Advertisement

Contour recognition of roadheader cutting head based on shape matching

  • Yuxin DuEmail author
  • Minming Tong
Industrial and commercial application
  • 9 Downloads

Abstract

In this paper, a shape matching algorithm is presented to perform the cutting head recognition for roadheaders based on a binocular vision system installed on the machine. The shape descriptor is a simplified intersection angle of tangent lines which is firstly proposed on the basis of contour points’ spatial positions. It exhibits significant self-contained property and features describing capacity for both partial and whole shapes. To achieve the best match, the MVM algorithm was improved with skipping and multiple matching penalties to complete the multiple mapping and to skip existing outliers in sequences. More precisely, these advantages make the proposed algorithm less sensible to the local variations caused by varied views. Experimental results demonstrated that the proposed method outperforms existing ones with stronger robustness and higher accuracy. In actual pictures tests, the cutting head recognition rate reached 100% with spatial positioning errors under 2.2 cm, which met the requirements for accurate location in real time.

Keywords

Shape matching Shape descriptor Minimum variance matching (MVM) Shape similarity Object detection 

Notes

References

  1. 1.
    Zhou Y, Liu JT, Bai X (2012) Research and perspective on shape matching. Acta Autom Sin 38:889–910MathSciNetCrossRefGoogle Scholar
  2. 2.
    Hu MK (1962) Visual pattern recognition by moment invariants. IRE Trans Inf Theory 8:179–187zbMATHGoogle Scholar
  3. 3.
    Zahn CT, Roskies RZ (2009) Fourier descriptors for plane closed curves. IEEE Trans Comput C-21:269–281MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Belongie S (2002) Shape Matching and object recognition using shape context. IEEE Trans Pattern Anal Mach Intell 24:509–522CrossRefGoogle Scholar
  5. 5.
    Ling HB, Jacobs DW (2007) Shape classification using the inner-distance. IEEE Trans Pattern Anal Mach Intell 29:286–299CrossRefGoogle Scholar
  6. 6.
    Shu X, Wu XJ (2011) A novel contour descriptor for 2D shape matching and its application to image retrieval. Image Vis Comput 29:286–294CrossRefGoogle Scholar
  7. 7.
    Zheng DC, Min H (2013) Improved shape recognition method based on representative shape context. J Comput Aided Des Comput Graph 25:215–220Google Scholar
  8. 8.
    Yang CZ, Wei H, Yu Q, Yang C, Wei H, Yu Q (2018) A novel method for 2D nonrigid partial shape matching. Neurocomputing 275:1160–1176CrossRefGoogle Scholar
  9. 9.
    Huang WG, Hu DM, Yang JY, Zhu ZK (2015) Chord angle representation for shape matching under occlusion. Opt Precis Eng 23:1758–1767CrossRefGoogle Scholar
  10. 10.
    Vlachos M, Hadjieleftheriou M, Gunopulos D, Keogha E (2003) Indexing multi-dimensional time-series with support for multiple distance measures. In: ACM SIGKDD international conference on knowledge discovery and data mining ACM, pp 216–225Google Scholar
  11. 11.
    Sakoe H, Chiba S (1971) A dynamic programming approach to continuous speech recognition. In: International congress on acoustics, Budapest, pp 65–69Google Scholar
  12. 12.
    Latecki LJ, Wang Q, Koknar-Tezel S, Megalooikonomou V (2007) Optimal subsequence bijection. In: IEEE International conference on data mining IEEE, pp 565–570Google Scholar
  13. 13.
    Latecki LJ, Megalooikonomou V, Wang Q, Yu D (2007) An elastic partial shape matching technique. Pattern Recognit 40:3069–3080CrossRefzbMATHGoogle Scholar
  14. 14.
    Mondal T, Ragot N, Ramel JY, Pal U (2014) Flexible sequence matching technique: application to word spotting in degraded documents. In: International conference on frontiers in handwriting recognition IEEE, pp 210–215Google Scholar
  15. 15.
    Mondal T, Ragot N, Ramel JY, Pal U (2015) Exemplary sequence cardinality: an effective application for word spotting. In: International conference on document analysis and recognition IEEE, pp 1146–1150Google Scholar
  16. 16.
    Du YX, Tong MM, Zhou LL, Dong HB (2016) Edge detection based on Retinex theory and wavelet multi-scale product for mine images. Appl Opt 55:9625–9637CrossRefGoogle Scholar
  17. 17.
    Tian J (2010) Research on boom-type roadheader auto cutting and profiling control system. CUMT(Beijing), BeijingGoogle Scholar
  18. 18.
    Zhang XH, Liu YW, Yang WJ, Mao QH, Wang DM, Zhou Y (2018) Vision measurement system for cutting head attitude of mine-used boom-type roadheader. Ind Mine Autom 44:63–67CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Information and Electrical EngineeringChina University of Mining and TechnologyXuzhouChina
  2. 2.School of Mechanical and Electrical EngineeringXuzhou University of TechnologyXuzhouChina

Personalised recommendations