Browse > Article
http://dx.doi.org/10.5909/JBE.2009.14.4.450

Bilayer Segmentation of Consistent Scene Images by Propagation of Multi-level Cues with Adaptive Confidence  

Lee, Soo-Chahn (Automation and Systems Research Institute, Seoul National University)
Yun, Il-Dong (School of Digital Information Engineering, Hankuk University of Foreign Studies)
Lee, Sang-Uk (School of Electrical Engineering and Computer Science, Seoul National University)
Publication Information
Journal of Broadcast Engineering / v.14, no.4, 2009 , pp. 450-462 More about this Journal
Abstract
So far, many methods for segmenting single images or video have been proposed, but few methods have dealt with multiple images with analogous content. These images, which we term consistent scene images, include concurrent images of a scene and gathered images of a similar foreground, and may be collectively utilized to describe a scene or as input images for multi-view stereo. In this paper, we present a method to segment these images with minimum user input, specifically, manual segmentation of one image, by iteratively propagating information via multi-level cues with adaptive confidence depending on the nature of the images. Propagated cues are used as the bases to compute multi-level potentials in an MRF framework, and segmentation is done by energy minimization. Both cues and potentials are classified as low-, mid-, and high- levels based on whether they pertain to pixels, patches, and shapes. A major aspect of our approach is utilizing mid-level cues to compute low- and mid- level potentials, and high-level cues to compute low-, mid-, and high- level potentials, thereby making use of inherent information. Through this process, the proposed method attempts to maximize the amount of both extracted and utilized information in order to maximize the consistency of the segmentation. We demonstrate the effectiveness of the proposed method on several sets of consistent scene images and provide a comparison with results based only on mid-level cues [1].
Keywords
Image Set Segmentation; Consistent Scene Images; Multi-level Cues; Adaptive Confidence;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. PAMI 24 (2002) 603–619   DOI   ScienceOn
2 Shi, J., Malik, J.: Normalized cuts and image segmentation. PAMI 22 (2000) 888–905   DOI   ScienceOn
3 Sun, J., Zhang, W., Tang, X., Shum, H.: Background cut. In: ECCV06. (2006) II: 628–41
4 Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. PAMI 26 (2004) 1124–137   DOI   ScienceOn
5 Homepage, T.P.V.O.C.: (http://www.pascal-network.org/challenges/ voc/)
6 Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching: Incorporating a global constraint into mrfs. In: CVPR06. (2006) I: 993–000   DOI
7 Li., S.Z.: Markov Random Field Modeling in Computer Vision. Springer-Verlag (1995)
8 Rubner, Y., Tomasi, C., Guibas, L.: The earth mover’s distance as a metric for image retrieval. IJCV 40 (2000) 99–21   DOI
9 Chuang, Y.Y., Agarwala, A., Curless, B., Salesin, D.H., Szeliski, R.: Video matting of complex scenes. ACM Transactions on Graphics 21 (2002) 243–48 Sepcial Issue of the SIGGRAPH 2002 Proceedings.   DOI
10 Chuang, Y.Y., Agarwala, A., Curless, B., Salesin, D.H., Szeliski, R.: Video matting of complex scenes. ACM Transactions on Graphics 21 (2002) 243–48 Sepcial Issue of the SIGGRAPH 2002 Proceedings
11 Yin, P., Criminisi, A., Winn, J., Essa, I.: Tree-based classifiers for bilayer video segmentation. In: CVPR07. (2007)
12 1. Lu, L., Hager, G.: A nonparametric treatment for location/segmentation based visual tracking. In: CVPR07. (2007)
13 Freedman, D., Zhang, T.: Interactive graph cut based segmentation with shape priors. In: CVPR05. (2005) I: 755–62   DOI
14 Kwon, D., Yun, I., Lee, S.: Efficient feature-based nonrigid registration of multi-phase liver ct volumes. BMVC (2008)
15 Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV 59 (2004) 167–181   DOI
16 Xu, C., Prince, J.: Snakes, shapes, and gradient vector flow. T-IP 7 (1998) 359–69   DOI   ScienceOn
17 Li, Y., Sun, J., Shum, H.Y.: Video object cut and paste. ACM Trans. Graph. 24 (2005)   DOI   ScienceOn
18 Wang, J., Bhat, P., Colburn, R.A., Agrawala, M., Cohen, M.F.: Interactive video cutout. ACM Trans. Graph. 24 (2005) 585–94   DOI   ScienceOn
19 Zheng, S., Tu, Z., Yuille, A.: Detecting object boundaries using low-, mid-, and high-level information. In: CVPR07. (2007)
20 Kolmogorov, V., Criminisi, A., Blake, A., Cross, G., Rother, C.: Probabilistic fusion of stereo with color and contrast for bi-layer segmentation. IJCV 76 (2008)   DOI
21 Boykov, Y., Funka Lea, G.: Graph cuts and efficient n-d image segmentation. IJCV 70 (2006) 109–131   DOI
22 Criminisi, A., Cross, G., Blake, A., Kolmogorov, V.: Bilayer segmentation of live video. In: CVPR06. (2006)
23 Rother, C., Kolmogorov, V., Blake, A.: ”grabcut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23 (2004) 309–14   DOI   ScienceOn
24 Kohli, P., Kumar, M., Torr, P.: P3 & beyond: Solving energies with higher order cliques. In: CVPR07. (2007)
25 Kumar, M., Torr, P., Zisserman, A.: Obj cut. In: CVPR05. (2005)   DOI
26 Campbell, N., Vogiatzis, G., Hernandez, C., Cipolla, R.: Automatic 3d object segmentation in multiple views using volumetric graph-cuts. In: BMVC07. (2007)