Abstract
In order to improve the accuracy and rapidity of feature line extraction from point clouds, the work proposed a feature line extraction method based on geometric structure of point space. Firstly, a spatial grid dynamic division method is designed to locate the feature region of the model. A new feature points detection operator based on the linear intercept ratio is proposed according to the geometric information of points. Then, the feature points are refined by the Laplacian operator. Finally, the refined feature points are connected into the characteristic curve by the improved method of polyline growth. Compared with the feature points detection method based on surface variation (MSSV) or the angle of normal vector (SM-PD), the proposed method has low rate of error recognition with the increased noise intensity. Meanwhile, the computation time is 224.42 ms for the standard Armadillo model, less than 530.23 ms of the MSSV and 350.75 ms of the SM-PD. The experimental results show that the proposed method can accurately extract the feature points, with good noise immunity, especially suitable for the massive point cloud model.
Graphical Abstract
Similar content being viewed by others
References
Sirazitdinova, E., Jonas, S. M., Lensen, J., et al. (2016). Towards efficient mobile image-guided navigation through removal of outliers. EURASIP Journal on Image and Video Processing, 1, 43–53.
Lehment, N. K., et al. (2013). Using segmented 3D point clouds for accurate likelihood approximation in; human pose tracking. International Journal of Computer Vision, 101(3), 482–497.
Li, H., Huang, D., Morvan, J. M., et al. (2015). Towards 3D face recognition in the real: A registration-free approach using fine-grained matching of 3D Keypoint descriptors. International Journal of Computer Vision, 113(2), 128–142.
Gumhold, S., Wang, X., & Macleod, R. (2001). Feature extraction from point clouds. In Proceedings of 10IMR (pp. 293–305).
Pauly, M., Keiser, R., & Gross, M. (2010). Multi-scale feature extraction on point-sampled surfaces. In Computer graphics forum (pp. 281–289).
Min, K. P., Lee, S. J., & Lee, K. H. (2012). Multi-scale tensor voting for feature extraction from unstructured point clouds. Graphical Models, 74(4), 197–208.
Nie, J. H., Liu, Y., Gao, H., Wang, B., & Ge, Y. (2015). Feature line detection from point cloud based on signed surface variation and region segmentation. Journal of Computer-Aided Design and Computer Graphics., 27(12), 332–339.
Nie, J. (2016). Extracting feature lines from point clouds based on smooth shrink and iterative thinning. Graphical Models, 84, 38–49.
Ho, H. T., & Gibbins, D. (2009). Curvature-based approach for multi-scale feature extraction from 3D meshes and unstructured point clouds. Computer Vision Iet, 3(4), 201–212.
Wushour, S., & Cao, J. M. (2012). An extraction algorithm for sharp feature points from point clouds. Journal of Xi’an Jiaotong University, 46(12), 1–5.
Pang, X. F. (2010). An algorithm for extracting and enhancing valley-ridge features from point sets. Acta Automatica Sinica, 36(8), 1073–1083.
Liu, Y., Wang, C. Y., Gao, N., & Zhang, Z. (2017). Point cloud adaptive simplification of feature extraction. Optics and Precision Engineering, 25(1), 245–254.
Wang, L. H., & Yuan, B. Z. (2011). Feature point detection for 3D scattered point cloud model. Signal Process, 27(6), 932–938.
Zhang, Y. H., Geng, G., Wei, X., Su, H., & Zhou, M. (2016). Point clouds simplification with geometric feature reservation. Journal of Computer-Aided Design and Computer Graphics., 28(9), 1420–1427.
Zhang, Y., Geng, G., Wei, X., Zhang, S., & Li, S. (2016). A statistical approach for extraction of feature lines from point clouds. Computers & Graphics, 56, 31–45.
Fu, S. Y., Wu, L. S., & Chen, H. W. (2017). Point cloud simplification method based on grid dynamic partitioning. Acta Optica Sinica, 37(11), 11150071–11150079.
Lee, P. F., & Huang, C. P. (2011). The DSO feature based point cloud simplification. Eighth International Conference on Computer Graphics, Imaging and Visualization, CGIV, 2011, 1–6.
Wu, L.-S., Shi, H. L., & Chen, H. W. (2016). Denoising of three-dimensional point data based on classification of feature information. Optics and Precision Engineering, 24(6), 1465–1473.
Tian, J., Jiang, W., Luo, T., Cai, K., Peng, J., & Wang, W. (2012). Adaptive coding of generic 3d triangular meshes based on octree decomposition. The Visual Computer, 28(6–8), 819–827.
Yuan, X. C., Wu, L. S., & Chen, H. W. (2015). Feature preserving point cloud simplification. Optics and Precision Engineering., 23(9), 2666–2676.
Guo, Y., Wang, F., & Xin, J. (2017). Point-wise saliency detection on 3D point clouds via covariance descriptors. The Visual Computer, 3(2), 1–14.
Torrente, M. L., Biasotti, S., & Falcidieno, B. (2017). Recognition of feature curves on 3D shapes using an algebraic approach to Hough transforms. Pattern Recognition, 73, 111–130.
Daniels, J., Ha, L. K., Ochotta, T, & Silva, C. (2007). Robust smooth feature extraction from point clouds. In Shape modeling and applications (pp. 123–136).
Altantsetseg, E., Muraki, Y., Matsuyama, K., & Konno, K. (2013). Feature line extraction from unorganized noisy point clouds using truncated Fourier series. The Visual Computer, 29(6–8), 617–626.
Acknowledgements
Thank the anonymous reviewers for their comments and constructive suggestions. The Armadillo and Fandisk data were from The Stanford 3D Scanning Repository.
Funding
The work was funded by the National Natural Science Foundation of China through Projects (Grant Nos. 51065021, 51365037,and 51705229), and was supported in part by the Science and Technology Project of Jiangxi Education Department of China (GJJ181032).
Author information
Authors and Affiliations
Contributions
FSY conceived the original idea for the project and improved the algorithm; the first version of the paper is written by him. WLS confirmed the performance of the algorithm. All authors contributed to the helpful discussions and analyzed the results. Both authors read and approved the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare that they have no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fu, S., Wu, L. Feature Line Extraction from Point Clouds Based on Geometric Structure of Point Space. 3D Res 10, 16 (2019). https://doi.org/10.1007/s13319-019-0227-x
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13319-019-0227-x