Advertisement

Automatic Matting Using Depth and Adaptive Trimap

  • Ying ZhaoEmail author
  • Chao Chen
  • Liyan Liu
  • Wei Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9555)

Abstract

Image matting refers to the problem of accurately extracting the foreground object from an image. The trimap containing labels of known foreground, known background and unknown has been broadly used to reduce solution space of the problem. The matte of an unknown pixel can be solved using samples from its neighbor known foreground and known background. However, the existing methods of color-based sampling may fail when foreground and background share similar colors, meanwhile, automatically generated trimap may not properly cover foreground boundary. In this paper, we propose a novel matting method using depth-assisted sampling and adaptive trimap generation. We use depth to assist color for improving sample selection and generate trimap based on color distribution of local unknown regions to make it cover foreground boundary adaptively. Our experiments show the effectiveness of proposed method.

Keywords

Image matting Trimap Alpha matte Depth 

References

  1. 1.
    Zheng, Y., Kambhamettu, C.: Learning based digital matting. In: IEEE International Conference on Image Processing (ICIP), pp. 889–896 (2009)Google Scholar
  2. 2.
    Gastal, E.S.L., Oliveira, M.M.: Shared sampling for real time alpha matting. Proc. Eurographics 29, 575–584 (2010)Google Scholar
  3. 3.
    Shahrian, E., Rajan, D.: Weighted color and texture sample selection for image matting. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 718–725 (2012)Google Scholar
  4. 4.
    Shahrian, E., Rajan, D., Price, B., Cohen, S.: Improving image matting using comprehensive sampling sets. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 636–643 (2013)Google Scholar
  5. 5.
    Wang, O., Finger, J., Yang, Q., Davis, J., Yang, R.: Automatic natural video matting with depth. In: IEEE Pacific Conference on Computer Graphics and Applications (PG), pp. 469–472 (2007)Google Scholar
  6. 6.
    Chuang, Y.Y., Curless, B., Salesin, D.H., Szeliski, R.: A bayesian approach to digital matting. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, p. 7 (2001)Google Scholar
  7. 7.
    Sun, J., Jia, J., Tang, C.K., Shum, H.Y.: Poisson matting. ACM Trans. on Graph. (ToG) 23(3), 315–321 (2004)CrossRefGoogle Scholar
  8. 8.
    Piti, F., Kokaram, A.: Matting with a depth map. In: IEEE International Conference on Image Processing (ICIP), pp. 21–24 (2010)Google Scholar
  9. 9.
    Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. 30(1), 228–242 (2008)CrossRefGoogle Scholar
  10. 10.
    Mutto, D., Zanuttigh, P., Cortelazzo, G.M.: Time-of-Flight Cameras and Microsoft Kinect. SpringerBriefs in Electrical and Computer Engineering. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    He, K., Sun, J., Tang, X.: Fast matting using large kernel matting laplacian matrices. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2165–2172 (2010)Google Scholar
  12. 12.
    Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., Rott, P.: A perceptually motivated online benchmark for image matting. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1826–1833 (2009)Google Scholar
  13. 13.
    Shibuya, N., Shimohata, Y., Harada, T., Kuniyoshi, Y.: Smart extraction of desired object from color-distance image with users tiny scribble. In: IEEE Conference on Intelligent Robots and Systems, pp. 2846–2853 (2008)Google Scholar
  14. 14.
    Frick, A., Franke, M., Koch, R.: Time-consistent foreground segmentation of dynamic content from color and depth video. In: Mester, R., Felsberg, M. (eds.) DAGM 2011. LNCS, vol. 6835, pp. 296–305. springer, Heidelberg (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Ricoh Software Research Center (Beijing) Co., Ltd.BeijingChina

Personalised recommendations