Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Detection of morphology defects in pipeline based on 3D active stereo omnidirectional vision sensor

There are many kinds of defects in pipes, which are difficult to detect with a low degree of automation. In this work, a novel omnidirectional vision inspection system for detection of the morphology defects is presented. An active stereo omnidirectional vision sensor is designed to obtain the texture and depth information of the inner wall of the pipeline in real time. The camera motion is estimated and the space location information of the laser points are calculated accordingly. Then, the faster region proposal convolutional neural network (Faster R-CNN) is applied to train a detection network on their image database of pipe defects. Experimental results demonstrate that system can measure and reconstruct the 3D space of pipe with high quality and the retrained Faster R-CNN achieves fine detection results in terms of both speed and accuracy.

References

    1. 1)
      • 18. Suo, C.B., Yang, D.Q., Liu, Y.P.: ‘Comparing sift, surf, brisk, orb and freak in some different perspectives’, Beijing Surv. Mapp., 2014, 04, (1), pp. 2326.
    2. 2)
      • 9. Li, J.X., Wu, E.Q., Ke, Y.L.: ‘New inner surface profile sensor for mini-diameter pipes’, J. Zhejiang Univ., 2006, 40, (9), pp. 16191623.
    3. 3)
      • 5. Kannala, J., Brandt, S.S., Heikkila, J.: ‘Measuring and modelling sewer pipes from video’, Mach. Vis. Appl., 2008, 19, (2), pp. 7383.
    4. 4)
      • 19. Zhou, J., Chen, L., Liu, Q., et al: ‘Fast and accurate ransac based on optimal sequential probability test and local optimization’, Chin. J. Sci. Instrum., 2012, 33, (9), pp. 20372044.
    5. 5)
      • 11. Zhang, Y.H., Jin, C.Y., Wang, Y.: ‘Detection of pipe holes and threi reconstruction base on circle-structured light’, J. Beijing Univ. Chem. Technol., 2012, 39, (5), pp. 113117.
    6. 6)
      • 2. Tang, Y., Pan, M.C., Luo, F.L., et al: ‘Detection of corrosion in pipeline using pulsed magnetic flux leakage testing’, Comput. Meas. Control, 2010, 18, (1), pp. 3843.
    7. 7)
      • 13. Tang, Y.P., Wang, Q., Zong, M.L., et al: ‘Design of vertically aligned binocular omnistereo vision sensor’, Chin. J. Sens. Actuators, 2010, 2010, (1), p. 624271.
    8. 8)
      • 12. Yamazawa, K., Yagi, Y., Yachida, M.: ‘Obstacle detection with omnidirectional image sensor hyperomni vision’. Proc. Int. Conf. Robotics and Automation, Aichi, Japan, May 1995, pp. 10621067.
    9. 9)
      • 15. Micusik, B., Pajdla, T.: ‘Estimation of omnidirectional camera model from epipolar geometry’. Proc. Int. Conf. Computer Vision and Pattern Recognition, Madison, USA, June 2003, pp. 485490.
    10. 10)
      • 4. Yang, M., Su, T.C.: ‘Automated diagnosis of sewer pipe defects based on machine learning approaches’, Expert Syst. Appl., 2008, 35, (3), pp. 13271337.
    11. 11)
      • 10. Matsui, K., Yamashita, A., Kaneko, T.: ‘3-D shape reconstruction of pipe with omni-directional laser and omni-directional camera’. Proc. Int. Conf. Asian Society for Precision Engineering and Nanotechnology, Kitakyushu, Japan, November 2009, pp. 15.
    12. 12)
      • 17. Zhu, Q.G., Wang, J., Zhang, P.Z., et al: ‘Research on mobile robot localization based on Gaussian moment improved surf algorithm’, Chin. J. Sci. Instrum., 2015, 36, (11), pp. 24512457.
    13. 13)
      • 7. Yang, M.D., Su, T.C., Pan, N.F., et al: ‘Feature extraction of sewer pipe defects using wavelet transform and co-occurrence matrix’, Int. J. Wavelets Multiresolution Inf. Process., 2011, 9, (2), pp. 211225.
    14. 14)
      • 20. Yang, M.D., Su, T.C., Pan, N.F., et al: ‘Systematic image quality assessment for sewer inspection’, Expert Syst. Appl., 2011, 38, (3), pp. 17661776.
    15. 15)
      • 6. Osama, M., Tariq, S.E.: ‘Automated detection of surface defects in water and sewer pipes’, Autom. Constr., 1999, 8, (5), pp. 581588.
    16. 16)
      • 21. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. Proc. Int. Conf. Computer Vision and Pattern Recognition, Las Vegas, USA, June 2016, pp. 770778.
    17. 17)
      • 8. Duran, O., Althoefer, K., Seneviratne, L.D., et al: ‘Automated pipe defect detection and categorization using camera/laser-based profiler and artificial neural network’, IEEE Trans. Autom. Sci. Eng., 2007, 4, (1), pp. 118126.
    18. 18)
      • 16. Scaramuzza, D., Martinelli, A., Siegwart, R.: ‘A toolbox for easily calibrating omnidirectional cameras’. Proc. Int. Conf. Intelligent Robots and Systems, San Diego, USA, October 2007, pp. 56955701.
    19. 19)
      • 1. Masahiko, H., Hirotsugu, O.: ‘Sh-wave emat technique for gas pipeline inspection’, Nondestruct. Test. Eval. Int., 1999, 32, (3), pp. 127132.
    20. 20)
      • 3. Wang, Y., Wang, J.L.: ‘Optoelectronic inspection of in-pipe surfaces’, J. Appl. Opt., 2008, 29, (5), pp. 735739.
    21. 21)
      • 14. Yi, S., Choi, B., Ahuja, N.: ‘Real-time omni-directional distance measurement with active panoramic vision’, Int. J. Control Autom. Syst., 2008, 5, (2), pp. 184191.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2017.0616
Loading

Related content

content/journals/10.1049/iet-ipr.2017.0616
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address