Abstract
We show how pixel-based methods can be applied to a sparse image representation resulting from a superpixel segmentation. On this sparse image representation we only estimate a single motion vector per superpixel, without working on the full-resolution image. This allows the accelerated processing of high-resolution content with existing methods. The use of superpixels in optical flow estimation was studied before, but existing methods typically estimate a dense optical flow field – one motion vector per pixel – using the full-resolution input, which can be slow. Our novel approach offers important speed-ups compared to dense pixel-based methods, without significant loss of accuracy.
Part of the research leading to this work was performed within the iMinds HiViz project. Simon Donné is funded by BOF grant 01D21213, and Bart Goossens is a postdoctoral research fellow for FWO.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC Superpixels. Tech. rep, EPFL, EPFL (2010)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC Superpixels Compared to State-of-the-art Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence (2012)
Van den Bergh, M., Van Gool, L.: Real-time stereo and flow-based video segmentation with superpixels. In: 2012 IEEE Workshop on Applications of Computer Vision (WACV), pp. 89–96, January 2012
Chang, H.S., Wang, Y.C.: Superpixel-based large displacement optical flow. In: 2013 20th IEEE International Conference on Image Processing (ICIP), September 2013
Drulea, M., Nedevschi, S.: Motion estimation using the correlation transform. IEEE Transactions on Image Processing 22(8), 3260–3270 (2013)
Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. International Journal of Computer Vision 59(2) (2004)
Gkamas, T., Nikou, C.: Guiding optical flow estimation using superpixels. In: 2011 17th International Conference on Digital Signal Processing (DSP), pp. 1–6, July 2011
Goossens, B., De Vylder, J., Philips, W.: Quasar - A new heterogeneous programming framework for image and video processing algorithms on CPU and GPU. In: 2014 IEEE International Conference on Image Processing, ICIP 2014, Paris, France, October 27–30, 2014, pp. 2183–2185. IEEE (2014). http://quasar.ugent.be
Heinrich, M.P., Jenkinson, M., Papież, B.W., Glesson, F.V., Brady, S.M., Schnabel, J.A.: Edge- and detail-preserving sparse image representations for deformable registration of chest MRI and CT Volumes. In: Gee, J.C., Joshi, S., Pohl, K.M., Wells, W.M., Zöllei, L. (eds.) IPMI 2013. LNCS, vol. 7917, pp. 463–474. Springer, Heidelberg (2013)
Kopf, J., Shamir, A., Peers, P.: Content-adaptive image downscaling. ACM Trans. Graph. 32(6) (2013)
Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: Turbopixels: Fast superpixels using geometric flows. IEEE Trans. Pattern Anal. Mach. Intell. 31(12) (2009)
Mori, G.: Guiding model search using segmentation. In: Tenth IEEE International Conference on Computer Vision, ICCV 2005, vol. 2, October 2005
Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configurations: combining segmentation and recognition. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004, vol. 2, June 2004
Nishigaki, M.: Color segmentation-based optical flow computation and motion segmentation (2008)
Ren, C.Y., Reid, I.: gslic: a real-time implementation of slic superpixe segmentation. University of Oxford, Department of Engineering Science, Tech. rep. (2011)
Ren, X., Malik, J.: Learning a classification model for segmentation. In: Proceedings. Ninth IEEE International Conference on Computer Vision, October 2003
Scharstein, D., Pal, C.: Learning conditional random fields for stereo. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–8, June 2007
Vedaldi, A., Soatto, S.: Quick shift and kernel methods for mode seeking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 705–718. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Donné, S., Aelterman, J., Goossens, B., Philips, W. (2015). Fast and Robust Variational Optical Flow for High-Resolution Images Using SLIC Superpixels. In: Battiato, S., Blanc-Talon, J., Gallo, G., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2015. Lecture Notes in Computer Science(), vol 9386. Springer, Cham. https://doi.org/10.1007/978-3-319-25903-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-25903-1_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25902-4
Online ISBN: 978-3-319-25903-1
eBook Packages: Computer ScienceComputer Science (R0)