Abstract
Although many efficient image cutout approaches have been proposed, it is still a challenge to cut out foreground objects from a video clip because of the costs of time and memory consumption and the difficulty in maintaining temporal coherence for the cutout results. In this paper, we propose a novel and efficient video cutout approach by extending a multilevel banded image segmentation method to video cutout. In our method, the segmentation results are propagated frame by frame at the lowest resolution level based on optical flow, and are refined in image pyramids level by level through banded graph cuts. We construct an adaptive narrow band to ensure that the segmentation result falls exactly into the narrow band during propagation. Experimental results show that the video cutout approach based on adaptive multilevel bands dramatically reduces time and memory costs, and achieves ideal segmentation results.
Similar content being viewed by others
References
Rother C, Kolmogorov V, Blake A. “Grabcut” — interactive foreground extraction using iterated graph cut. In: Proceeding of ACM SIGGRAPH, 2004. 309–341
Li Y, Sun J, Tang C K, et al. Lazy snapping. In: Proceeding of ACM SIGGRAPH, 2004. 303–308
Liu J Y, Sun J, Shum H Y. Paint selection. In: Proceeding of ACM SIGGRAPH, 2009
Huang H, Zhang L, Zhang H C. RepSnapping: efficient image cutout for repeated scene elements. In: Proceeding of Pacific Graphics, 2011
Boykov Y Y, Jolly M P. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: Proceeding of ICCV, 2001. 105–112
Boykov Y Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts. IEEE Trans Pattern Analysis Mach Intell, 2001, 23: 1222–1239
Lombaert H, Sun Y Y. A multilevel banded graph cuts method for fast image segmentation. In: Proceeding of ICCV, 2005. 259–265
Li Y, Sun J, Shum H Y. Video object cut and paste. In: Proceeding of ACM SIGGRAPH, 2005. 595–600
Wang J, Bhat P, Agrawala M, Cohen M F. Interactive video cutout. In: Proceeding of ACM SIGGRAPH, 2005. 585–594
Vincent L, Soille P. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans Pattern Analysis Mach Intell, 1991, 13: 583–598
Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Analysis Mach Intell, 2002, 24: 603–619
Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision. In: Proceeding of Imaging Understanding Workshop, 1981. 121–130
Chuang Y J, Agarwala A, Curless B, et al. Video matting of complex scenes. In: Proceeding of ACM SIGGRAPH, 2002. 243–248
Bai X, Wang J, Simons H D, et al. Video SnapCut: robust video object cutout using localized classifiers. In: Proceeding of ACM SIGGRAPH, 2009
Xie Z F, Shen Y, Ma L Z, et al. Seamless video composition using optimized mean-value cloning. Visual Computer, 2010, 26: 1123–1134
Jia Y T, Hu S M, Martin R R. Video completion using tracking and fragment merging. Visual Computer, 2005, 21: 601–610
Criminisi A, Cross G, Blake A, et al. Bilayer segmentation of live video. In: Proceeding of CVPR, 2006. 53–60
Zhang G F, Jia J Y, Hua W, et al. Robust bilayer segmentation and motion/depth estimation with a handheld camera. TPAMI, 2011, 33: 603–617
Grundmann M, Kwatra V, Han M, et al. Efficient hierarchical graph-based video segmentation. In: Proceeding of CVPR, 2010
Zhang S H, Chen T, Zhang Y F, et al. Vectorizing Cartoon Animations. IEEE Trans Visual Computer Graph, 2009, 15: 618–629
Kopf J, Cohen M F, Lischinski D, et al. Joint bilateral upsampling. In: Proceeding of ACM SIGGRAPH, 2007
Bai X, Sapiro G. A geodesic framework for fast interactive image and video segmentation and matting. In: Proceeding of ICCV, 2007. 1038–1044
Cheng M M, Zhang G X, Mitra N J, et al. Global contrast based salient region detection. In: Proceeding of CVPR, 2011. 409–416
Chen T, Cheng M M, Tan P, et al. Sketch2Photo: internet image montage. ACM Trans Graph, 2009, 28: 1–10
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chen, M., Sui, B., Gao, Y. et al. Efficient video cutout based on adaptive multilevel banded method. Sci. China Inf. Sci. 55, 1082–1092 (2012). https://doi.org/10.1007/s11432-012-4560-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-012-4560-4