Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Video object segmentation with shape cue based on spatiotemporal superpixel neighbourhood

In this study, the authors present a method to extract moving objects in image sequences. The proposed approach is based on a graph cuts algorithm defined on a spatiotemporal superpixel neighbourhood. Presegmented superpixels are partitioned into foreground and background while preserving temporal and spatial coherence. It achieves this goal by three steps. First, instead of operating at pixel level, the superpixels are advocated as basic units of the authors segmentation scheme. Second, within the graph cuts framework, two superpixel-based data terms and two superpixel-based smoothness terms are proposed to solve segmentation problem. Finally, the proposed method yields the segmentation of all the superpixels within video volume by the graph cuts algorithm. To illustrate the advantages of this approach, the quantitative and qualitative results are compared with other state-of-the-art methods. The experimental results show that the proposed method gives better performance of segmentation with respect to these methods.

References

    1. 1)
      • 21. Felzenszwalb, P., Huttenlocher, D.: ‘Distance transforms of sampled functions’. Technical Report, TR2004–1963, Cornell Computing Information Science, 2004.
    2. 2)
      • 5. Lee, Y., Kim, J., Grauman, K.: ‘Key-segments for video object segmentation’. Proc. Int. Conf. Computer Vision, Barcelona, Spain, 2011, pp. 19952002.
    3. 3)
      • 8. Varcheie, P., Sills-Lavoie, M., Bilodeau, G.: ‘A multiscale region-based motion detection and background subtraction algorithm’, Sensors, 2010, 10, (2), pp. 10411061 (doi: 10.3390/s100201041).
    4. 4)
      • 24. Brox, T., Malik, J.: ‘Object segmentation by long term analysis of point trajectories’. Proc. European Conf. Computer vision, Crete, Greece, 2010, pp. 282295.
    5. 5)
      • 21. Felzenszwalb, P., Huttenlocher, D.: ‘Distance transforms of sampled functions’. Technical Report, TR2004–1963, Cornell Computing Information Science, 2004.
    6. 6)
      • 18. Felzenszwalb, P., Huttenlocher, D.: ‘Efficient graph-based image segmentation’, Int. J. Comput. Vis., 2004, 59, (2), pp. 167181 (doi: 10.1023/B:VISI.0000022288.19776.77).
    7. 7)
      • 19. Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: ‘Anisotropic huber-l1 optical flow’. Proc. British Machine Vision Conf., London, England, 2009.
    8. 8)
      • 20. Tian, Z., Xue, J., Li, C., Lan, X., Zheng, N.: ‘Auto-generated strokes for motion segmentation’. Proc. Int. Symp. Circuits and Systems, Rio de Janeiro, Brazil, 2011, pp. 857860.
    9. 9)
      • 15. Li, Y., Sun, J., Shum, H.: ‘Video object cut and paste’. Proc. ACM SIGGRAPH, Los Angeles, USA, 2005, pp. 595600.
    10. 10)
      • 9. Ren, X., Malik, J.: ‘Learning a classification model for segmentation’. Proc. Int. Conf. Computer Vision, Nice, France, 2003, pp. 1017.
    11. 11)
      • 14. Kohli, P., Rihan, J., Bray, M., Torr, P.: ‘Simultaneous segmentation and pose estimation of humans using dynamic graph cuts’, Int. J. Comput. Vis., 2008, 79, (3), pp. 285298 (doi: 10.1007/s11263-007-0120-6).
    12. 12)
      • 4. Huang, Y., Liu, Q., Metaxas, D.: ‘Video object segmentation by hypergraph cut’. Proc. Int. Conf. Computer Vision and Pattern Recognition, Miami, USA, 2009, pp. 17381745.
    13. 13)
      • 13. Boykov, Y., Jolly, M.: ‘Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images’. Proc. Int. Conf. Computer Vision, Vancouver, Canada, 2001, pp. 105112.
    14. 14)
      • 17. Shi, J., Malik, J.: ‘Normalized cuts and image segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (8), pp. 888905 (doi: 10.1109/34.868688).
    15. 15)
      • 22. Kolmogorov, V., Zabin, R.: ‘What energy functions can be minimized via graph cuts’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (2), pp. 147159 (doi: 10.1109/TPAMI.2004.1262177).
    16. 16)
      • 23. Tsai, D., Flagg, M., Rehg, J.: ‘Motion coherent tracking with multi-label mrf optimization’. Proc. British Machine Vision Conf., Aberystwyth, Wales, 2010, pp. 111.
    17. 17)
      • 11. Kumar, M., Torr, P., Zisserman, A.: ‘Objcut: efficient segmentation using top-down and bottom-up cues’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (3), pp. 530545 (doi: 10.1109/TPAMI.2009.16).
    18. 18)
      • 16. Comaniciu, D., Meer, P.: ‘Mean shift: a robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603619 (doi: 10.1109/34.1000236).
    19. 19)
      • 6. Stauffer, C., Grimson, W.: ‘Learning patterns of activity using real-time tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (8), pp. 747757 (doi: 10.1109/34.868677).
    20. 20)
      • 12. Yin, Z., Collins, R.: ‘Shape constrained figure-ground segmentation and tracking’. Proc. Int. Conf. Computer Vision and Pattern Recognition, Miami, USA, 2009, pp. 731738.
    21. 21)
      • 10. Freedman, D., Zhang, T.: ‘Interactive graph cut based segmentation with shape priors’. Proc. Int. Conf. Computer Vision and Pattern Recognition, San Diego, USA, 2005, pp. 755762.
    22. 22)
      • 3. Kumar, M., Torr, P., Zisserman, A.: ‘Learning layered motion segmentations of video’, Int. J. Comput. Vis., 2008, 76, (3), pp. 301319 (doi: 10.1007/s11263-007-0064-x).
    23. 23)
      • 7. Elgammal, A., Duraiswami, R., Harwood, D., Davis, L.: ‘Background and foreground modeling using nonparametric kernel density estimation for visual surveillance’, Proc. IEEE, 2002, 90, (7), pp. 11511163 (doi: 10.1109/JPROC.2002.801448).
    24. 24)
      • 1. Guan, Y.: ‘Spatio-temporal motion-based foreground segmentation and shadow suppression’, IET Comput. Vis., 2010, 4, (1), pp. 5060 (doi: 10.1049/iet-cvi.2008.0016).
    25. 25)
      • 2. Xue, B., Jue, W., David, S., Guillermo, S.: ‘Video snapcut: robust video object cutout using localized classifiers’. Proc. ACM SIGGRAPH, New Orleans, USA, 2009.
    26. 26)
      • 25. Endres, I., Hoiem, D.: ‘Category independent object proposals’. Proc. European Conf. Computer Vision, Crete, Greece, 2010, pp. 575588.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2012.0189
Loading

Related content

content/journals/10.1049/iet-cvi.2012.0189
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address