Abstract
This paper proposes a feature extraction method for scattered point clouds. First, a clustering algorithm is used to divide point clouds into different regions that represent the original features. In each sub-region, we calculate the angles between the directed line segments from sampling points to the neighborhood points and set the angle threshold to identify edge feature points of uniform distribution. For the edge points of non-uniform distribution, we introduce the local neighborhood size as a discrete scale parameter for edge point detection, and then accurately identify and record the detected edge points. Then, according to the mean curvature of point clouds, the local feature weights of sampling points in the sub-region are calculated so that potential sharp feature points in a local area are detected. Finally, a minimum spanning tree of feature points is established to construct connected regions and generate feature point sets. A Bidirectional Principal Component Analysis (BD-PCA) search method is used to trim and break the small branches and multiline segments to generate feature curves. We carried out experiments on point cloud models with different densities to verify the effectiveness and superiority of our method. Results show that the edge features and sharp features are effectively extracted, and our method is not affected by the noise, neighborhood scale, or quality of sampling.
Similar content being viewed by others
References
Bazazian D, Casas JR, Ruiz-Hidalgo J (2017) Segmentatione-based multi-scale edge extraction to measure the persistence of features in unorganized point clouds. In: A international joint conference on computer vision, imaging and computer graphics theory and applications. 12th international joint conference on computer vision, imaging and computer graphics theory and applications. Porto, pp 317–325
Buchanan M (2007) The social atom: why the rich get richer, cheaters get caught, and your neighbor usually looks like you. Publishers Wkly 11(3):303–305
Elkhrachy I (2017) Feature extraction of laser scan data based on geometric properties. J Indian Soc Remote Sens 45(1):1–10
Fan J, Ma L, Sun A et al (2020) An approach for extracting curve profiles based on scanned point cloud. Measurement 149:107023
Feng Q (2013) Li zi qun suan fa ji qi gong ye ying yong (in Chinese). Science Press, Beijing
Fu S, Wu L (2019) Feature line extraction from point clouds based on geometric structure of point space. 3D Res 10(2):16
Gumhold S, Wang X, MacLeod R (2001) Feature extraction from point clouds. In: Proceedings of the 10th international meshing roundtable, pp 293–305
Hu J, Liu Z, Zhang P et al (2019) Feature extraction of scattered point clouds based on discrete Morse theory. Acta Opt Sin 39(6):0615002
Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: Proceedings of the IEEE international conference on neural networks, Piscataway, no 4, pp 1942–1948
Li Q, Huang X, Li S et al (2018) Feature extraction from point clouds for rigid aircraft part inspection using an improved Harris algorithm. Meas Sci Technol 29(11):115202
Lin HB, Wang W, Shao YC et al (2017) Feature extraction from unorganized point cloud based on analytical tensor voting. J Graph 38(02):137–143
Liu X, Jin C (2014) Feature line extraction from unorganized noisy point clouds. J Comput Inf Syst 10(8):3503–3510
Liu Y, Wang CY, Gao N et al (2017) Point cloud adaptive simplification of feature extraction. Opt Precis Eng 25(1):245–254
Min KP, Lee SJ, Lee KH (2012) Multi-scale tensor voting for feature extraction from unstructured point clouds. Graph Model 74(4):197–208
Ni H, Lin X, Ning X et al (2016) Edge detection and feature line tracing in 3D-point clouds by analyzing geometric properties of neighborhoods. Remote Sens 8(9):710
Nie J, Liu Y, Gao H et al (2015) Feature line detection from point cloud based on signed surface variation and region segmentation. J Comput-Aided Des Comput Graph 12:2332–2339
Pauly M, Keiser R, Gross M (2003) Multi-scale feature extraction on point-sampled surfaces. Comput Graph Forum 22(3):281–289
Shi Y, Eberhart RC (1998) A modified particle swarm optimizer. In: Proceedings of IEEE conference on evolutionary computation, Anchorage, pp 69–73
Wang Y, Feng H-Y, Delorme F-É et al (2013) An adaptive normal vector estimation method for scanned point clouds with sharp features. Comput Aided Des 45(11):1333–1348
Weber C, Hahmann S, Hagen H (2010) Sharp feature detection in point clouds. Shape Model Int Conf IEEE 2010:175–186
Xu J, Zhou M, Wu Z et al (2015) Robust surface segmentation and edge feature lines extraction from fractured fragments of relics. J Comput Des Eng 2(2):79–87
Zhang Y, Geng G, Wei X et al (2016) A statistical approach for extraction of feature lines from point clouds. Comput Graph 56:31–45
Zhang YH, Geng GH, Wei XR et al (2017) Feature extraction of point clouds using the DBSCAN clustering. Xi’an Dianzi Keji Daxue Xuebao/J Xidian Univ 44(2):114–120
Funding
This study was funded by the National Natural Science Foundation of China (Nos. 51,365,037 and 51,065,021).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix 1
The important parameters of FCM clustering algorithm are as follows: c is the number of clusters. Let the date set X is divided into c(2 ≤ c ≤ n) subsets. P = {p1, p2, ⋯, pc} is the clustering center of these subsets. μik is the membership degree of point. The parameter m is a weighting exponent that controls the level of cluster fuzziness. We can take m = 2 according to one previous work(Pal N R, Bezdek J C (1995) On cluster validity for the fuzzy c-means model. IEEE Transactions on Fuzzy Systems 3(3): 370–379). dik is the squared Euclidean distance, which is used to measure the distance between the feature vector xk of k object and the centerpi of cluster i. The objective function is denoted by Jm.
The following pseudo codes are the details.
Appendix 2
Rights and permissions
About this article
Cite this article
Wang, X., Chen, H. & Wu, L. Feature extraction of point clouds based on region clustering segmentation. Multimed Tools Appl 79, 11861–11889 (2020). https://doi.org/10.1007/s11042-019-08512-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08512-1