Mosaic Animations from Video Inputs

  • Rafael B. Gomes
  • Tiago S. Souza
  • Bruno M. Carvalho
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4872)

Abstract

Mosaic is a Non-Photorealistic Rendering (NPR) style for simulating the appearance of decorative tile mosaics. To simulate realistic mosaics, a method must emphasize edges in the input image, while placing the tiles in an arrangement to minimize the visible grout (the substrate used to glue the tiles that appears between them). This paper proposes a method for generating mosaic animations from input videos (extending previous works on still image mosaics) that uses a combination of a segmentation algorithm and an optical flow method to enforce temporal coherence in the mosaic videos, thus avoiding that the tiles move back and forth the canvas, a problem known as swimming. The result of the segmentation algorithm is used to constrain the result of the optical flow, restricting its computation to the areas detected as being part of a single object. This intra-object coherence scheme is applied to two methods of mosaic rendering, and a technique for adding and removing tiles for one of the mosaic rendering methods is also proposed. Some examples of the renderings produced are shown to illustrate our techniques.

Keywords

Video Sequence Segmentation Algorithm Voronoi Diagram Temporal Coherence Video Input 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Hausner, A.: Simulating decorative mosaics. In: Proc. of ACM SIGGRAPH, pp. 207–214. ACM Press, New York (2001)Google Scholar
  2. 2.
    Blasi, G.D., Gallo, G.: Artificial mosaics. The Vis. Comp. 21, 373–383 (2005)CrossRefGoogle Scholar
  3. 3.
    Faustino, G., Figueiredo, L.: Simple adaptive mosaic effects. In: Proc. of SIBGRAPI, pp. 315–322 (2005)Google Scholar
  4. 4.
    Haeberli, P.: Paint by numbers: Abstract image representations. In: Proc. of ACM SIGGRAPH, pp. 207–214. ACM Press, New York (1990)CrossRefGoogle Scholar
  5. 5.
    Dobashi, Y., Haga, T., Johan, H., Nishita, T.: A method for creating mosaic images using Voronoi diagrams. In: Proc. of Eurographics, pp. 341–348 (2002)Google Scholar
  6. 6.
    Meier, B.: Painterly rendering for animation. In: Proc. of ACM SIGGRAPH, pp. 477–484. ACM Press, New York (1996)Google Scholar
  7. 7.
    Litwinowicz, P.: Processing images and video for an impressionist effect. In: Proc. of ACM SIGGRAPH, pp. 407–414. ACM Press, New York (1997)Google Scholar
  8. 8.
    Hertzmann, A., Perlin, K.: Painterly rendering for video and interaction. In: Proc. of NPAR, pp. 7–12 (2000)Google Scholar
  9. 9.
    Wang, J., Xu, Y., Shum, H.-Y., Cohen, M.: Video tooning. ACM Trans. on Graph. 23, 574–583 (2004)CrossRefGoogle Scholar
  10. 10.
    Smith, K., Liu, Y., Klein, A.: Animosaics. In: Proc. of 2005 ACM SIGGRAPH/Eurograph. SCA, pp. 201–208. ACM Press, New York (2005)CrossRefGoogle Scholar
  11. 11.
    Dalal, K., Klein, A.W., Liu, Y., Smith, K.: A spectral approach to NPR packing. In: Proc. of NPAR, pp. 71–78 (2006)Google Scholar
  12. 12.
    Collomosse, J., Rowntree, D., Hall, P.: Stroke surfaces: Temporally coherent artistic animations from video. IEEE Trans. on Visualiz. and Comp. Graph. 11, 540–549 (2005)CrossRefGoogle Scholar
  13. 13.
    Carvalho, B., Oliveira, L., Silva, G.: Fuzzy segmentation of color video shots. In: Kuba, A., Nyúl, L.G., Palágyi, K. (eds.) DGCI 2006. LNCS, vol. 4245, pp. 402–407. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Carvalho, B.M., Herman, G.T., Kong, T.Y.: Simultaneous fuzzy segmentation of multiple objects. Disc. Appl. Math. 151, 55–77 (2005)MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Galun, M., Apartsin, A., Basri, R.: Multiscale segmentation by combining motion and intensity cues. In: Proc. of IEEE CVPR, pp. 256–263. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  16. 16.
    Khan, S., Shah, M.: Object based segmentation of video using color, motion and spatial information. In: Proc. of IEEE CVPR, vol. 2, pp. 746–751. IEEE Computer Society Press, Los Alamitos (2001)Google Scholar
  17. 17.
    Proesmans, M., Gool, L.V., Pauwels, E., Oosterlinck, A.: Determination of optical flow and its discontinuities using non-linear diffusion. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 2, pp. 295–304. Springer, Heidelberg (1994)Google Scholar
  18. 18.
    McCane, B., Novins, K., Crannitch, D., Galvin, B.: On benchmarking optical flow. Comp. Vis. and Image Underst. 84, 126–143 (2001)MATHCrossRefGoogle Scholar
  19. 19.
    Lloyd, S.: Least square quantization in PCM. IEEE Trans. on Inform. Theory 28, 129–137 (1982)MATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Oliveira, L.: Segmentação fuzzy de imagens e vídeos. Master’s thesis, Universidade Federal do Rio Grande do Norte, Natal, Brazil (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Rafael B. Gomes
    • 1
  • Tiago S. Souza
    • 1
  • Bruno M. Carvalho
    • 1
  1. 1.Departamento de Informática e Matemática Aplicada, Universidade Federal do Rio Grande do Norte, Campus Universitário, S/N, Lagoa Nova, Natal, RN, 59.072-970Brazil

Personalised recommendations