Three-Dimensional Point Cloud Registration Based on Normal Vector Angle
The widespread use of three-dimensional laser scanning makes point cloud registration essential for model reconstruction. Although iterative closest point (ICP) is a widely used algorithm for automatic and accurate point cloud registration, the ICP algorithm is time-intensive and typically falls in local optima. We employ the normal vector angle of the 3D model and integrate a heuristic search into the ICP algorithm to improve its efficiency, especially while registering complex surfaces. We compare this improved ICP algorithm with the original ICP algorithm and variants of the algorithm in terms of convergence, robustness, and response from a poor initial cloud point position to verify that the proposed improvements outperform the conventional ICP algorithm in the three evaluated aspects when processing point clouds with complex surfaces.
Keywords3D laser scanning Point cloud Fine registration Iterative closest point (ICP)
The authors gratefully acknowledge the financial support from the National Natural Science Foundation of China (Grant No. 51504239).
- Chen, Y., & Medioni, G. (1991). Object modeling by registration of multiple range images. In IEEE international conference on robotics and automation, 1991. Proceedings (pp. 145–155). IEEE.Google Scholar
- Chen, X., Zhang, G., & Hua, X. (2015). Point cloud simplification based on the information entropy of normal vector angle. Chinese Journal of Lasers, 08, 336–344.Google Scholar
- Dorigo, M. (1992). Optimization, learning and natural algorithms. Thesis Politecnico Di Milano Italy.Google Scholar
- Fitzgibbon, A. W. (2015). Robust registration of 2D and 3D point sets. Image and Vision Computing, 21(s 13–14), 1145–1153.Google Scholar
- Gelfand, N., Rusinkiewicz, S., Ikemoto, L., et al. (2003). Geometrically stable sampling for the ICP algorithm. In International conference on 3-D digital imaging and modeling, 2003. 3DIM 2003. Proceedings (pp. 260–267). IEEE.Google Scholar
- Jost, T., & Heinz, H. (2003). A multi-resolution ICP with heuristic closest point search for fast and robust 3D registration of range images. In IEEE conference on 3D imaging and modeling (pp. 427–433).Google Scholar
- Mitra, N. J., Gelfand, N., Pottmann, H., et al. (2004). Registration of point cloud data from a geometric optimization perspective. In Proceedings of the 2004 Eurographics/ACM SIGGRAPH symposium on geometry processing (pp. 22–31). ACM.Google Scholar
- Moravec, H. P. (1977). Towards automatic visual obstacle avoidance. In International joint conference on artificial intelligence (pp. 584–584).Google Scholar
- Pauly, M., Mitra, N. J., Giesen, J., et al. (2005). Example-based 3D scan completion. In Symposium on geometry processing (pp. 23–32).Google Scholar
- Pulli, K. (1999). Multiview registration for large data sets. In International conference on 3-D digital imaging and modeling (pp. 160–168). IEEE Computer Society.Google Scholar
- Rusinkiewicz, S., & Levoy, M. (2001). Efficient variants of the ICP algorithm. In 3DIM (p. 145). IEEE Computer Society.Google Scholar
- Zeng, F. X., Li, L., & Diao, X. P. (2017). Iterative closest point algorithm registration based on curvature features. Laser & Optoelectronics Progress, 54(1), 107–114. (in Chinese).Google Scholar