This work proposes an invariant descriptor and a pipeline for the registration of surface range images based on segmentation/reconstruction making use of an edge detection technique combined with a clustering technique using mesh decimation. This novel descriptor is applied to contours and it is invariant to similarity transformations including rotation, translation, uniform scale and it is robust to noise. The proposed feature descriptor makes use of corresponding points extracted from two images and a signature label is assigned specifically to a point considering the geometrical distribution of its neighbourhood, reducing possible areas of overlapping and the ambiguity in the search process. The descriptor was evaluated through a series of tests with various object range images. To validate the candidate transformations, the fitting errors between the two range images are evaluated by the iterative closest point algorithm. This study also presents and discusses results from the application of the developed pipeline in a vision sensor mounted on a robot arm specially built as part of a R&D project to acquire range images by laser scanning over the surface of hydraulic turbine blades. The sensor generates 3D surface models to be registered in the 3D coordinate system of the robot controller.

References

1. 1)
  - 12. Li, Y., Snavely, N., Huttenlocher, D., et al: ‘Worldwide pose estimation using 3D point clouds’, in Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (Eds.): Computer vision – ECCV 2012. LNCS (7572), 2012, pp. 15–29. Available at https://doi.org/10.1007/978-3-642-33718-5_2.
2. 2)
  - 29. Planitz, B.M., Maeder, A.J., Williams, J.A.: ‘The correspondence framework for 3D surface matching algorithms’, Comput. Vis. Image Underst., 2005, 97, pp. 347–383. doi:10.1016/j.cviu.2004.08.001.
3. 3)
  - 26. Rosenfeld, A., Wezka, J.S.: ‘An improved method of angle detection on digital curves’, IEEE Trans. Comput., 1975, C-24, (9), pp. 940–941.
4. 4)
  - 28. ISO GUM: ‘Guide to the expression of uncertainty in measurement – propagation of distributions using a Monte Carlo method’. Geneve, First edition, 2008. Available at https://www.bipm.org/utils/common/documents/jcgm/JCGM_101_2008_E.pdf, acessed in December 2018.
5. 5)
  - 6. Flusser, J., Zitova, B., Suk, T.: ‘Moments and moment invariants in pattern recognition’ (Wiley, Chichester, 2009).
6. 6)
  - 22. Freeman, H., Davis, L.S.: ‘A corner finding algorithm for chain coded curves’, IEEE Trans. Comput., 1977, 26, (3), pp. 297–303.
7. 7)
  - 15. Mingqiang, Y., Kidiyo, K., Joseph, R.: ‘A survey of shape feature extraction techniques’, in Yin, P.-Y. (Ed.): ‘Pattern Recognition’ (IN-TECH, Vienna, 2008), pp. 43–90.
8. 8)
  - 17. Yang, H., Yu, M., Zhang, S.: ‘Wide baseline stereo matching based on scale invariant feature transformation with hybrid geometric constraints’, IET Comput. Vis., 2014, 8, (6), pp. 611–619. doi: 10.1049/iet-cvi.2013.0265.
9. 9)
  - 10. Zhong, L., Changchen, Z., Xingming, W., et al: ‘An effective 3D shape descriptor for object recognition with RGB-D sensors’, Sensors (Basel), 2017, 17, (3), pp. 1–17. Available at https://doi.org/10.3390/s17030451.
10. 10)
  - 4. Li, L., Li, C., Tang, Y., et al: ‘An integrated approach of reverse engineering aided remanufacturing process for worn components’, Robot. Comput.-Integr. Manuf., 2017, 48, pp. 39–50.
11. 11)
  - 8. Besl, P., Mckay, N.: ‘A method for registration of 3-D shapes’, IEEE Trans. Pattern Anal. Mach. Intell.., 1992, 14, pp. 239–256.
12. 12)
  - 9. Chen, C.-S., Chen, P.-C., Hsu, C.-M.: ‘Three-dimensional object recognition and registration for robotic grasping systems using a modified viewpoint feature histogram’, Sensors (Basel), 2016, 16, (11), pp. 1–14. Available at https://doi.org/10.3390/s16111969.
13. 13)
  - 19. Silva, J.P., Borges, D.L., Vidal, F.B.: ‘A dynamic approach for approximate pairwise alignment based on 4-points congruence sets of 3D points’. Proc. 18th IEEE Int. Conf. on Image Processing, Brussels, 2013, pp. 889–892. doi: 10.1109/ICIP.2011.6116701.
14. 14)
  - 3. Senin, N., Colosimo, B.M., Pacella, M.: ‘Point set augmentation through fitting for enhanced ICP registration of point clouds in multisensor coordinate metrology’, Robot. Comput.-Integr. Manuf., 2013, 29, (1), pp. 39–52.
15. 15)
  - 21. Gonzalez, R., Woods, R.: ‘Digital image processing’ (Prentice Hall, New Jersey, 2008, 3rd edn.).
16. 16)
  - 13. Wu, Z., Song, S., Khosla, A., et al: ‘3D shapenets: a deep representation for volumetric shape modeling’. Proc. of 28th IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Boston, MA, 2015, pp. 1912–1920.
17. 17)
  - 18. Tombari, F., Salti, S., Di-Stefano, L.: ‘A performance evaluation of 3D key point detectors’. Proc. of the IEEE Int. Conf. on 3D Imaging, Modeling, Processing, Visualization, and Transmission, Hangzhou, China, 2013, vol. 102, (1–3), pp. 198–220.
18. 18)
  - 7. Amanatiadis, A., Kaburlasos, V.G., Gasteratos, A., et al: ‘Evaluation of shape descriptors for shape-based image retrieval’, IET Image Process., 2009, 5, (5), pp. 493–499. doi: 10.1049/iet-ipr.2009.0246.
19. 19)
  - 23. Haykin, S.: ‘Adaptive filter theory’ (Prentice Hall, New Jersey, 2002).
20. 20)
  - 14. Zhang, H., Wei, Q., Jiang, Z.: ‘3D reconstruction of space objects from multi-views by a visible sensor’, Sensors (Basel), 2015, 17, (7), pp. 1–16. Available at http://doi.org/10.3390/s17071689.
21. 21)
  - 16. Zhang, D., Lu, G.: ‘Review of shape representation and description techniques’, Pattern Recognit., 2004, 37, (1), pp. 1–19.
22. 22)
  - 1. Öztürk, S., Kuzucuoğlu, A.E.: ‘Optimal bid valuation using path finding for multi-robot task allocation’, J. Intell. Manuf.., 2015, 26, (5), pp. 1049–1062. Available at https://doi.org/10.1007/s10845-014-0909-4.
23. 23)
  - 2. Motta, J.M.S.T., Llanos-Quintero, C.H., Sampaio, R.C.: ‘Inverse kinematics and model calibration optimization of a five-D.O.F. Robot for repairing the surface profiles of hydraulic turbine blades’, Int. J. Adv. Robot. Syst., 2016, 13, pp. 1–15. Available at https://doi.org/10.5772/63673.
24. 24)
  - 11. Wohlhart, P., Lepetit, V.: ‘Learning descriptors for object recognition and 3D pose estimation’. Proc. 2015 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015. doi: 10.1109/CVPR.2015.7298930.
25. 25)
  - 27. Beus, H.L., Tiu, S.S.H.: ‘An improved corner detection algorithm based on chain-coded plane curves’, Pattern Recognit., 1987, 20, (3), pp. 291–296.
26. 26)
  - 5. Yago, D., Ferran, R., Xavier, L., et al: ‘A qualitative review on 3D coarse registration methods’, ACM Comput. Surv., 2015, 47, (3), p. 36. Available at http://dx.doi.org/10.1145/2692160.
27. 27)
  - 20. Chui, K.L., Chiu, W.K., Yu, K.M.: ‘Direct 5-axis tool-path generation from point cloud input using 3D biarc fitting’, Robot. Comput.-Integr. Manuf., 2008, 24, (20), pp. 270–286.
28. 28)
  - 24. Chetverikov, D., Szabó, Z.: ‘A simple and efficient algorithm for detection of high curvature points in planar curves’. Proceedings of the 23rd Workshop of Austrian Pattern Recognition Group, Steyr, 27–28 May 1999, pp. 175–184..
29. 29)
  - 25. Rosenfeld, H., Johnston, E.: ‘Angle detection on digital curves’, IEEE Trans. Comput., 1973, C-22, (9), pp. 875–878.

Novel invariant feature descriptor and a pipeline for range image registration in robotic welding applications

References

Related content