Advertisement

A Hardware-Friendly Adaptive Tensor Based Optical Flow Algorithm

  • Zhao-Yi Wei
  • Dah-Jye Lee
  • Brent E. Nelson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4842)

Abstract

A tensor-based optical flow algorithm is presented in this paper. This algorithm uses a cost function that is an indication of tensor certainty to adaptively adjust weights for tensor computation. By incorporating a good initial value and an efficient search strategy, this algorithm is able to determine optimal weights in a small number of iterations. The weighting mask for the tensor computation is decomposed into rings to simplify a 2D weighting into 1D. The devised algorithm is well-suited for real-time implementation using a pipelined hardware structure and can thus be used to achieve real-time optical flow computation. This paper presents simulation results of the algorithm in software, and the results are compared with our previous work to show its effectiveness. It is shown that the proposed new algorithm automatically achieves equivalent accuracy to that previously achieved via manual tuning of the weights.

Keywords

Optical Flow Structure Tensor Active Contour Model Weighting Process Mask Size 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Farnebäck, G.: Very high accuracy velocity estimation using orientation tensors, parametric motion, and simultaneous segmentation of the motion field. In: Proc. ICCV, vol. 1, pp. 77–80 (2001)Google Scholar
  2. 2.
    Farnebäck, G.: Fast and accurate motion estimation using orientation tensors and parametric motion models. In: Proc. ICPR., vol. 1, pp. 135–139 (2000)Google Scholar
  3. 3.
    Liu, H., Chellappa, R., Rosenfeld, A.: Accurate dense optical flow estimation using adaptive structure tensors and a parametric model. IEEE Trans. Image Processing 12, 1170–1180 (2003)CrossRefGoogle Scholar
  4. 4.
    Haussecker, H., Spies, H.: Handbook of Computer Vision and Application, vol. 2, ch. 13, Academic, New York (1999)Google Scholar
  5. 5.
    Wang, H., Ma, K.: Structure tensor-based motion field classification and optical flow estimation. In: Proc. ICICS-PCM, vol. 1, pp. 66–70 (2003)Google Scholar
  6. 6.
    Previous publication hidden for blind reviewGoogle Scholar
  7. 7.
    Correia, M., Campilho, A.: Real-time implementation of an optical flow algorithm. In: Proc. ICIP, vol. 4, pp. 247–250 (2002)Google Scholar
  8. 8.
    Zuloaga, A., Martín, J.L, Ezquerra, J.: Hardware architecture for optical flow estimation in real time. In: Proc. ICIP, vol. 3, pp. 972–976 (1998)Google Scholar
  9. 9.
    Martín, J.L., Zuloaga, A., Cuadrado, C., Lázaro, J., Bidarte, U.: Hardware implementation of optical flow constraint equation using FPGAs. In: Computer Vision and Image Understanding, vol. 98, pp. 462–490 (2005)Google Scholar
  10. 10.
    Díaz, J., Ros, E., Pelayo, F., Ortigosa, E.M., Mota, S.: FPGA-based real-time optical-flow system. IEEE Trans. Circuits and Systems for Video Technology 16(2), 274–279 (2006)CrossRefGoogle Scholar
  11. 11.
    Middendorf, M., Nagel, H.–H.: Estimation and interpretation of discontinuities in optical flow fields. In: Proc. ICCV, vol. 1, pp. 178–183 (2001)Google Scholar
  12. 12.
    Kühne, G., Weickert, J., Schuster, O., Richter, S.: A tensor-driven active contour model for moving object segmentation. In: Proc. ICIP, vol. 2, pp. 73–76 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Zhao-Yi Wei
    • 1
  • Dah-Jye Lee
    • 1
  • Brent E. Nelson
    • 1
  1. 1.Department of Electrical and Computer Engineering, Brigham Young University, Provo, UTUSA

Personalised recommendations