Abstract
In autonomous driving technology, vehicles use LiDAR to accomplish various tasks. Issues are that the point cloud collected by the LiDAR is too sparse and some objects are mutilated, which is a great challenge for tasks such as detection and recognition. It is necessary to merge multiple frames of point clouds with registration algorithm to make data complete and dense. Previous point cloud registration methods run slowly and have low accuracy when dealing with autopilot field point clouds. It is difficult to find the correspondence of different point clouds. While humans can easily find the exact corresponding through the visual information received by eyes, as it contains color and texture. The visual images acquired by optical cameras can simulate the human eyes well. Therefore, we propose to use visual image assisted point cloud registration. Firstly, we extract the keypoints of visual images, then we obtain their depth by depth completion algorithm and back-project them into 3D space as 3D keypoints. Finally, we screen 3D keypoint pairs by spatial structure similarity to estimate the rigid transformation parameters. After experiments, it is proved that our method achieves substantial improvement in both speed and accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, S., Liu, B., Feng, C., et al.: 3D Point cloud processing and learning for autonomous driving: impacting map creation, localization, and perception. IEEE Signal Process. Mag. 38(1), 68–86 (2021)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Yin, W., Liu, Y., Shen, C., et al.: Enforcing geometric constraints of virtual normal for depth prediction. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, South Korea, pp. 5684–5693 (2019)
He, K., Sun, J., Tang, X.: Guided image filtering. In: European Conference on Computer Vision, Crete, Greece, pp. 1–14 (2010)
Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. IEEE Trans. Pattern Anal. Mach. Intell. 13(4), 376–380 (1991)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, pp. 3354–3361 (2012)
Besl, P.J., Mckay, H.D.: A method for registration of 3-D shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14(2), 239–256 (1992)
Rusu, R.B., Blodow, N., Beetz, M.: Fast point feature histograms (FPFH) for 3D registration. In: IEEE International Conference on Robotics and Automation, Kobe, Japan, pp. 3212–3217 (2009)
Zhong, Y.: Intrinsic shape signatures: a shape descriptor for 3d object recognition. In: IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, Kyoto, Japan, pp. 689–696 (2009)
Chen, C.S., Hung, Y.P., Cheng, J.B.: RANSAC-based DARCES: a new approach to fast automatic registration of partially overlapping range images. IEEE Trans. Pattern Anal. Mach. Intell. 21(11), 1229–1234 (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Gao, Y., Ma, J., Wu, B., Zhang, T., Yang, Y. (2022). Point Clouds Registration Algorithm Based on Spatial Structure Similarity of Visual Keypoints. In: Pan, L., Cui, Z., Cai, J., Li, L. (eds) Bio-Inspired Computing: Theories and Applications. BIC-TA 2021. Communications in Computer and Information Science, vol 1566. Springer, Singapore. https://doi.org/10.1007/978-981-19-1253-5_1
Download citation
DOI: https://doi.org/10.1007/978-981-19-1253-5_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1252-8
Online ISBN: 978-981-19-1253-5
eBook Packages: Computer ScienceComputer Science (R0)