Abstract
This paper proposes a novel video co-segmentation method, which aims to extract multi-class objects from a group of videos. A set of tracklets are first generated based on object proposals, and then a novel directed graph is constructed to connect object tracklets. The directed graph is transformed to an undirected graph, and the extraction of common object tracklets is solved by using maximum weighted clique. The obtained common object tracklets are used as seed regions to perform manifold ranking and to generate the object-level saliency maps. Based on common object tracklets and object-level saliency maps, GrabCut is exploited to get the refined co-segmentation results. Experimental results on a public video dataset show that the proposed video co-segmentation method consistently outperforms the state-of-the-art methods.
Similar content being viewed by others
References
Bron C, Kerbosch J (1973) Algorithm 457: finding all cliques of an undirected graph. Commun ACM 16(9):575–577
Chen DJ, Chen HT, Chang LW (2012) Video object cosegmentation. In Proc. of ACM International Conference on Multimedia 805–808
Cheng MM, Mitra NJ, Huang X, Hu SM (2014) SalientShape: group saliency in image collections. Vis Comput 30(4):443–453
Chiu WC, Fritz M (2013) Multi-class video co-segmentation with a generative multi-video model. In: Proc. of IEEE Conference on Computer Vision Pattern Recognition 321–328
Du H, Liu Z, Jiang J, Shen L (2013) Stretchability-aware block scaling for image retargeting. J Vis Commun Image Represent 24(4):499–508
Endres I, Hoiem D (2010) Category independent object proposals. In: Proc. of European Conference on Computer Vision 575–588
Faktor A, Irani M (2014) Video segmentation by non-local consensus voting. In: Proc. of British Machine Vision Conference, article 8
Fu H, Xu D, Zhang B, Lin S, Ward RK (2015) Object-based multiple foreground video co-segmentation via multi-state selection graph. IEEE Trans Image Process 24(11):3415–3424
Guo J, Li Z, Cheong LF, Zhou SZ (2013) Video co-segmentation for meaningful action extraction. In: Proc. of IEEE International Conference on Computer Vision 2232–2239
Guo J, Cheong LF, Tan RT, Zhou SZ (2014) Consistent foreground co-segmentation. In Proc. of Asian Conference on Computer Vision 241–257
Huang G, Pun CM, Lin C (2017) Unsupervised video co-segmentation based on superpixel co-saliency and region merging. Multimed Tools Appl 76(10):12941–12964
Jacobs D, Goldman D, Shechtman E (2010) Cosaliency: Where people look when comparing images. In: Proc. of ACM symposium on User interface software and technology 219–228
Lee YJ, Kim J, Grauman K (2011) Key-segments for video object segmentation. In: Proc. of IEEE International Conference on Computer Vision 1995–2002
Liu C (2009) Beyond pixels: Exploring new representations and applications for motion analysis. Ph.D. Dissertation, Massachusetts Inst. Technol., Cambridge
Liu Z, Zou W, Li L, Shen L, Le Meur O (2014) Co-saliency detection based on hierarchical segmentation. IEEE Sign Proc Lett 21(1):88–92
Lou Z, Gevers T (2014) Extracting primary objects by video co-segmentation. IEEE Trans Multimed 16(8):2110–2117
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cyber 9(1):62–66
Papazoglou A, Ferrari V (2013) Fast object segmentation in unconstrained video. In: Proc. of IEEE International Conference on Computer Vision 1777–1784
Perazzi F, Wang O, Gross M, Sorkine-Hornung A (2015) Fully connected object proposals for video segmentation. In: Proc. of IEEE International Conference on Computer Vision 3227–3234
Perazzi F, Pont-Tuset J, McWilliams B, Van Gool L, Gross M, Sorkine-Hornung A (2016) A benchmark dataset and evaluation methodology for video object segmentation. In: Proc. of IEEE Conference on Computer Vision Pattern Recognition 724–732
Rother C, Kolmogorov V, Blake A (2004) Grabcut: interactive foreground extraction using iterated graph cuts. ACM Trans Graph 23(3):309–314
Rother C, Minka T, Kolmogorov V, Blake A (2006) Cosegmentation of image pairs by histogram matching-incorporating a global constraint into mrfs. In: Proc. of IEEE Conference on Computer Vision Pattern Recognition 993–1000
Rubio JC, Serrat J, López A (2012) Video co-segmentation. In Proc. of Asian Conference on Computer Vision 13–24
Vicente S, Rother C, Kolmogorov V (2011) Object cosegmentation. In: Proc. of IEEE Conference on Computer Vision Pattern Recognition 2217–2224
Wang W, Shen J, Li X, Porikli F (2015) Robust video object cosegmentation. IEEE Trans Image Process 24(10):3137–3148
Wang W, Shen J, Porikli F (2015) Saliency-aware geodesic video object segmentation. In: Proc. of IEEE Conference on Computer Vision Pattern Recognition 3395–3402
Wang W, Shen J, Sun H, Shao L (2017) ViCoS2: Video co-saliency guided co-segmentation. IEEE Trans. Circuits Syst. Video Technol. doi: https://doi.org/10.1109/TCSVT.2017.2701279
Wen L, Du D, Lei Z, Li SZ, Yang MH (2015) JOTS: Joint online tracking and segmentation. In: Proc. of IEEE Conference on Computer Vision Pattern Recognition 2226–2234
Xiao F, Lee YJ (2016) Track and segment: An iterative unsupervised approach for video object proposals. In: Proc. of IEEE Conference on Computer Vision Pattern Recognition 933–942
Y. Xie, L. Ye, Z. Liu, and X. Zhou (2016) Video co-saliency detection. In: Proc. of International Conference on Digital Image Processing, article 100335G
Xu B, Bu J, Chen C, Cai D, He X, Liu W, Luo J (2011) Efficient manifold ranking for image retrieval. In: Proc. of International ACM SIGIR Conference on Research and Development in Information Retrieval 525–534
Ye L, Liu Z, Li J, Zhao W, Shen L (2015) Co-saliency detection via co-salient object discovery and recovery. IEEE Sign Proc Lett 22(11):2073–2077
Zhang D, Javed O, Shah M (2013) Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In: Proc. of IEEE Conference on Computer Vision Pattern Recognition 628–635
Zhang D, Javed O, Shah M (2014) Video object co-segmentation by regulated maximum weight cliques. In: Proc. of European Conference on Computer Vision 551–566
Zhang J, Li K, Tao W (2016) Multivideo object cosegmentation for irrelevant frames involved videos. IEEE Sign Proc Lett 23(6):785–789
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant No. 61471230, and by the Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xie, Y., Liu, Z., Zhou, X. et al. Video co-segmentation based on directed graph. Multimed Tools Appl 78, 10353–10372 (2019). https://doi.org/10.1007/s11042-018-6614-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6614-0