ACCESS.2020.2995369 ↗
14. Chen, L.C., Hoang, D.C., Lin, H.I., and Nguyen, T.H. (2016). Innovative methodology for multi-view point cloud registration in robotic 3D object scanning and reconstruction. Appl. Sci., 6.10.3390/app6050132 ↗
15. Automatic point cloud coarse registration using geometric keypoint descriptors for indoor scenes10.1016/j.autcon.2017.06.016 ↗
16. Zhong, Y. (October, January 27). Intrinsic shape signatures: A shape descriptor for 3D object recognition. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, Kyoto, Japan.10.1109/ICCVW.2009.5457637 ↗
17. Frome, A., Huber, D., Kolluri, R., Bülow, T., and Malik, J. (2004). Recognizing objects in range data using regional point descriptors. European Conference on Computer Vision, Springer.10.1007/978-3-540-24672-5_18 ↗
18. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography
19. Buch, A.G., Kraft, D., Kämäräinen, J.-K., Petersen, H.G., and Krüger, N. (2013, January 6–10). Pose estimation using local structure-specific shape and appearance context. Proceedings of the 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany.10.1109/ICRA.2013.6630856 ↗
20. Li, S., Wang, J., Liang, Z., and Su, L. (2016, January 10–15). Tree point clouds registration using an improved ICP algorithm based on kd-tree. Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.10.1109/IGARSS.2016.7730186 ↗
21. 3DHoPD: A fast low-dimensional 3-D descriptor10.1109/LRA.2017.2667721 ↗
22. Dynamic differential evolution algorithm applied in point cloud registration10.1088/1757-899X/428/1/012032 ↗