Directionally Weakened Diffusion for Optical Flow

Abstract:

Optical flow estimation from image sequences is of paramount importance to computer vision applications. Many optical flow algorithms have been proposed for optical flow computation, which minimize a certain energy function involving a data term and a smoothness term. In this paper, we propose a new method to compute optical flow by decomposing the Laplacian operator along the tangential and gradient direction of the image. Experimental results show that the new method could gain more accurate estimation of optical flow around motion discontinuities compared with the classical methods.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 2449-2452
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.2449
• Online since: November 2011
• Authors: Jie Zhao, Huai Bin Wang, Yuan Quan Wang
• Keywords: Directionally Weakened Diffusion, Global Smoothness, Optical Flow

References

[1] Horn, B., & Schunck, B. Determining optical flow. Artificial Intelligence, Vol. 17, (1981), p.185–203.

DOI: 10.1016/0004-3702(81)90024-2

[2] Nagel, H. -H., & Enkelmann, W. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 3, (1986), p.565–593.

DOI: 10.1109/tpami.1986.4767833

[3] Sun, D., Roth, S., Lewis, J., & Black,M. Learning optical flow. In Proceedings of the European conference on computer vision. Vol. 3, (2008), p.83–97.

[4] Zimmer, H., Bruhn, A., Weickert, J., Valgaerts, L., Salgado, A., Rosenhahn, B., & Seidel, H. -P. Complementary optic flow. In Proceedings of seventh international workshop on energy minimization methods in computer vision and pattern recognition. (2009).

DOI: 10.1007/978-3-642-03641-5_16

[5] Seitz, S., & Baker, S. Filter flow. In Proceedings of the IEEE international conference on computer vision. (2009).

[6] Trobin, W., Pock, T., Cremers, D., & Bischof, H. Continuous energy minimization via repeated binary fusion. In Proceedings of the European conference on computer vision. Vol. 4, (2008), p.677–690.

DOI: 10.1007/978-3-540-88693-8_50

[7] Nir, T., Bruckstein, A., &Kimmel, R. Over-parameterized variational optical flow. International Journal of Computer Vision, Vol. 76, (2008), p.205–216.

DOI: 10.1007/s11263-007-0051-2

[8] Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In Pajdla, T., Matas, J., eds.: Computer Vision – ECCV 2004, Part IV. Vol. 3024, (2004), p.25–36.

DOI: 10.1007/978-3-540-24673-2_3

[9] Bruhn, A., Weickert, J. Towards ultimate motion estimation: Combining highest accuracy with real-time performance. In Proceedings of the Tenth International Conferenceon Computer Vision. Vol. 1, (October 2005), p.749–755.

DOI: 10.1109/iccv.2005.240

[10] Baker, S., & Matthews, I. Lucas-Kanade 20 years on: a unifying framework. International Journal of Computer Vision, Vol. 46, (2004), p.221–255.

DOI: 10.1023/b:visi.0000011205.11775.fd

[11] Xiao Jia, Yuanquan Wang. An Edge Preserving Gradient Vector Flow for Active Contours. In Proceedings of the 2nd International Congress on Image and Signal, (Oct. 2009), pp.1-4.

DOI: 10.1109/cisp.2009.5304695