Research Article

Video Segmentation using 2D+time Mumford-Shah Functional

by  Mohamed El Aallaoui, Abdelwahad Gourch
journal cover
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 55 - Issue 3
Published: October 2012
Authors: Mohamed El Aallaoui, Abdelwahad Gourch
10.5120/8734-2748
PDF

Mohamed El Aallaoui, Abdelwahad Gourch . Video Segmentation using 2D+time Mumford-Shah Functional. International Journal of Computer Applications. 55, 3 (October 2012), 15-19. DOI=10.5120/8734-2748

                        @article{ 10.5120/8734-2748,
                        author  = { Mohamed El Aallaoui,Abdelwahad Gourch },
                        title   = { Video Segmentation using 2D+time Mumford-Shah Functional },
                        journal = { International Journal of Computer Applications },
                        year    = { 2012 },
                        volume  = { 55 },
                        number  = { 3 },
                        pages   = { 15-19 },
                        doi     = { 10.5120/8734-2748 },
                        publisher = { Foundation of Computer Science (FCS), NY, USA }
                        }
                        %0 Journal Article
                        %D 2012
                        %A Mohamed El Aallaoui
                        %A Abdelwahad Gourch
                        %T Video Segmentation using 2D+time Mumford-Shah Functional%T 
                        %J International Journal of Computer Applications
                        %V 55
                        %N 3
                        %P 15-19
                        %R 10.5120/8734-2748
                        %I Foundation of Computer Science (FCS), NY, USA
Abstract

this paper describes a new video segmentation method obtained by minimizing an extension of Mumford-Shah functional used for 2D+time partitions. This extension permits to write the Mumford- Shah functional as an amultiscale energy, which is minimized on a 2D+time persistent hierarchy. The building of this hierarchy based on connected components of spatio-temporal regions.

References
  • H. Winnemoller, S. C. Olsen, and B. Gooch. Real-time video abstraction. ACM Transactions on Graphics Proc. of the ACM SIGGRAPH conf, 25:1221–1226, July 2006.
  • J. Chen, S. Paris, and F. Durand. Real-time edge-aware image processing with the bilateral grid. ACM Transactions on Graphics Proc. of the ACM SIGGRAPH conf, 26:103, July 2007.
  • Y. Wang, K. F Loe, T. Tan, and J-K. Wu. Spatiotempo-ral video segmentation based on graphical models. IEEE transactions on image processing, 14:937–947, July 2005.
  • J. P Collomosse, D. Rowntree, and P. M Hall. Stroke surfaces: Temporally coherent artistic animations from video. IEEE Transactions on Visualization and Computer Graphics, 11:540–549, 2005.
  • W. Brendel and S. Todorovic. Video object segmentation by tracking regions. IEEE 12th International Conference on Computer Vision, pages 833–840, 2009.
  • D. Comaniciu and P. Meer. A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis Machine Intelligence, 24:603–619, 2002.
  • A. W. Klein, P. J. Sloan, A. Finkelstein, and M. F. Cohen. Stylized video cubes. pages 15–22.
  • J. Wang, B. Thiesson, Y. Xu, and M. Cohen. Image and video segmentation by anisotropic kernel mean shift. in Proc. 8th European Conference on Computer Vision, Prague, Czech Republic, 2:238–249, May 2004.
  • D. DeMenthon and R. Megret. Spatio-temporal segmentation of video by hierarchical mean shift analysis. Technical Report: LAMP-TR-090/CAR-TR-978/CSTR- 4388/UMIACS-TR-2002-68, University of Maryland, College Park, 2002.
  • S. Paris and F. Durand. A topological approach to hierarchical segmentation using mean shift. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, Minnesota, USA, pages 1–8, June 2007.
  • T. Wang, J. -Y. Guillemaut, and J. Collomosse. Multi-label propagation for coherent video segmentation and artistic stylization. 17th IEEE International Conference on Image Processing (ICIP), pages 3005–3008, September 2010.
  • H. Greenspan, J. Goldberger, and A. Mayer. A probabilistic framework for spatio-temporal video representation. CCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV, pages 461–475, 2002.
  • D. Mumford and J. Shah. Optimal approximations by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics, 42:577–686, 1989.
  • L. Vese and T. Chan. A mumtiphase level set framework for image segmentation using the mumford and shah model. Inter. J. Computer Vision, 50:271–293, 2002.
  • L. Guigues. Modles multi-chelles pour la segmentation d'images. PhD thesis, Cergy-Pontoise University, 2003.
  • L. I. Muoz. Image segmentation and compression using the tree of shapes of an image. motion estimation. PhD thesis, Pompeu Fabra University, Barcelona, 2005.
  • C. Ballester V. Caselles and P. Monasse. The tree of shapes of an image. SAIM: Control, Optimization and Calculus of Variations, 9:1–18, 2003.
  • P. Monasse. Morphological representation of digital images and application to registration. PhD thesis, Universit Paris IX-Dauphine, June 2000.
  • D. G. LOWE. Object recognition from local scale-invariant features. ICCV '99 Proceedings of the International Conference on Computer Vision, 2:1150–1157, 1999.
  • D. G. LOWE. Distinctive image features from scaleinvariant keypoints. International Journal of Computer vision, 60:91–110, November 2004.
  • M. Grundmann, V. Kwatra, M. Han, and I. Essa. Efficient hierarchical graph-based video segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, USA, June 2010.
  • S. Paris. Edge-preserving smoothing and mean-shift segmentation of video streams. ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II, pages 460–473, 2008.
Index Terms
Computer Science
Information Sciences
No index terms available.
Keywords

Video segmentation 2D+time Mumford-Shah functional amultiscale energy hierarchy 2D-shapes

Powered by PhDFocusTM