Abstract
The efficiency and accuracy of point set registration is always a challenge to deal with. In this paper, we propose an improved algorithm using a scale invariant feature extracted. The larger transformation scale and rotation angle cause lower registration accuracy. The initial corresponding point set can be obtained using a scale invariant feature transform (SIFT) operator. In addition, the geometric features of the points are combined to remove the wrong points. The unit quaternion algorithm is used to estimate the best rigid body transformation matrix for precise registration. The experiments show that the registration accuracy increases by 7.99%, while the time consumption decreased by 6.24% in a typical indoor scene.
Similar content being viewed by others
References
B. Wu, B. Yu, Q. Wu, et al., Remote Sensing, 9, 92 (2017).
M. Yiming, W. Jianming, T. Tao, et al., Laser Optoelectron. Progr., 56, 105 (3019).
Y. Li, Y. Wang, and Y. Xie, Adv. Space Res., 63, 1576 (2019).
P. J. Besl and N. D. McKay, “Method for registration of 3D shapes,” in: Sensor Fusion IV: Control Paradigms and Data Structures, International Society for Optics and Photonics (1992), Vol. 1611, p. 586.
C. Zhang, S. Du, J. Liu, et al., Neurocomput., 195, 172 (2016).
F. Xin-Nan, G. U. Ya-Fei, and N. I. Jian-Jun, Comput. Modern., 02, 1 (2019).
S. Li, Y. He, Q. Li, et al., J. Russ. Laser Res., 39, 591 (2018).
B. Jian and B. C. Vemuri, “A robust algorithm for point set registration using mixture of Gaussians,” in: The 10th IEEE International Conference on Computer Vision (ICCV’05), IEEE Proc., 1(2), 1246 (2005).
S. Du, J. Liu, C. Zhang, et al., Neurocomput., 157, 187 (2015).
L. Zhao, X. Shen, and X. Long, Comput. Graph., 36, 577 (2012).
Q. P. Li, Trans-Scale Registration and Fusion for Motion Image From Multiple Sources, Beijing University of Posts and Telecommunications (2015).
D. Z. Cheng, Y. J. Li, and R. X. Yu, Comput. Sim., 28, 285 (2011).
D. G. Lowe, Int. J. Comput. Vision, 60, 91 (2004).
H. J. Tao and F. P. Da, Chin. J. Lasers, 40, 184 (2013).
Z. Teng and A. Zhang, Bull. Surv. Mapping, 11, 7 (2010).
X. Yang and H.Wang, Comput. Sim., 8, 235 (2010).
Y. Yongxing, W. Shudong, Z. Hao, et al., Geotech. Invest. Surv., 44, 55 (2016).
P. Biber and W. Straler, “The normal distributions transform: A new approach to laser scan matching,” in: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003), IEEE Proc., 3, 2743 (2003); Cat. No. 03CH37453.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hu, Q., Niu, J., Wang, Z. et al. Improved Point Cloud Registration with Scale Invariant Feature Extracted. J Russ Laser Res 42, 219–225 (2021). https://doi.org/10.1007/s10946-021-09953-6
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10946-021-09953-6