A new multi-vision-based reconstruction algorithm for tube inspection



Complex tubes are used widely in aerospace vehicles today, and their accurate assembly can determine the equipment’s performance and longevity. The machining precision of the tube determines its assembly reliability. As most tubes are metallic, springback is a major factor preventing them from realizing accuracy requirements in primary processing. Thus, it is important to inspect the processed tubes and then fix any geometric errors to satisfy the assembly requirements. However, the widely adopted tube inspection method in the literature is time-consuming and inconvenient because it is greatly dependent on human operation. In fact, there is no effective inspection method for tubes with complex shapes and large dimensions. To address this, an automatic tube reconstruction algorithm based on multi-vision is proposed in this paper. The algorithm discretizes the tube into many small cylinders, referred to as primitives. Multi-vision technology and the tube edges are then used to reconstruct the primitives to form the initial model, from which a three-dimensional model can be constructed within 2 min. Our algorithm dramatically improves the reconstruction speed because it concentrates only on the reconstruction of finite cylinders rather than point clouds on the tube surface. And the reconstruction accuracy is 0.17 mm, allowing arc recognition of bending angles ranging from 1° to 180°. Also, the restrictions due to reflection on the surface and the lack of necessary texture for matching are solved at the same time. A comparison of reconstructed and computer-aided design (CAD) models resolves geometric error and springback for machining parameter optimization, providing improved accuracy particularly for tube bending, which is of great significance for the realization of automated tube production.


Cylinder primitive Multi-vision Shape from silhouette Tube reconstruction 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Liu Q, Wang C (2010) Pipe-assembly approach for aero-engines by modified particle swarm optimization. Assembly Auto 30(4):365–377. doi: 10.1108/01445151011075825 CrossRefGoogle Scholar
  2. 2.
    Gibbon D, Ward J, Kay N (2000) The design, development and testing of a propulsion system for the snap-1 nanosatellite. Proc 14th Annual AIAA/USU Conference on Small Satellites (SSCOO-I-3), Logan, UT, Aug 2000.Google Scholar
  3. 3.
    Zhou C, Yin Y (2010) Pipe assembly planning algorithm by imitating human imaginal thinking. Assembly Auto 30(1):66–74. doi: 10.1108/01445151011016082 CrossRefGoogle Scholar
  4. 4.
    He Y, Heng L, Zhiyong Z, Mei Z, Jing L, Guangjun L (2012) Advances and trends on tube bending forming technologies. Chin J Aeronaut 25(1):1–12. doi: 10.1016/S1000-9361(11)60356-7 CrossRefGoogle Scholar
  5. 5.
    Guo XZ, Jin K, Wang H, Pei WJ, Ma FY, Tao J, Kim N (2016) Numerical simulations and experiments on fabricating bend pipes by push bending with local induction-heating process. Int J Adv Manuf Technol 84(9–12):2689–2695. doi: 10.1007/s00170-015-7898-0 CrossRefGoogle Scholar
  6. 6.
    Feng YW, Thornton AC (2000) Tube production and assembly systems: the impact of compliance and variability on yield. ASME Design Automation Conference 2000, Baltimore.Google Scholar
  7. 7.
    Lee I-K, Kim KJ (2004) Shrinking: another method for surface reconstruction. In: GMP’04: Proceedings of the geometric modeling and processing, IEEE Computer Society: 259–266. doi:  10.1109/gmap.2004.1290047
  8. 8.
    Bauer U, Polthier K (2009) Generating parametric models of tubes from laser scans. Comput Aided Design 41(10):719–729. doi: 10.1016/j.cad.2009.01.002 CrossRefGoogle Scholar
  9. 9.
    Kawashima K, Kanai S, Date H (2014) As-built modeling of piping system from terrestrial laser-scanned point clouds using normal-based region growing. J Comput Des Eng 1(1):13–26. doi: 10.7315/JCDE.2014.002 Google Scholar
  10. 10.
    Son H, Bosche F, Kim C (2015) As-built data acquisition and its use in production monitoring and automated layout of civil infrastructure: a survey. Adv Eng Inform 29(2):172–183. doi: 10.1016/j.aei.2015.01.009 CrossRefGoogle Scholar
  11. 11.
    Goulette F (1997) Automatic cad modeling of industrial pipes from range images. Proc Int’l Conf 3D Digital Imaging and Modeling. Los Alamitos, CA: 229-233. doi: 10.1109/IM.1997.603870
  12. 12.
    Veldhuis H, Vosselman G (1998) The 3D reconstruction of straight and curved pipes using digital line photogrammetry. ISPRS-J Photogramm Remote Sens 53(1):6–16. doi: 10.1016/S0924-2716(97)00031-2 CrossRefGoogle Scholar
  13. 13.
    Tangelder JWH, Vosselman G, Heuvel FAVD (2000) Object-oriented measurement of pipe systems using edge matching and csg models with constraints. Int Arch Photogramm Remote Sens XXXIII(Supplement B5):132–139Google Scholar
  14. 14.
    Vosselman G, Tangelder JWH (2000) 3D reconstruction of industrial installations by constrained fitting of cad models to images. Mustererkennug, G. Sommer, N. Kruger, Ch. Perwass (Eds.), Informatik aktuell, Springer Verlag: 185-92. doi: 10.1007/978-3-642-59802-9_36
  15. 15.
    Tangelder JWH, Ermes P, Vosselman G, Heuvel FAVD (2003) CAD-based photogrammetry for reverse engineering of industrial installations. Computer Aided Civ Inf 18(4):264–274. doi: 10.1111/1467-8667.00316 CrossRefGoogle Scholar
  16. 16.
    Aubry M, Maturana D, Efros AA, Rusell BC, Sivic J (2014) Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of CAD models. In: 2014 I.E. Conference on Computer Vision and Pattern Recognition:3762–3769Google Scholar
  17. 17.
    Opton. Available at: (Accessed 20 December, 2015)
  18. 18.
    Fisher RB (2004) Applying knowledge to reverse engineering problems. Comput Aided Design 36(6):501–510. doi: 10.1016/S0010-4485(03)00158-1 CrossRefGoogle Scholar
  19. 19.
    Advanced tubular. Available at: (Accessed 20 December, 2015)
  20. 20.
    Tezet. Available at: (Accessed 20 December, 2015)
  21. 21.
    Bosemann W (1996) The optical tube measurement system olm-photogrammetric methods used for industrial and process control. Int Arch Photogramm Remote Sens XXXL(part b5):55–58Google Scholar
  22. 22.
  23. 23.
    Brettel M, Friederichsen N, Keller M, Rosenberg M (2014) How virtualization, decentralization and network building change the manufacturing landscape: an industry 4.0 perspective. Int J Mech Aerosp Ind Mechatron Manufac Eng 8(1):37–44Google Scholar
  24. 24.
    Fiorenzo F, Domenico M (2014) The evolution of large-scale dimensional metrology from the perspective of scientific articles and patents. Int J Adv Manuf Technol 70(5):887–909. doi: 10.1007/s00170-013-5317-y Google Scholar
  25. 25.
    Luhmann T (2010) Close range photogrammetry for industrial applications. ISPRS-J Photogramm Remote Sens 65(6):558–569. doi: 10.1016/j.isprsjprs.2010.06.003 CrossRefGoogle Scholar
  26. 26.
    Ahmadabadian AH, Robson S, Boehm J, Shortis M, Wenzel K, Fritsch D (2013) A comparison of dense matching algorithms for scaled surface reconstruction using stereo camera rigs. ISPRS-J Photogramm Remote Sens 78:157–167. doi: 10.1016/j.isprsjprs.2013.01.015 CrossRefGoogle Scholar
  27. 27.
    Remondino F, Spera MG, Nocerino E, Menna F, Nex F (2014) State of the art in high density image matching. Photogramm Rec 29(146):144–166. doi: 10.1111/phor.12063 CrossRefGoogle Scholar
  28. 28.
    David CK (2001) Contour into texture: information content of surface contours and texture flow. J Opt Soc Am A 18(1):12–35. doi: 10.1364/JOSAA.18.000012 MathSciNetCrossRefGoogle Scholar
  29. 29.
    Lou HZ, Stelson KA (2001) Three-dimensional tube geometry control for rotary draw tube bending, part 2: statistical tube tolerance analysis and adaptive bend correction. J Manuf Sci E-T Asme 123:266–271CrossRefGoogle Scholar
  30. 30.
    Ding G, Jiang L, Qin S, Zhu S, Ma S (2012) Computer-integrated manufacturing system for tube bending. Int J Comput Integ M 25(11):1059–1068. doi: 10.1080/0951192X.2012.684710 CrossRefGoogle Scholar
  31. 31.
    Shrivakshan GT, Chandrasekar C (2012) A comparison of various edge detection techniques used in image processing. Int J Comput Sci Issues 9(4):269–276Google Scholar
  32. 32.
    Chen NQ, Wang JJ, Yu LA, Su CY (2014) Sub-pixel edge detection of led probes based on canny edge detection and iterative curve fitting. International Symposium on Computer, Consumer and Control (IS3C):131-134.doi: 10.1109/IS3C.2014.45
  33. 33.
    Fitzgibbon AW (2001) Simultaneous linear estimation of multiple view geometry and lens distortion. In: Proceedings of IEEE Conference on CVPR:125–132.doi: 10.1109/CVPR.2001.990465
  34. 34.
    Furukawa Y, Ponce J (2008) Accurate camera calibration from multi-view stereo and bundle adjustment. Computer Vision and Pattern Recognition, Anchorage, Alaska, USA,:1-8.doi: 10.1109/CVPR.2008.4587681
  35. 35.
    Triggs B, McLauchlan PF, Hartley RI, Fitzgibbon AW (2002) Bundle adjustment-a modern synthesis. Vision algorithms: theory and practice. Volume 1883 of the series Lecture Notes in Computer Science: 298-372.Google Scholar
  36. 36.
    Madsen K, Nielsen HB, Tingleff O (2004) Methods for non-linear least squares problems. 2nd Edition, April 2004.Google Scholar
  37. 37.
    Miroslaw K, Jerzy W, Filip P (2013) Application of reverse engineering for identification of damage and support the reparation of the vehicles. J KONES Powertrain Transp 20(4):155–161Google Scholar
  38. 38.
    Bosemann W (2005) Advances in photogrammetric measurement solutions. Comput Ind 56(8–9):886–893. doi: 10.1016/j.compind.2005.05.014 CrossRefGoogle Scholar
  39. 39.
    Wade P, Moran D, Graham J, Jackson CB (1997) Robust and accurate 3d measurement of formed tube using trinocular stereo vision. The British Machine Vision Conference. BMVC, Essex, UK:1-10.Google Scholar
  40. 40.
    Bergamasco F, Cosmo L, Albareli A, Torsello A (2012) A robust multi-camera 3d ellipse fitting for contactless measurements.2012 Second Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization & Transmission: 168–175. doi: 10.1109/3dimpvt.2012.22
  41. 41.
    Ogniewicz RL (1994) Skeleton-space: a multiscale shape description combining region and boundary information, Proc of IEEE Comp Soc Conf Comp Vis Pattern Recogn: 746–751.doi: 10.1109/CVPR.1994.323891
  42. 42.
    Zoran M, Najdan V, Marko M, Bojan B (2014) New hybrid vision-based control approach for automated guided vehicles. Int J Adv Manuf Technol 66(1):231–249. doi: 10.1016/0004-3702(95)00022-4 Google Scholar
  43. 43.
    Zhang Z, Deriche R, Faugeras O (1995) A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Artif Intell 78(1–2):87–119CrossRefGoogle Scholar
  44. 44.
    Torr PHS, Zisserman A (1997) Robust parameterization and computation of the trifocal tensor. Image Vis Comput 15(8):591–605. doi: 10.1016/S0262-8856(97)00010-3 CrossRefGoogle Scholar
  45. 45.
    Kolev K, Brox T, Cremers D (2012) Fast joint estimation of silhouettes and dense 3d geometry from multiple images. IEEE T Pattern Anal 34(3):493–505. doi: 10.1109/TPAMI.2011.150 CrossRefGoogle Scholar
  46. 46.
    Lukacs G, Martin R, Marshall D (1998) Faithful least-squares fitting of spheres, cylinders, cones and tori for reliable segmentation. In 5th European Conference on Computer Vision, Lecture Notes in Computer Science, Vol. 1406, Springer: 671-686. doi: 10.1007/bfb0055697
  47. 47.
    Shojaei R, Sohrabi M, Amjadi MA (2010) Statistical measurement system analysis of ruston TA1750 gas turbine 1st stage nozzle. Adv Math Comput Meth: 29–33Google Scholar
  48. 48.
    Rahmati SHA, Amalnick MS (2015) Fuzzy gauge capability (Cg and Cgk) through buckley approach. Int J Mech Aerosp Ind Mechatron Manuf Eng 9(8):1467–1470Google Scholar
  49. 49.
    Li H, Yang H, Song FF, Zhang M, Li GJ (2012) Springback characterization and behaviors of high-strengh ti-3ai-2.5v tube in cold rotary draw bending. J Mater Process Tech 212(9):1973–1987. doi: 10.1016/j.jmatprotec.2012.04.022 CrossRefGoogle Scholar
  50. 50.
    Chaibi Y, Cresson T, Aubert B, Hausselle J, Neyret P, Hauger O, de Guise JA, Skalli W (2012) Fast 3d reconstruction of the lower limb using a parametric model and statistical inferences and clinical measurements calculation from biplanar x-rays. Comput Method Biomecc 15(5):457–466. doi: 10.1080/10255842.2010.540758 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd. 2017

Authors and Affiliations

  1. 1.Laboratory of Digital Manufacturing, School of Mechanical EngineeringBeijing Institute of TechnologyBeijingChina

Personalised recommendations