A Real-Time Occlusion Aware Hardware Structure for Disparity Map Computation

  • Christos Georgoulas
  • Ioannis Andreadis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5716)

Abstract

Many machine vision applications deal with depth estimation in a scene. Disparity map recovery from a stereo image pair has been extensively studied by the computer vision community. Previous methods are mainly restricted to software based techniques on general-purpose architectures, presenting relatively high execution time due to the computationally complex algorithms involved. In this paper a new hardware module suitable for real-time disparity map computation module is realized. This enables a hardware based occlusion-aware parallel-pipelined design, implemented on a single FPGA device with a typical operating frequency of 511 MHz. It provides accurate disparity map computation at a rate of 768 frames per second, given a stereo image pair with a disparity range of 80 pixels and 640x480 pixel spatial resolution. The proposed method allows a fast disparity map computational module to be built, enabling a suitable module for real-time stereo vision applications.

Keywords

FPGA-hardware implementation occlusions real–time imaging disparity maps color image processing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barnard, S.T., Thompson, W.B.: Disparity analysis of images. IEEE Transactions on Pattern Analysis and Machine Intelligence 2, 333–340 (1980)CrossRefGoogle Scholar
  2. 2.
    Di Stefano, L., Marchionni, M., Mattoccia, S.: A fast area-based stereo matching algorithm. Image and Vision Computing 22(12), 983–1005 (2004)CrossRefGoogle Scholar
  3. 3.
    Muhlmann, K., Maier, D., Hesser, J., Manner, R.: Calculating dense disparity maps from color stereo images, an efficient implementation. Int. J. Comput. Vision 47(1-3), 79–88 (2002)CrossRefMATHGoogle Scholar
  4. 4.
    Jordan, J.R., Bovik, A.C.: Using chromatic information in edge-based stereo correspondence. Computer Vision, Graphics, and Image Processing: Image Understanding 54(1), 98–118 (1991)MATHGoogle Scholar
  5. 5.
    Baumberg, A.: Reliable feature matching across widely separated views. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 774–781 (2000)Google Scholar
  6. 6.
    Hirschmuller, H.: Improvements in Real-Time Correlation-Based Stereo Vision. In: Proceedings of IEEE Workshop on Stereo and Multi-Baseline Vision, pp. 141–148 (2001)Google Scholar
  7. 7.
    Brown, M., Burschka, D., Hager, G.: Advances in computational stereo. IEEE Transactions on Image Processing 25, 993–1008 (2003)Google Scholar
  8. 8.
    Georgoulas, C., Kotoulas, L., Sirakoulis, G., Andreadis, I., Gasteratos, A.: Real-Time Disparity Map Computation Module. Journal of Microprocessors & Microsystems 32(3), 159–170 (2008)CrossRefGoogle Scholar
  9. 9.
    Georgoulas, C., Andreadis, I.: A real-time fuzzy hardware structure for disparity map computation. Submitted to Journal of Real-Time Image ProcessingGoogle Scholar
  10. 10.
    Chang, C., Chatterjee, S., Kube, P.R.: On an Analysis of Static Occlusion in Stereo Vision. In: Proceedings of Computer Vision and Pattern Recognition, pp. 722–723 (1991)Google Scholar
  11. 11.
    Fua, P.: A Parallel Stereo Algorithm that Produces Dense Depth Maps and Preserves Image Features. Machine Vision and Applications 6(1), 35–49 (1993)CrossRefGoogle Scholar
  12. 12.
    Bhat, D.N., Nayar, S.K.: Ordinal Measures for Image Correspondence. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(4), 415–423 (1998)CrossRefGoogle Scholar
  13. 13.
    Sara, R., Bajcsy, R.: On Occluding Contour Artifacts in Stereo Vision. In: Proceedings of Computer Vision and Pattern Recognition, pp. 852–857 (1997)Google Scholar
  14. 14.
    Belhumeur, P.N.: A Bayesian Approach to Binocular Stereopsis. Int. J. Computer Vision 19(3), 23–260 (1996)CrossRefGoogle Scholar
  15. 15.
    Birchfield, S., Tomasi, C.: Depth Discontinuities by Pixel-to- Pixel Stereo. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1073–1080 (1998)Google Scholar
  16. 16.
    Faugeras, O., et al.: Real-time correlation-based stereo: algorithm, implementations and application. Technical Report RR 2013, INRIA (1993)Google Scholar
  17. 17.
    Konolige, K.: Small vision systems: Hardware and implementation. In: 8th International Symposium on Robotics Research, Hayama, Japan, pp. 203–212. Springer, London (1997)Google Scholar
  18. 18.
    Matthies, L., Kelly, A., Litwin, T.: Obstacle detection for unmanned ground vehicles: A progress report. In: International Symposium of Robotics Research, Munich, Germany (1995)Google Scholar
  19. 19.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vision 47(1-3), 7–42 (2002)CrossRefMATHGoogle Scholar
  20. 20.
    Leeser, M., Hauck, S., Tessier, R.: Editorial: field-programmable gate arrays in embedded systems. EURASIP Journal on Embedded Systems (1), 11 (2006)Google Scholar
  21. 21.
    Gong, M., Yang, Y.H.: Near real-time reliable stereo matching using programmable graphics hardware. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 924–931 (2005)Google Scholar
  22. 22.
    Kim, J.C., Lee, K.M., Choi, B.T., Lee, S.U.: A dense stereo matching using two-pass dynamic programming with generalized ground control points. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1075–1082 (2005)Google Scholar
  23. 23.
    Gong, M., Yang, Y.H.: Real-Time Stereo Matching Using Orthogonal Reliability-Based Dynamic Programming. IEEE Transactions on Image Processing 16(3), 879–884 (2007)MathSciNetCrossRefGoogle Scholar
  24. 24.
    Veksler, O.: Extracting Dense Features for Visual Correspondence with Graph Cuts. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 689–694 (2003)Google Scholar
  25. 25.
    Gong, M., Yang, Y.H.: Fast Unambiguous Stereo Matching Using Reliability-Based Dynamic Programming. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(6), 998–1003 (2005)CrossRefGoogle Scholar
  26. 26.
    Khaleghi, B., Ahuja, S., Wu, J.Q.M.: A new Miniaturized Embedded Stereo-Vision System (MESVS-I). In: Proceedings of Canadian Conference on Computer and Robot Vision, pp. 26–33 (2008)Google Scholar
  27. 27.
    Woodill, J.I., Buck, R., Jurasek, D., Gordon, G., Brown, T.: 3D Vision: Developing an Embedded Stereo-Vision System. IEEE Computer 40(5), 106–108 (2007)CrossRefGoogle Scholar
  28. 28.
    Miyajima, Y., Maruyama, T.: A Real-Time Stereo Vision System with FPGA. In: Y. K. Cheung, P., Constantinides, G.A. (eds.) FPL 2003. LNCS, vol. 2778, pp. 448–457. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  29. 29.
    Ambrosch, K., Humenberger, M., Kubinger, W., Steininger, A.: SAD-based Stereo Matching Using FPGAs. In: Embedded Computer Vision part II, pp. 121–138. Springer, London (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Christos Georgoulas
    • 1
  • Ioannis Andreadis
    • 1
  1. 1.Laboratory of Electronics Department of Electrical and Computer EngineeringDemocritus University of ThraceXanthiGreece

Personalised recommendations