Advertisement

Range and Intensity Vision for Rock-Scene Segmentation

  • Simphiwe Mkwelo
  • Frederick Nicolls
  • Gerhard de Jager
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

This paper presents a methodology for the automatic segmentation of rock-scenes using a combination of range and intensity vision. A major problem in rock scene segmentation is the effect of noise in the form of surface texture and color density variations, which causes spurious segmentations. We show that these problems can be avoided through pre-attentive range image segmentation followed by focused attention to edges. The segmentation process is inspired by the Human Visual System’s operation of using a priori knowledge from pre-attentive vision for focused attention detail. The result is good rock detection and boundary accuracy that can be attributed to independence of range data to texture and color density variations, and knowledge driven intensity edge detection respectively. Preliminary results on a limited image data-set are promising.

Keywords

surface texture color density variations range image segmentation intensity edge detection 

References

  1. 1.
    Lange, T.B: Measurement of the size distribution of rocks on a conveyor belt using machine vision, PhD thesis at the University of Witwatersrand (1990)Google Scholar
  2. 2.
    Crida, R.C.: A machine vision approach to rock fragmentation, PhD thesis at the University of Cape Town (1995)Google Scholar
  3. 3.
    Mkwelo, S., De Jager, G., Nicolls, F.: Watershed-based Segmentation of Rock Scenes and Proximitybased Classification of Watershed Regions Under Uncontrolled Lighting. SAIEE Transactions, Research Journal of SAIEE 96(1), 28–34 (2005)Google Scholar
  4. 4.
    Sudhakar, J., Adhikari, G.R., Gupta, R.N.: Comparison of Fragmentation Measurements by Photographic and Image Analysis Techniques. Rock Mechanics and Rock Engineering 39(2), 159–168 (2005)CrossRefGoogle Scholar
  5. 5.
    Kemeny, J.: The Split-Online Fragmentation Analysis System (February 12, 2006), www.spliteng.com/splitonline/fragmentation.asp
  6. 6.
    Franklin, J.: Granulometry Analysis Software (February 12, 2006), www.wipware.com/wipfrag.php
  7. 7.
    Maerz, N.H., Zhou, W.: Optical Digital Fragmentation Measuring Systems-Inherent Sources of Error. FRAGBLAST The International Journal for Blasting and Fragmentation 2(4), 415–431 (1998)Google Scholar
  8. 8.
    Thurley, M.J: Three Dimensional Data Analysis for Separation and Sizing of Rock Piles in Mining. PhD Thesis, Monash University, Department Electrical and Computer Systems Engineering (2002)Google Scholar
  9. 9.
    Luo, R.C., Yih, C.C., Su, K.L.: Multisensor fusion and integration: Approaches, Applications and Future Directions. IEEE Sensors Journal 2(2) (2002)Google Scholar
  10. 10.
    Shah, S., Argarwal, J.K., Eledah, J., Ghosh, J.: Multisensor Integration for scene classification: An experiment in human form detection. In: International Conference on Image Processing, Santa Barbara, October 26-29, 1997 (1997)Google Scholar
  11. 11.
    Neira, J., Tardos, J.D., Horn, J., Schmidt, G.: Fusing range an intensity images for mobile robot localization. IEEE Transactions on robotics and automation 15(1) (1999)Google Scholar
  12. 12.
    Umeda, K., Arai, K.: Industrial vision system by fusing range and intensity image. In: Proc. of IEEE Int. Conf. on Multisensor fusion and integration for Intelligent Systems, October 2-5, 1994 (1994)Google Scholar
  13. 13.
    Zhang, Y., Sun, Y., Sari-Sarraf, H., Aidi, M.A.: Imapact of Intensity Edge Map on Segmentation of noisy range images. In: Proc. of Spie Conf. on Three Dimensional Capture and Applications III, San Jose,CA, vol. 3958, pp. 260–269 (2000)Google Scholar
  14. 14.
    Besl, P.J., Jain, R.C.: Segmentation Through Variable Order Surface Fitting. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI 10(2), 167–192 (1988)CrossRefGoogle Scholar
  15. 15.
    Han, F., Tu, Z., Zhu, S.: Range image segmentation by an effective jump diffusion method. IEEE Transactions on pattern analysis and machine intelligence 26(9) (2004)Google Scholar
  16. 16.
    Gee, L.A, Abidi, M.A.: Segmentation of range images using morphological operations: Review and examples. In: SPIE Conference on Intelligent Robots and Computer Vision XIV, Philadelphia, PA, vol. 2588, pp. 734–746 (October 1995)Google Scholar
  17. 17.
    Mkwelo, S., De Jager, G., Nicolls, F.: Three Dimensional rock-scene modelling using dense stereo reconstruction. In: 13th Proceedings of PRASA (November 2006)Google Scholar
  18. 18.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two frame stereo correspondence algorithms. International Journal of Computer Vision 47(1), 7–42 (2002)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Simphiwe Mkwelo
    • 1
  • Frederick Nicolls
    • 2
  • Gerhard de Jager
    • 2
  1. 1.Defence Peace Security and Safety, Council for Scientific and Industrial Research (CSIR), Meiring Naude road, Lynnwood, Pretoria 0002South Africa
  2. 2.Department of Electrical Engineering, University of Cape Town, Rondebosch 7700South Africa

Personalised recommendations