Supervoxel-based targetless registration and identification of stable areas for deformed point clouds
-
Yihui Yang
and
Volker Schwieger
Abstract
Accurate and robust 3D point cloud registration is the crucial part of the processing chain in terrestrial laser scanning (TLS)-based deformation monitoring that has been widely investigated in the last two decades. For the scenarios without signalized targets, however, automatic and robust point cloud registration becomes more challenging, especially when significant deformations and changes exist between the sequence of scans which may cause erroneous registrations. In this contribution, a fully automatic registration algorithm for point clouds with partially unstable areas is proposed, which does not require artificial targets or extracted feature points. In this method, coarsely registered point clouds are firstly over-segmented and represented by supervoxels based on the local consistency assumption of deformed objects. A confidence interval based on an approximate assumption of the stochastic model is considered to determine the local minimum detectable deformation for the identification of stable areas. The significantly deformed supervoxels between two scans can be detected progressively by an efficient iterative process, solely retaining the stable areas to be utilized for the fine registration. The proposed registration method is demonstrated on two datasets (both with two-epoch scans): An indoor scene simulated with different kinds of changes, including rigid body movement and shape deformation, and the Nesslrinna landslide close to Obergurgl, Austria. The experimental results show that the proposed algorithm exhibits a higher registration accuracy and thus a better detection of deformations in TLS point clouds compared with the existing voxel-based method and the variants of the iterative closest point (ICP) algorithm.
-
Author contributions: Yihui Yang: conceptualization, methodology, software, investigation, experiments, visualization, writing – original draft; Volker Schwieger: writing – review & editing, supervision.
-
Research funding: None declared.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
1. Holst, C, Kuhlmann, H. Challenges and present fields of action at laser scanner based deformation analyses. J Appl Geodes 2016;10:17–25. https://doi.org/10.1515/jag-2015-0025.Search in Google Scholar
2. Wunderlich, T, Niemeier, W, Wujanz, D, Holst, C, Neitzel, F, Kuhlmann, H. Areal deformation analysis from TLS point clouds—the challenge. Allg Vermessungs Nachrichten (AVN) 2016;123:340–51.Search in Google Scholar
3. Lague, D, Brodu, N, Leroux, J. Accurate 3D comparison of complex topography with terrestrial laser scanner: application to the Rangitikei canyon (NZ). ISPRS J Photogrammetry Remote Sens 2013;82:10–26. https://doi.org/10.1016/j.isprsjprs.2013.04.009.Search in Google Scholar
4. Holst, C, Janßen, J, Schmitz, B, Blome, M, Dercks, M, Schoch-Baumann, A, et al.. Increasing spatio-temporal resolution for monitoring alpine solifluction using terrestrial laser scanners and 3D vector fields. Rem Sens 2021;13:1192. https://doi.org/10.3390/rs13061192.Search in Google Scholar
5. Pfeiffer, J, Zieher, T, Bremer, M, Wichmann, V, Rutzinger, M. Derivation of three-dimensional displacement vectors from multi-temporal long-range terrestrial laser scanning at the Reissenschuh landslide (Tyrol, Austria). Rem Sens 2018;10:1688. https://doi.org/10.3390/rs10111688.Search in Google Scholar
6. Barbarella, M, Fiani, M, Lugli, A. Landslide monitoring using multitemporal terrestrial laser scanning for ground displacement analysis. Geomatics, Nat Hazards Risk 2015;6:398–418. https://doi.org/10.1080/19475705.2013.863808.Search in Google Scholar
7. Janßen, J, Kuhlmann, H, Holst, C. Target-based terrestrial laser scan registration extended by target orientation. J Appl Geodes 2022;16:91–106. https://doi.org/10.1515/jag-2020-0030.Search in Google Scholar
8. Wujanz, D. Terrestrial laser scanning for geodetic deformation monitoring [Ph.D. thesis]. Germany: Technische Universität Berlin; 2016.Search in Google Scholar
9. Friedli, E. Point cloud registration and mitigation of refraction effects for geomonitoring using long-range terrestrial laser scanning [Ph.D. thesis]. Switzerland: ETH Zurich; 2020.Search in Google Scholar
10. Vosselman, G, Maas, H-G. Airborne and terrestrial laser scanning. Boca Raton, FL, USA: CRC Press; 2010.Search in Google Scholar
11. Rusu, RB, Blodow, N, Beetz, M. Fast point feature histograms (FPFH) for 3D registration. In: Proceedings of 2009 IEEE international conference on robotics and automation (ICRA). Kobe, Japan; 2009.10.1109/ROBOT.2009.5152473Search in Google Scholar
12. Yang, B, Dong, Z, Liang, F, Liu, Y. Automatic registration of large-scale urban scene point clouds based on semantic feature points. ISPRS J Photogrammetry Remote Sens 2016;113:43–58. https://doi.org/10.1016/j.isprsjprs.2015.12.005.Search in Google Scholar
13. Aiger, D, Mitra, NJ, Cohen-Or, D. 4-points congruent sets for robust pairwise surface registration. ACM Trans Graph 2008;27:1–10. https://doi.org/10.1145/1360612.1360684.Search in Google Scholar
14. Theiler, PW, Wegner, JD, Schindler, K. Keypoint-based 4-points congruent sets–automated marker-less registration of laser scans. ISPRS J Photogrammetry Remote Sens 2014;96:149–63. https://doi.org/10.1016/j.isprsjprs.2014.06.015.Search in Google Scholar
15. Besl, PJ, McKay, ND. A method for registration of 3-D shapes. IEEE Trans Pattern Anal Mach Intell 1992;14:239–56. https://doi.org/10.1109/34.121791.Search in Google Scholar
16. Park, SY, Subbarao, M. An accurate and fast point-to-plane registration technique. Pattern Recogn Lett 2003;24:2967–76. https://doi.org/10.1016/s0167-8655(03)00157-0.Search in Google Scholar
17. Yang, B, Zang, Y, Dong, Z, Huang, R. An automated method to register airborne and terrestrial laser scanning point clouds. ISPRS J Photogrammetry Remote Sens 2015;109:62–76. https://doi.org/10.1016/j.isprsjprs.2015.08.006.Search in Google Scholar
18. Segal, A, Haehnel, D, Thrun, S. Generalized-icp. In: Robotics: science and systems; 2009, vol 2:435 p.10.15607/RSS.2009.V.021Search in Google Scholar
19. Chetverikov, D, Stepanov, D, Krsek, P. Robust Euclidean alignment of 3D point sets: the trimmed iterative closest point algorithm. Image Vis Comput 2005;23:299–309. https://doi.org/10.1016/j.imavis.2004.05.007.Search in Google Scholar
20. Wujanz, D, Krueger, D, Neitzel, F. Identification of stable areas in unreferenced laser scans for deformation measurement. Photogramm Rec 2016;31:261–80. https://doi.org/10.1111/phor.12152.Search in Google Scholar
21. Friedli, E, Wieser, A. Identification of stable surfaces within point clouds for areal deformation monitoring. In: Proceedings of 3rd joint international symposium on deformation monitoring (JISDM). Vienna, Austria; 2016.Search in Google Scholar
22. Bustos, AP, Chin, TJ. Guaranteed outlier removal for point cloud registration with correspondences. IEEE Trans Pattern Anal Mach Intell 2017;40:2868–82. https://doi.org/10.1109/tpami.2017.2773482.Search in Google Scholar
23. Gojcic, Z, Zhou, C, Wegner, JD, Guibas, LJ, Birdal, T. Learning multiview 3d point cloud registration. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR). Virtual; 2020.10.1109/CVPR42600.2020.00183Search in Google Scholar
24. Rusu, RB, Marton, ZC, Blodow, N, Dolha, M, Beetz, M. Towards 3D point cloud based object maps for household environments. Robot Autonom Syst 2008;56:927–41. https://doi.org/10.1016/j.robot.2008.08.005.Search in Google Scholar
25. Gojcic, Z, Zhou, C, Wieser, A. F2S3: robustified determination of 3D displacement vector fields using deep learning. J Appl Geodes 2020;14:177–89. https://doi.org/10.1515/jag-2019-0044.Search in Google Scholar
26. Papon, J, Abramov, A, Schoeler, M, Worgotter, F. Voxel cloud connectivity segmentation-supervoxels for point clouds. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR). Portland, Oregon, USA; 2013.10.1109/CVPR.2013.264Search in Google Scholar
27. Taubenheim, J. Statistische Auswertung geophysikalischer und meteorologischer Daten. Leipzig, Germany: Akad. Verlagsgesellschaft Geest & Portig K. G.; 1969.Search in Google Scholar
28. Kauker, S, Schwieger, V. A synthetic covariance matrix for monitoring by terrestrial laser scanning. J Appl Geodes 2017;11:77–87. https://doi.org/10.1515/jag-2016-0026.Search in Google Scholar
29. Pfeiffer, J, Wujanz, D, Zieher, T, Rutzinger, M, Scaioni, M, Höfle, B, et al.. Terrestrial laser scanning data of the Nesslrinna landslide close to Obergurgl, Austria acquired during the 2019 Innsbruck summer school of Alpine research. Pangaea: University of Innsbruck; 2019 [Accessed 31 August 2022].Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Guest Editorial
- Special Issue: Deformation Monitoring
- Research Articles
- High-precision intermode beating electro-optic distance measurement for mitigation of atmospheric delays
- EDM-GNSS distance comparison at the EURO5000 calibration baseline: preliminary results
- A mobile robot for monitoring floor flatness in real-time
- On the quality checking of persistent scatterer interferometry data by spatial-temporal modelling
- Image segmentation of breakwater blocks by edge-base Hough transformation
- Real movement or systematic errors? – TLS-based deformation analysis of a concrete wall
- Investigation of space-continuous deformation from point clouds of structured surfaces
- Supervoxel-based targetless registration and identification of stable areas for deformed point clouds
- Forecasting post-earthquake rockfall activity
Articles in the same Issue
- Frontmatter
- Guest Editorial
- Special Issue: Deformation Monitoring
- Research Articles
- High-precision intermode beating electro-optic distance measurement for mitigation of atmospheric delays
- EDM-GNSS distance comparison at the EURO5000 calibration baseline: preliminary results
- A mobile robot for monitoring floor flatness in real-time
- On the quality checking of persistent scatterer interferometry data by spatial-temporal modelling
- Image segmentation of breakwater blocks by edge-base Hough transformation
- Real movement or systematic errors? – TLS-based deformation analysis of a concrete wall
- Investigation of space-continuous deformation from point clouds of structured surfaces
- Supervoxel-based targetless registration and identification of stable areas for deformed point clouds
- Forecasting post-earthquake rockfall activity
