Abstract
3D scanning devices are traditionally employed in reverse engineering tasks that can be carried out semi-automatically, with user assistance. However, their application in manufacturing process control requires automatic point cloud segmentation and extraction of geometric primitives. In this paper, we propose a method for automatic recognition of planes and cylinders (most frequently encountered geometric primitives in mechanical engineering) from unstructured point clouds. The method is based on the scatter of data during least squares fitting of second order surfaces. It consists of three phases and the first phase represents automatic point cloud segmentation. The second phase deals with merging of over-segmented regions and surfaces parameters estimation, whereas the final phase provides extraction of recognized geometric primitives. The method is experimentally verified using three real-world case studies, and its performances are compared with two state of the art recognition algorithms. The results have shown that the proposed method outperforms alternative approaches in terms of appropriately recognized planes and cylinders without surface type confusion, as well as when the recognition of non-existent primitives is considered. In addition, the method determines surfaces parameters with high accuracy.
Similar content being viewed by others
Notes
It should be noted that in the focus of our research is the method for geometric primitives recognition and not the design of scanning devices.
Plane, open b-spline, cone, cylinder, sphere, other, revolution, extrusion, closed b-spline and torus are considered.
Note that the code does not include parameters estimation.
References
Chen, M., Tang, Y., Zou, X., Huang, K., Li, L., He, Y.: High-accuracy multi-camera reconstruction enhanced by adaptive point cloud correction algorithm. Opt. Lasers Eng. 122, 170–183 (2019)
Li, C., Wang, S., Zhuang, Y., Yan, F.: Deep sensor fusion between 2D laser scanner and IMU for mobile robot localization. IEEE Sens. J. 21, 8501–8509 (2019)
Liu, Y., Tian, X.: Robot path planning with two-axis positioner for non-ideal sphere-pipe joint welding based on laser scanning. Int. J. Adv. Manuf. Technol. 105(1), 1295–1310 (2019)
Yan, M., Zhang, K., Liu, D., Yang, H., Li, Z.: Autonomous programming and adaptive filling of lap joint based on three-dimensional welding-seam model by laser scanning. J. Manuf. Process. 53, 396–405 (2020)
Hwang, S., An, Y.K., Yang, J., Sohn, H.: Remote inspection of internal delamination in wind turbine blades using continuous line laser scanning thermography. Int. J. Precis. Eng. Manuf. Green Technol. 7, 1–14 (2020)
Wang, W., Cai, Y., Wang, H.P., Carlson, B.E., Poss, M.: Quality inspection scheme for automotive laser braze joints. Int. J. Adv. Manuf. Technol. 106(3), 1553–1566 (2020)
Khalid, M.U., Hager, J.M., Kraus, W., Huber, M.F., Toussaint, M.: Deep workpiece region segmentation for bin picking. In: 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), pp. 1138–1144. IEEE (2019)
Tang, Y., Chen, M., Lin, Y., Huang, X., Huang, K., He, Y., Li, L.: Vision-based three-dimensional reconstruction and monitoring of large-scale steel tubular structures. Adv. Civ. Eng. 2020, 1236021 (2020)
Tang, Y., Li, L., Wang, C., Chen, M., Feng, W., Zou, X., Huang, K.: Real-time detection of surface deformation and strain in recycled aggregate concrete-filled steel tubular columns via four-ocular vision. Robot. Comput. Integr. Manuf. 59, 36–46 (2019)
Tang, Y.C., Wang, C., Luo, L., Zou, X., et al.: Recognition and localization methods for vision-based fruit picking robots: a review. Front. Plant Sci. 11, 510 (2020)
Chen, M., Tang, Y., Zou, X., Huang, K., Huang, Z., Zhou, H., Wang, C., Lian, G.: Three-dimensional perception of orchard banana central stock enhanced by adaptive multi-vision technology. Comput. Electron. Agric. 174, 105508 (2020)
Rabbani, T., Heuvel, F., Vosselman, G.: Segmentation of point clouds using smoothness constraint. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 36, 248–253 (2006)
Tsuchie, S.: Reconstruction of adaptive swept surfaces from scanned data for styling design. Vis. Comput. (2021). https://doi.org/10.1007/s00371-020-02030-0
Markovic, V., Jakovljevic, Z., Miljkovic, Z.: Feature sensitive three-dimensional point cloud simplification using support vector regression. Tehnicki Vjesnik 26(4), 985–994 (2019)
Schnabel, R., Wahl, R., Klein, R.: Efficient RANSAC for point-cloud shape detection. Comput. Graph. Forum 26(2), 214–226 (2007)
Tran, T.T., Cao, V.T., Laurendeau, D.: Extraction of reliable primitives from unorganized point clouds. 3D Research 6(4), 44 (2015)
Jakovljevic, Z., Puzovic, R., Pajic, M.: Recognition of planar segments in point cloud based on wavelet transform. IEEE Trans. Ind. Inform. 11(2), 342–352 (2015)
Vieira, M., Shimada, K.: Surface mesh segmentation and smooth surface extraction through region growing. Comput. Aided Geom. Des. 22(8), 771–792 (2005)
Angelo, L.D., Stefano, P.D.: Geometric segmentation of 3D scanned surfaces. Comput. Aided Des. 62, 44–56 (2015)
Angelo, L.D., Stefano, P.D., Morabito, A.: Fillets, rounds, grooves and sharp edges segmentation from 3D scanned surfaces. Comput. Aided Des. 110, 78–91 (2019)
Lai, H.C., Chang, Y.H., Lai, J.Y.: Development of feature segmentation algorithms for quadratic surfaces. Adv. Eng. Softw. 40(10), 1011–1022 (2009)
Wang, J., Gu, D., Yu, Z., Tan, C., Zhou, L.: A framework for 3D model reconstruction in reverse engineering. Comput. Ind. Eng. 63(4), 1189–1200 (2012)
Attene, M., Falcidieno, B., Spagnuolo, M.: Hierarchical mesh segmentation based on fitting primitives. Vis. Comput. 22(3), 181–193 (2006)
Rabbani, T., Heuvel, F.: Efficient Hough transform for automatic detection of cylinders in point clouds. In: Proceedings of ISPRS Workshop Laser Scan 2005, ISPRS Archives, vol. 36 (2005)
Ogundana, O.O., Huntley, J.M., Coggrave, C.R., Burguete, R.L.: Automated detection of planes in 3-D point clouds using fast Hough transforms. Opt. Eng. 50(5), 1–12 (2011)
Ogundana, T., Coggrave, C.R., Burguete, R.L., Huntley, J.M.: Fast Hough transform for automated detection of spheres in three-dimensional point clouds. Opt. Eng. 46(5), 1–11 (2007)
Mukhopadhyay, P., Chaudhuri, B.B.: A survey of Hough transform. Pattern Recognit. 48(3), 993–1010 (2015)
Tran, T.T., Cao, V.T., Laurendeau, D.: Extraction of cylinders and estimation of their parameters from point clouds. Comput. Graph. 46, 345–357 (2015)
Tran, T.T., Cao, V.T., Laurendeau, D.: eSphere: extracting spheres from unorganized point clouds: how to extract multiple spheres accurately and simultaneously. Vis. Comput. 32(10), 1205–1222 (2016)
Oh, I., Ko, K.: Automated recognition of 3D pipelines from point clouds. Vis. Comput. 37, 1385–1400 (2020)
Liu, Y., Zhang, J., Hou, J., Ren, J., Tang, W.: Cylinder detection in large-scale point cloud of pipeline plant. IEEE Trans. Vis. Comput. Graph. 19(10), 1700–1707 (2013)
Patil, A.K., Holi, P., Lee, S.K., Chai, Y.H.: An adaptive approach for the reconstruction and modeling of as-built 3D pipelines from point clouds. Autom. Constr. 75, 65–78 (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS-17, pp. 5105–5114. Curran Associates Inc., Red Hook (2017)
Morel, J., Bac, A., Kanai, T.: Segmentation of unbalanced and in-homogeneous point clouds and its application to 3D scanned trees. Vis. Comput. 36(10–12), 2419–2431 (2020)
Wang, J., Xu, C., Dai, L., Zhang, J., Zhong, R.Y.: An unequal learning approach for 3D point cloud segmentation. IEEE Trans. Ind. Inform. 17, 7913–7922 (2020)
Li, Y., Ma, L., Zhong, Z., Cao, D., Li, J.: Tgnet: geometric graph CNN on 3-D point cloud segmentation. IEEE Trans. Geosci. Remote Sens. 58(5), 3588–3600 (2020)
Xu, Y., Arai, S., Tokuda, F., Kosuge, K.: A convolutional neural network for point cloud instance segmentation in cluttered scene trained by synthetic data without color. IEEE Access 8, 70262–70269 (2020)
Nagy, B., Benedek, C.: 3D CNN-based semantic labeling approach for mobile laser scanning data. IEEE Sens. J. 19(21), 10034–10045 (2019)
Sharma, G., Liu, D., Maji, S., Kalogerakis, E., Chaudhuri, S., Měch, R.: ParSeNet: a parametric surface fitting network for 3D point clouds. In: European Conference on Computer Vision, pp. 261–276. Springer (2020)
Winiwarter, L., Mandlburger, G., Schmohl, S., Pfeifer, N.: Classification of ALS point clouds using end-to-end deep learnings. PFG J. Photogramm. Remote Sens. Geoinf. Sci. 87(3), 75–90 (2019)
Lalonde, J.F., Vandapel, N., Hebert, M.: Automatic three-dimensional point cloud processing for forest inventory. Tech. Rep. CMU-RI-TR-06-21, Carnegie Mellon University, Pittsburgh (2006)
Kwon, S.W., Bosche, F., Kim, C., Haas, C.T., Liapi, K.A.: Fitting range data to primitives for rapid local 3D modeling using sparse range point clouds. Autom. Constr. 13(1), 67–81 (2004)
Hubert, M., Rousseeuw, P.J., Branden, K.V.: ROBPCA: a new approach to robust principal component analysis. Technometrics 47(1), 64–79 (2005)
Nurunnabi, A., Sadahiro, Y., Lindenbergh, R.: Robust cylinder fitting in three-dimensional point cloud data. ISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. XLII–1/W1, 63–70 (2017)
do Carmo, M.: Differential Geometry of Curves and Surfaces. Prentice-Hall, Inc., Englewood Cliffs (1976)
Chaperon, T., Goulette, F.: Extracting cylinders in full 3D data using a random sampling method and the Gaussian image. In: Proceedings of the Vision Modeling and Visualization Conference, pp. 35–42 (2001)
Jakovljevic, Z., Markovic, V.: Recognition of one class quadric surfaces from unstructured point cloud. In: Proceedings of the 8th International Working Conference Total Quality Management—Advanced and Intelligent Approaches, pp. 353–360 (2015)
Jakovljevic, Z., Markovic, V.: Recognition of quadrics from 3D point clouds generated by scanning of rotational parts. J. Prod. Eng. 19(1), 65–68 (2016)
Jakovljevic, Z., Markovic, V., Puzovic, R., Majstorovic, V.: Recognition of one class of quadrics from 3D point clouds. Procedia CIRP 57, 292–297 (2016)
Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct least square fitting of ellipses. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 476–480 (1999)
Reza, A., Sengupta, A.S.: Least square ellipsoid fitting using iterative orthogonal transformations. Appl. Math. Comput. 314, 349–359 (2017)
Ying, X., Yang, L., Kong, J., Hou, Y., Guan, S., Zha, H.: Direct least square fitting of ellipsoids. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), pp. 3228–3231 (2012)
Al-sharadqah, A., Chernov, N.: Error analysis for circle fitting algorithms. Electron. J. Stat. 3, 886–911 (2009)
Xia, S., Chen, D., Wang, R., Li, J., Zhang, X.: Geometric primitives in LiDAR point clouds: a review. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 13, 685–707 (2020)
GOM GmbH: Atos compact scan—the compact class of scanning. http://www.gom.com/metrology-systems/system-overview/atos-compact-scan.html
Range Vision: Pro 3D scanner. https://rangevision.com/en/products/pro
Koch, S., Matveev, A., Jiang, Z., Williams, F., Artemov, A., Burnaev, E., Alexa, M., Zorin, D., Panozzo, D.: ABC: a big CAD model dataset for geometric deep learning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Petitjean, S.: A survey of methods for recovering quadrics in triangle meshes. ACM Comput. Surv. 34(2), 211–262 (2002)
Benkő, P., Martin, R.R., Várady, T.: Algorithms for reverse engineering boundary representation models. Comput. Aided Des. 33(11), 839–851 (2001)
CloudCompare: 3D point cloud and mesh processing software. https://www.danielgm.net/cc (2020)
Sharma, G., Liu, D., Kalogerakis, E., Maji, S., Chaudhuri, S., Měch, R.: ParSeNet: a parametric surface fitting network for 3D point clouds. https://github.com/Hippogriff/parsenet-codebase (2021)
Acknowledgements
This research was supported by the Science Fund of the Republic of Serbia, Grant No. 6523109, AI-MISSION4.0, 2020–2022, as well as by the Ministry of Education, Science and Technological Development of the Serbian Government, Grant No. 451-03-68/2020-14/200105.
Author information
Authors and Affiliations
Corresponding author
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
Markovic, V., Jakovljevic, Z. & Budak, I. Automatic recognition of cylinders and planes from unstructured point clouds. Vis Comput 38, 4329–4352 (2022). https://doi.org/10.1007/s00371-021-02299-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-021-02299-9