Salient Object Segmentation from Stereoscopic Images

  • Xingxing FanEmail author
  • Zhi Liu
  • Linwei Ye
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9069)


In this paper, we propose for stereoscopic images an effective object segmentation approach by incorporating saliency and depth information into graph cut. A saliency model based on color and depth is first used to generate the saliency map. Then the graph cut based on saliency and depth information as well as with the introduction of saliency weighted histogram is proposed to segment salient objects in one cut. Experimental results on a public stereoscopic image dataset with ground truths of salient objects demonstrate that the proposed approach outperforms the state-of-the-art salient object segmentation approaches.


Salient object segmentation Saliency map Depth information Graph cut Saliency weighted histogram 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Boykov, Y., Funka-Lea, G.: Graph cuts and efficient N-D image segmentation. International Journal of Computer Vision 70(2), 109–131 (2006)CrossRefGoogle Scholar
  2. 2.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of mincut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Machine Intell. 26(9), 1124–1137 (2004)CrossRefGoogle Scholar
  3. 3.
    Liu, Z., Shi, R., Shen, L., Xue, Y., Ngan, K.N., Zhang, Z.: Unsupervised salient object segmentation based on kernel density estimation and two-phase graph cut. IEEE Trans. Multimedia 14(4), 1275–1289 (2012)CrossRefGoogle Scholar
  4. 4.
    Rother, C., Kolmogorov, V., Blake, A.: Grabcut - interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics 23(3), 309–314 (2004)CrossRefGoogle Scholar
  5. 5.
    Cheng, M.M., Mitra, N.J., Huang, X.L., Torr, P.H.S., Hu, S.M.: Global contrast based salient region detection. IEEE Trans. Pattern Anal. Machine Intell. (2014), doi.: 10.1109/TPAMI, 2345401Google Scholar
  6. 6.
    Tang, M., Gorelick, L., Veksler, L., Boykov, Y.: GrabCut in one cut. In: Proc. IEEE ICCV, pp. 1769–1776. IEEE Press, Sydney (2013)Google Scholar
  7. 7.
    Mishra, A.K., Shrivastava, A., Aloimonos, Y.: Segmenting “simple” objects using RGB-D. In: Proc. IEEE ICRA, pp. 4406–4413. IEEE Press, Saint Paul (2012)Google Scholar
  8. 8.
    Liu, H., Philipose, M., Sun, M.T.: Automatic objects segmentation with RGB-D cameras. Journal of Visual Communication and Image Representation 25(4), 709–718 (2014)CrossRefGoogle Scholar
  9. 9.
    Fan, X., Liu, Z., Sun, G.: Salient region detection for stereoscopic images. In: Proc. IEEE DSP, pp. 454–458. IEEE Press, Hong Kong (2014)Google Scholar
  10. 10.
    Lei, J., Zhang, H., You, L., Hou, C., Wang, L.: Evaluation and modeling of depth feature incorporated visual attention for salient object segmentation. Neurocomputing 120, 24–33 (2013)CrossRefGoogle Scholar
  11. 11.
    Niu, Y., Geng, Y., Li, X., Liu, F.: Leveraging stereopsis for saliency analysis. In: Proc. IEEE CVPR, pp. 454–461. IEEE Press, Providence (2012)Google Scholar
  12. 12.
    Liu, Z., Zou, W., Le Meur, O.: Saliency tree: A novel saliency detection framework. IEEE Trans. Image Process. 23(5), 1937–1952 (2014)CrossRefMathSciNetGoogle Scholar
  13. 13.
    Liu, C., Yuen, J., Torralba, A.: Sift flow: Dense correspondence across scenes and its application. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.School of Communication and Information EngineeringShanghai UniversityShanghaiChina

Personalised recommendations