access icon free Robust algorithm for multiview registration

Multiview registration is an important stage in three-dimensional modelling pipeline. Motion averaging is an efficient approach for multiview registration which utilises the redundancy in overlap among the scans. The averaging of the underlying relative motions is performed in the corresponding Lie-algebra elements of the SE(3) transformation matrices. However, this method is non-robust and affected by the presence of outliers in the set of relative motions. The authors present a graph-based approach to filter out the outliers before performing averaging of motions. The relative motions are assigned weights based on their agreement with global motions and other relative motions. The results indicate that the authors’ approach can efficiently filter out the outliers and can thus introduce robustness to multiview registration using motion averaging.

Inspec keywords: image motion analysis; matrix algebra; graph theory; image registration; redundancy; image filtering

Other keywords: overlap redundancy; lie-algebra element; motion averaging; three-dimensional modelling pipeline; SE(3) transformation matrices; outlier filtering; graph-based approach; multiview registration robust algorithm; image scan

Subjects: Optical, image and video signal processing; Combinatorial mathematics; Combinatorial mathematics; Filtering methods in signal processing; Algebra; Computer vision and image processing techniques; Algebra

References

    1. 1)
      • 9. Eggert, D.W., Fitzgibbon, A.W., Fisher, R.B.: ‘Simultaneous registration of multiple range views for use in reverse engineering’. Proc. of IEEE Int. Conf. on Pattern Recognition, 1996, vol. 1, pp. 243247.
    2. 2)
      • 17. Sprickerhof, J., Nüchter, A., Lingemann, K., et al: ‘An explicit loop closing technique for 6d slam’. ECMR, Mlini/Dubrovnik, Croatia, September 2009, pp. 229234.
    3. 3)
      • 23. Govindu, V.M., Pooja, A.: ‘On averaging multiview relations for 3d scan registration’, IEEE Trans. Image Process., 2014, 23, (3), pp. 12891302.
    4. 4)
      • 8. Pulli, K.: ‘Multiview registration for large data sets’. Proc. of Int. Conf. on 3-D Digital Imaging and Modeling, Canada, October 1999, pp. 160168.
    5. 5)
      • 10. Nishino, K., Ikeuchi, K.: ‘Robust simultaneous registration of multiple range images’. Digitally Archiving Cultural Objects, 2008, pp. 7188.
    6. 6)
      • 27. Blanco, J.L.: ‘A tutorial on se (3) transformation parameterizations and on-manifold optimization’. Technical Report, University of Malaga, September 2010.
    7. 7)
      • 1. Dorai, C., Wang, G., Jain, A.K., et al: ‘From images to models: automatic 3D object model construction from multiple views’. Proc. of IEEE Int. Conf. on Pattern Recognition, Vienna, Austria, August 1996, vol. 1, pp. 770774.
    8. 8)
      • 25. Chatterjee, A., Govindu, V.: ‘Efficient and robust large-scale rotation averaging’. Proc. of IEEE Int. Conf. on Computer Vision, Sydney, Australia, December 2013, pp. 521528.
    9. 9)
      • 3. Rusinkiewicz, S., Levoy, M.: ‘Efficient variants of the ICP algorithm’. Proc. of IEEE 3rd Int. Conf. on 3-D Digital Imaging and Modeling, Canada, June 2001, pp. 145152.
    10. 10)
      • 36. Rusu, R.B., Cousins, S.: ‘3d is here: point cloud library (PCL)’. IEEE Int. Conf. on Robotics and Automation (ICRA), Shanghai, China, May 2011, pp. 14.
    11. 11)
      • 32. Levoy, M.: ‘The Stanford 3D scanning repository’. Available at https://graphics.stanford.edu/data/3Dscanrep/, accessed 18 February 2016.
    12. 12)
      • 28. Fletcher, P.T., Lu, C., Joshi, S.: ‘Statistics of shape via principal geodesic analysis on Lie groups’. Proc. of IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, Madison, Wisconsin, June 2003, vol. 1, pp. 95101.
    13. 13)
      • 18. Sharp, G.C., Lee, S.W., Wehe, D.K.: ‘Multiview registration of 3d scenes by minimizing error between coordinate frames’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (8), pp. 10371050.
    14. 14)
      • 13. Grisetti, G., Strasdat, H., Konolige, K., et al: ‘g2o: a general framework for graph optimization’. IEEE Int. Conf. on Robotics and Automation, Shanghai, May 2011, pp. 36073613.
    15. 15)
      • 34. Zhong, Y.: ‘Intrinsic shape signatures: a shape descriptor for 3d object recognition’. IEEE 12th Int. Conf. on Computer Vision Workshops (ICCV Workshops), September 2009, pp. 689696.
    16. 16)
      • 24. Govindu, V.M.: ‘Robustness in motion averaging’. Proc. of Asian Conf. on Computer Vision, ACCV, Hyderabad, India, January 2006, pp. 457466.
    17. 17)
      • 7. Neugebauer, P.J.: ‘Reconstruction of real-world objects via simultaneous registration and robust combination of multiple range images’, Int. J. Shape Model. , 1997, 3, (01n02), pp. 7190.
    18. 18)
      • 20. Batlle, E., Matabosch, C., Salvi, J.: ‘Summarizing image/surface registration for 6dof robot/camera pose estimation’. Iberian Conf. on Pattern Recognition and Image Analysis, Spain, June 2007, pp. 105112.
    19. 19)
      • 5. Chen, Y., Gérard, M.: ‘Object modelling by registration of multiple range images’, Image Vis. Comput., 1992, 10, (3), pp. 145155.
    20. 20)
      • 19. Shiratori, T., Berclaz, J., Harville, M., et al: ‘Efficient large-scale point cloud registration using loop closures’. IEEE Int. Conf. on 3D Vision (3DV), Lyon, October 2015, pp. 232240.
    21. 21)
      • 16. Newcombe, R.A., Izadi, S., Hilliges, O., et al: ‘KinectFusion: real-time dense surface mapping and tracking’. 10th IEEE Int. Symp. on Mixed and Augmented Reality (ISMAR), October 2011, pp. 127136.
    22. 22)
      • 26. Joyner, D., Van Nguyen, M., Cohen, N.: ‘Algorithmic graph theory’ (Google Code, 2010).
    23. 23)
      • 6. Bergevin, R., Soucy, M., Gagnon, H.: ‘Towards a general multiview registration technique’, IEEE Trans. Pattern Anal. Mach. Intell., 1996, 18, (5), pp. 540547.
    24. 24)
      • 33. Mian, A., Bennamoun, M., Owens, R.: ‘On the repeatability and quality of keypoints for local feature-based 3d object retrieval from cluttered scenes’, Int. J. Comput. Vis., 2010, 89, (2–3), pp. 348361.
    25. 25)
      • 30. Duan, X., Sun, H., Peng, L.: ‘Riemannian means on special Euclidean group and unipotent matrices group’, Sci. World J., 2013, 2013, Article ID 292787.
    26. 26)
      • 22. Govindu, V.M.: ‘Lie-algebraic averaging for globally consistent motion estimation’. Proc. of the IEEE Computer Society Conf. CVPR, Washington DC, June 2004, vol. 1, pp. 684691.
    27. 27)
      • 2. Pankaj, D.S., Nidamanuri, R.R.: ‘A robust estimation technique for 3D point cloud registration’, Image Anal. Stereol. , 2016, 35, (1), pp. 1528.
    28. 28)
      • 31. Li, Z., Zhu, J., Lan, K., et al: ‘Improved techniques for multi-view registration with motion averaging’. IEEE 2nd Int. Conf. on 3D Vision (3DV), Tokyo, Japan, December 2014, vol. 1, pp. 713719.
    29. 29)
      • 35. Frome, A., Huber, D., Kolluri, R., et al: ‘Recognizing objects in range data using regional point descriptors’. Computer Vision ECCV, Prague, Czech Republic, May 2004, pp. 224237.
    30. 30)
      • 12. Borrmann, D., Elseberg, J., Lingermann, K., et al: ‘The efficient extension of globally consistent scan matching to 6DOF’, Knowl. Based Syst., 2008, 1, p. 20.
    31. 31)
      • 4. Benjemaa, R., Schmitt, F.: ‘A solution for the registration of multiple 3D point sets using unit quaternions’. European Conf. on Computer Vision, Germany, June 1998, pp. 3450.
    32. 32)
      • 14. Krishnan, S., Lee, P.Y., Moore, J.B., et al: ‘Global registration of multiple 3d point sets via optimization-on-a-manifold’. In Symp. on Geometry Processing, July 2005, pp. 187196.
    33. 33)
      • 29. Kanatani, K.: ‘Group-theoretical methods in image understanding’ (Springer Science and Business Media, 2012), vol. 20.
    34. 34)
      • 21. Shih, S.W., Chuang, Y.T., Yu, T.Y.: ‘An efficient and accurate method for the relaxation of multiview registration error’, IEEE Trans. Image Process., 2008, 17, (6), pp. 968981.
    35. 35)
      • 15. Mateo, X., Orriols, X., Binefa, X.: ‘Bayesian perspective for the registration of multiple 3d views’, Comput. Vis. Image Underst., 2014, 118, pp. 8496.
    36. 36)
      • 11. Huber, D.F., Hebert, M.: ‘Fully automatic registration of multiple 3d data sets’, Image Vis. Comput., 2003, 21, (7), pp. 637650.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2016.0080
Loading

Related content

content/journals/10.1049/iet-cvi.2016.0080
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading