Abstract
While most of the techniques for inferring optical flow are based on the brightness constancy assumption, various conditions including the presence of motion blur evidently violate this fundamental presumption. If the source image and the target image appear to be dissimilar due to different blur kernels, traditional methods will fail to achieve accurate results. We present a new method, MB-CLG, that considers constructing a new pair of blurred frames, followed by regular optical flow computation. The proposed method employs a coarse-to-fine approach, in conjunction with a smoothness matrix to account for occluded regions. Rather than warping frames or precomputing a large grid of derivatives, MB-CLG warps the flows at each iteration. This leads to lower computational cost, and requires less data storage. Based on the results for various sequences, MB-CLG outperforms existing optical flow methods in the sense of AAE, AEP and MSE.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Tull, D., Katsaggelos, A.: Regularized blur-assisted displacement field estimation. In: Proc. International Conference on Image Processing, vol. 3, pp. 85–88 (1996)
Jin, H., Favaro, P., Cipolla, R.: Visual tracking in the presence of motion blur. In: CVPR 2005, vol. 2, pp. 18–25 (2005)
Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Intl. Conf. on Artificial Intelligence, pp. 674–679 (1981)
Horn, B.K., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
Bruhn, A., Weickert, J., Schnörr, C.: Lucas/kanade meets horn/schunck: Combining local and global optic flow methods. Intl. J. of Computer Vision 61, 211–231 (2005)
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping, pp. 25–36. Springer (2004)
Sun, D., Roth, S., Black, M.: Secrets of optical flow estimation and their principles. In: CVPR 2010, pp. 2432–2439 (2010)
Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vision 92, 1–31 (2011)
Black, M.J., Anandan, P.: The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Comput. Vis. Image Underst. 63, 75–104 (1996)
Lee, D., Jeong, S., Lee, Y., Song, B.C.: Video deblurring algorithm using accurate blur kernel estimation and residual deconvolution based on a blurred-unblurred frame pair. IEEE Transactions on Image Processing 22, 926–940 (2013)
Yuan, L., Sun, J., Quan, L., Shum, H.Y.: Blurred/non-blurred image alignment using sparseness prior. In: ICCV, pp. 1–8 (2007)
Cho, S., Matsushita, Y., Lee, S.: Removing non-uniform motion blur from images. In: ICCV 2007, pp. 1–8 (2007)
Mei, C., Reid, I.: Modeling and generating complex motion blur for real-time tracking. In: CVPR 2008, pp. 1–8 (2008)
Portz, T., Zhang, L., Jiang, H.: Optical flow in the presence of spatially-varying motion blur. In: IEEE CVPR, pp. 1752–1759 (2012)
Weickert, J., Schnörr, C.: A theoretical framework for convex regularizers in pde-based computation of image motion. Intl. J. of Comput. Vision 45, 245–264 (2001)
Liu, C.: Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. Doctoral thesis, Massachusetts Institute of Technology (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Daraei, M.H. (2014). Optical Flow Computation in the Presence of Spatially-Varying Motion Blur. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2014. Lecture Notes in Computer Science, vol 8887. Springer, Cham. https://doi.org/10.1007/978-3-319-14249-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-14249-4_14
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14248-7
Online ISBN: 978-3-319-14249-4
eBook Packages: Computer ScienceComputer Science (R0)