Abstract
There are several optical flow models which aim to capture spatial characteristics of the flow such as divergence and curl. However accurate estimation is often a key challenge. In this context, we propose a variational optical flow model motivated by the harmonic-constraint based regularization for improving the estimation of rotation in motion. Our model is the standard Horn and Schunck model with an additional constraint penalizing the curl of the flow with an anisotropic weight term. Our implementation scheme is based on the robust Chambolle-Pock primal-dual algorithm. Further, to refine the flow-edges, we use the heuristic of weighted median filtering in our algorithm as a post-processing step. The results of our model indicate that it is comparable to, and in some cases, outperform some of the top-performing variational methods across multiple datasets in both angular and end-point errors.
Similar content being viewed by others
Data Availability
The image sequences (data) used for this study are publicly available from the following sources: https://github.com/Tianshu-Liu/OpenOpticalFlow as a supplementary material to [21]. https://www.vision.middlebury.edu/flow as a supplementary material to [4]. http://visual.cs.ucl.ac.uk/pubs/flowConfidence/supp/ as a supplementary material to [1]. http://sintel.is.tue.mpg.de/downloads as a supplementary material to [10].
References
Aoudha MO, Humayun A, Pollefeys M, Brostow GJ. Learning a confidence measure for optical flow. IEEE Trans Pattern Anal Mach Intell. 2013;35(5):1107–20. https://doi.org/10.1109/TPAMI.2012.171.
Aoudha MO, Humayun A, Pollefeys M, Brostow GJ, UCL Datasets Project Page. http://visual.cs.ucl.ac.uk/pubs/flowConfidence/supp/. Accessed December 2023.
Aubert G, Deriche R, Kornprobst P. Computing optical flow via variational techniques. SIAM J Appl Math. 1999;60:156–82. https://doi.org/10.1137/S0036139998340170.
Baker S, Scharstein D, Lewis J, Roth S, Black MJ, Szeliski R, A database and evaluation methodology for optical flow. In: IEEE international comference on computer vision. 2007, p. 1–8. https://www.doi.org/10.1109/ICCV.2007.4408903
Baker S, Scharstein D, Lewis J, Roth S, Black MJ, Szeliski R, Middlebury stereo vision page. www.vision.middlebury.edu/flow. Accessed 21 Aug 2022.
Barron JL, Fleet DJ, Beauchemin SS. Performance of optical flow techniques. Int J Comput Vis. 1994;12(1):43–77. https://doi.org/10.1007/BF01420984.
Black MJ, Sapiro G, Marimont DH, Heeger D. Robust anisotropic diffusion. IEEE Trans Image Process. 1998;7(3):421–32.
Brox T, Bruhn A, Papenberg N, Weickert J, High accuracy optical flow estimation based on a theory of warping. In: European conference on computer vision, Lecture notes in computer science. Berlin: Springer; 2004, Vol. 3024, p. 25–36. https://doi.org/10.1007/978-3-540-24673-2_3
Bruhn A, Weickert J, Toward ultimate motion estimation: combining highest accuracy with real-time performance. In: IEEE international conference on computer vision, 2005; p. 749–55. https://doi.org/10.1109/ICCV.2005.240
Buttler DJ, Wulff J, Stanley BG, Black MJ. A naturalistic open source movie for optical flow evaluation. Eur Conf Comput Vis. 2012;7577:611–25. https://doi.org/10.1007/978-3-642-33783-3_44.
Buttler DJ, Wulff J, Stanley BG, Black MJ, MPI Sintel Datasets. http://sintel.is.tue.mpg.de/downloads. Accessed December 2023.
Corpetti T, Mémin E, Pérez P, Estimating fluid optical flow. In: Proceedings of the 15th international conference on pattern recognition, 2000; vol. 3, p. 1033–6. https://doi.org/10.1109/ICPR.2000.903722
Chambolle A, Pock T. A first-order primal-dual algorithm for convex problems with applications in imaging. J Math Imaging Vis. 2011;40:120–45. https://doi.org/10.1007/s10851-010-0251-1.
Dirks H, Variational methods for joint motion estimation and image reconstruction, Ph.D. Thesis, Wilhems-Universität, 2015.
Doshi H, Kiran NU. Nonlinear evolutionary PDE-based refinement of optical flow. Mach Graph Vis. 2021;30(1/4):45–65. https://doi.org/10.22630/MGV.2021.30.1.3.
Hinterberger W, Scherzer O, Schnörr C, Weickert J. Analysis of optical flow models in the framework of calculus of variations. Numer Funct Anal Optim. 2002;23(1 &2):69–89. https://doi.org/10.1081/NFA-120004011.
Horn BKP, Schunck BG. Determining optical flow. Artif Intell. 1981;17:185–203. https://doi.org/10.1016/0004-3702(81)90024-2.
Kawakami T, Yamaguchi T, Harada H, Estimation of rotation and divergence from optical flow constraint. In: International conference on control, automation and systems, 2008; p. 2538–42. https://doi.org/10.1109/ICCAS.2008.4694282
Kohlberger T, Mémin E, Schnörr C. Variational dense motion estimation using Helmholtz Decomposition. In: International conference on scale-space theories in computer vision. 2003; vol. 2695, p. 432–48. https://doi.org/10.1007/3-540-44935-3_30.
Li Y, Osher S. A new median formula with applications to PDE based denoising. Commun Math Sci. 2009;7(3):741–53. https://doi.org/10.4310/CMS.2010.v8.n4.a16.
Liu T. OpenOpticalFlow: an open source program for extraction of velocity fields from flow visualization images. J Open Res Softw. 2017;5:29. https://doi.org/10.5334/jors.168.
Luttmann A, Bollt EM, Basnayake R, Kramer S, Tufillaro N. A framework for estimating potential flow from digital imagery. Chaos Interdiscip J Nonlinear Sci. 2013. https://doi.org/10.1063/1.4821188.
McCane B, Novins K, Crannitch D, Galvin B. On benchmarking optical flow. Comput Vis Image Underst. 2001;84:126–43. https://doi.org/10.1006/cviu.2001.0930.
Nagel HH, Enkelmann W. An investigation of the smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans Pattern Anal Mach Intell. 1986;8:565–93. https://doi.org/10.1109/TPAMI.1986.4767833.
Otte M, Nagel HH. Estimation of optical flow based on higher-order spatiotemporal derivatives in interlaced and non-interlaced image sequences. Artif Intell. 1995;78:5–43. https://doi.org/10.1016/0004-3702(95)00033-X.
Pan L, Liu M, Hartley R. Single image optical flow estimation with an event camera. Comput Vis Pattern Recognit. 2020. https://doi.org/10.1109/cvpr42600.2020.00174.
Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell. 1990;12(7):629–39. https://doi.org/10.1109/34.56205.
Sun D, Roth R, Black MJ, Secrets of optical flow estimation and their principles. In: IEEE computer society conference on computer vision and pattern recognition. 2010; p. 2432–9. https://doi.org/10.1109/CVPR.2010.5539939
Sun D, Roth S, Black MJ. A quantitative analysis of current practices in optical flow estimation and the principles behind them. Int J Comput Vis. 2014;106(2):115–37. https://doi.org/10.1007/s11263-013-0644-x.
Sun H, Tai X, Yuan J. Variational image motion estimation by preconditioned dual optimization. Inverse Probl Imaging. 2023;17(2):319–37. https://doi.org/10.3934/ipi.2022043.
Suter D, Motion estimation and vector splines. In: Computer vision and pattern recognition, 1994; p. 939-42. https://doi.org/10.1109/CVPR.1994.323929
Tu Z, Poppe R, Veltkamp RC. Adaptive guided image filter for warping in variational optical flow computation. Signal Process. 2016;127:253–65. https://doi.org/10.1016/j.sigpro.2016.02.018.
Tu Z, Xie W, Zhang D, Poppe R, Veltkamp RC, Li B, Yuan J. A survey of variational and CNN-based optical flow techniques. Signal Process Image Commun. 2019;72:9–24. https://doi.org/10.1016/j.image.2018.12.002.
Wedel A, Pock T, Zach C, Cremers D, Bischof H. An improved algorithm for TV-\(L^1\) Optical Flow. Dagstuhl Motion Workshop. 2008. https://doi.org/10.1007/978-3-642-03061-1_2.
Weickert J, Schnörr C. A theoritical framework for convex regularizers in PDE-based computation of image motion. Int J Comput Vis. 2001;45:245–64. https://doi.org/10.1023/A:1013614317973.
Weickert J, Anisotropic diffusion in image processing, ser. ECMI Series. Stuttgart, Germany:Teubner-Verlag; 1998.
Zhao J, Wang Y, Wang H. Optical flow with harmonic constraint and oriented smoothness. Int Conf Image Graph. 2011. https://doi.org/10.1109/ICIG.2011.122.
Zhang C, Zhu L, Chen Z, Kong D, Shang X, An improved evaluation method for optial flow of endpoint error. In: International conference on computer networks and communication technology, 2016; p. 312–7. https://doi.org/10.2991/cnct-16.2017.44
Zhang C, Ge L, Chen Z, Qin R, Li M, Liu W. Guided filtering: toward edge-preserving for optical flow. IEEE Access. 2018;6:26958–71. https://doi.org/10.1109/ACCESS.2018.2831920.
Acknowledgements
The authors express their deep sense of gratitude of Bhagawan Sri Sathya Sai Baba, Revered Founder Chancellor, SSSIHL.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Doshi, H., Kiran, N.U. A Variational Optical Flow Model for Accurate Motion Estimation from Rotational Image Sequences. SN COMPUT. SCI. 5, 359 (2024). https://doi.org/10.1007/s42979-024-02697-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-024-02697-5