A fast registration algorithm of rock point cloud based on spherical projection and feature extraction

Abstract

Point cloud registration is an essential step in the process of 3D reconstruction. In this paper, a fast registration algorithm of rock mass point cloud is proposed based on the improved iterative closest point (ICP) algorithm. In our proposed algorithm, the point cloud data of single station scanner is transformed into digital images by spherical polar coordinates, then image features are extracted and edge points are removed, the features used in this algorithm is scale-invariant feature transform (SIFT). By analyzing the corresponding relationship between digital images and 3D points, the 3D feature points are extracted, from which we can search for the two-way correspondence as candidates. After the false matches are eliminated by the exhaustive search method based on random sampling, the transformation is computed via the Levenberg-Marquardt-Iterative Closest Point (LM-ICP) algorithm. Experiments on real data of rock mass show that the proposed algorithm has the similar accuracy and better registration efficiency compared with the ICP algorithm and other algorithms.

Keywords

rock point cloud / registration / LM-ICP / spherical projection / feature extraction

References

[1] Akca D, Gruen A. A flexible mathematical model for matching of 3D surfaces and attributes. In: Proceedings of SPIE-IS&T Electronic Imaging. 2005, 184–195

[2] Salvi J, Matabosch C, Fofi D, Forest J. A review of recent range image registration methods with accuracy evaluation. Image and Vision Computing, 2007, 25(5): 578–596

[3] Besl P J, McKay N D. A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239–256

[4] Chen Y, Medioni G. Object modelling by registration of multiple range images. Image and Vision Computing, 1992, 10(3): 145–155

[5] Farin G E, Hoschek J, Kim M S. Handbook of Computer Aided Geometric Design. Amsterdam: North-Holland, 2002

[6] Wang T S, Duan Q C, Wang R. Research on registration method and precision in terrestrial 3D laser scanning. In: Proceedings of International Conference on Intelligent Earth Observing and Applications. 2015

[7] Jia D F, Cheng X J, Liu Y P, Cheng X L. The orientation method of terrestrial 3D laser scanner. Geotechnical Investigation & Surveying, 2014, 10: 60–65

[8] Chua C S, Jarvis R. Point signatures: a new representation for 3D object recognition. International Journal of Computer Vision, 1997, 25(1): 63–85

[9] Johnson A E. Spin-Images: A Representation for 3-D Surface Matching. MPitsburgh, PA: Carnegie Mellon University, 1997

[10] Stamos I, Leordean M. Automated feature-based range registration of urban scenes of large scale. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2003, 555–561

[11] Chen C, Stamos I. Semi-automatic range to range registration: a feature-based method. In: Proceedings of the 5th International Conference on 3-D Digital Imaging and Modeling. 2005, 254–261

[12] Dai J L, Chen Z Y, Ye X Z. The application of icp algorithm in point cloud alignment. Journal of Image and Graphics, 2007, 12(3): 517–521

[13] Manay S, Hong B W, Yezzi A J, Soatto S. Integral invariant signatures. In: Proceedings of the 8th European Conference on Computer Vision. 2004, 87–99

[14] Gelfand N, Mitra N J, Guibas L J, Pottmann H. Robust global registration. In: Proceedings of the 3rd Eurographics Symposium on Geometry Processing. 2005, 197–206

[15] Huang Q X, Flöry S, Gelfand N, Hofer M, Pottmann H. Reassembling fractured objects by geometric matching. ACMTransactions on Graphics, 2006, 26(3): 569–578

[16] Zhang L, Ma H C, Gao G, Chen Z. Automatic registration of urban aerial images with airborne lidar points based on line-point similarity invariants. Acta Geodaetica et Cartographica Sinica, 2014, 43(4): 372–379

[17] Díez Y, Roure F, Lladó X, Salvi J. A qualitative review on 3D coarse registration methods. ACM Computing Surveys, 2015, 47(3): 45

[18] Chen J, Wu X J, Wang M Y, Li X F. 3D shape modeling using a selfdeveloped hand-held 3D laser scanner and an efficient HT-ICP point cloud registration algorithm. Optics & Laser Technology, 2013, 45(1): 414–423

[19] Zhong Y, Zhang M. Automatic registration technology of point cloud based on improved ICP algorithm. Control Engineering of China, 2014, 21(1): 37–40

[20] Zhao M B, He J, Luo X B, Fu Q. Two-viewing angle ladar data registration based on improved iterative closest-point algorithm. Acta Optica Sinica, 2012, 32(11): 305–314

[21] Zhang L, Choi S I, Park S Y. Robust icp registration using biunique correspondence. In: Proceedings of International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission. 2011, 80–85

[22] Fitzgibbon A W. Robust registration of 2D and 3D point sets. Image and Vision Computing, 2003, 21(13): 1145–1153

[23] Biber P, Straβer W. The normal distributions transform: a new approach to laser scan matching. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. 2003, 2743–2748

[24] Magnusson M, Lilienthal A, Duckett T. Scan registration for autonomous mining vehicles using 3D-NDT. Journal of Field Robotics, 2007, 24(10): 803–827

[25] Yang M Y, Cao Y, McDonald J. Fusion of camera images and laser scans for wide baseline 3D scene alignment in urban environments. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(6): S52–S61

[26] Al-Manasir K, Fraser C S. Registration of terrestrial laser scanner data using imagery. The Photogrammetric Record, 2006, 21(115): 255–268

[27] Łępicka M, Kornuta T, Stefánczyk M. Utilization of colour in ICP-based point cloud registration. In: Proceedings of the 9th International Conference on Computer Recognition Systems. 2016, 821–830

[28] Syed I A, Sharma B. Hybrid 3D registration approach using RGB and depth images. In: Proceedings of the 2nd IEEE International Conference on Image Information Processing. 2013, 27–32

[29] Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91–110

[30] Bay H, Ess A, Tuytelaars T, Gool L V. Speeded-up robust features (SURT). Computer Vision and Image Understanding, 2008, 110(3): 346–359

[31] Rublee E, Rabaud V, Konolige K, Bradski G. ORB: an efficient alternative to SIFT or SURF. In: Proceedings of International Conference on Computer Vision. 2011, 2564–2571

[32] Zhang Y, Zou Z. Automatic registration method for remote sensing images based on improved orb algorithm. Remote Sensing for Land & Resources, 2013, 25(3): 20–24

[33] Yang J, Cao Z, Zhang Q. A fast and robust local descriptor for 3D point cloud registration. Information Sciences, 2016, 346–347: 163–179

[34] Shi P. Study on local descriptor. Shanghai: Shanghai Jiao Tong University, 2008

[35] Chen C S, Hung Y P, Cheng J B. A fast automatic method for registration of partially-overlapping range images. In: Proceedings of the 6th International Conference on Computer Vision. 1998, 242–248

[36] Mellado N, Aiger D, Mitra N J. Super 4PCS fast global pointcloud registration via smart indexing. Computer Graphics Forum, 2014, 33(5): 205–215

[37] Perumal L. Quaternion and its application in rotation using sets of regions. International Journal of Engineering and Technology Innovation, 2011, 1(1): 35–52

[38] Lato M, Kemeny J, Harrap R M, Bevan G. Rock bench: establishing a common repository and standards for assessing rockmass characteristics using lidar and photogrammetry. Computers & Geosciences, 2013, 50(1): 106–114

[39] Bouaziz S, Tagliasacchi A, Pauly M. Sparse iterative closest point. Computer Graphics Forum, 2013, 32(5): 113–123

RIGHTS & PERMISSIONS

2018 Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature