ABSTRACT
Existing video segmentation methods struggle to work accurately on production images. In particular, methods that rely on colour analysis can suffer when object and background colour ranges are similar. We extend one state of the art method by incorporating motion information from video frames. When tested on a variety of production footage, our new method shows significantly improved results.
- Adobe. Adobe after effects, 2012.Google Scholar
- A. Agarwala, M. Dontcheva, M. Agrawala, S. M. Drucker, A. Colburn, B. Curless, D. Salesin, and M. F. Cohen. Interactive digital photomontage. ACM Trans. Graph., 23(3): 294--302, 2004. Google ScholarDigital Library
- A. Agarwala, A. Hertzmann, D. Salesin, and S. M. Seitz. Keyframe-based tracking for rotoscoping and animation. ACM Trans. Graph., 23(3): 584--591, 2004. Google ScholarDigital Library
- P. Arbelaez, M. Maire, C. C. Fowlkes, and J. Malik. From contours to regions: An empirical evaluation. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20--25 June 2009, Miami, Florida, USA, pages 2294--2301. IEEE, 2009.Google ScholarCross Ref
- X. Bai and G. Sapiro. A geodesic framework for fast interactive image and video segmentation and matting. In IEEE 11th International Conference on Computer Vision, ICCV 2007, Rio de Janeiro, Brazil, October 14--20, 2007, pages 1--8. IEEE, 2007.Google ScholarCross Ref
- X. Bai, J. Wang, and G. Sapiro. Dynamic color flow: A motion-adaptive color model for object segmentation in video. In K. Daniilidis, P. Maragos, and N. Paragios, editors, Computer Vision - ECCV 2010 - 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5--11, 2010, Proceedings, Part V, volume 6315 of Lecture Notes in Computer Science, pages 617--630. Springer, 2010. Google ScholarDigital Library
- X. Bai, J. Wang, D. Simons, and G. Sapiro. Video snapcut: robust video object cutout using localized classifiers. ACM Trans. Graph., 28(3), 2009. Google ScholarDigital Library
- Y. Boykov and M.-P. Jolly. Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In ICCV, pages 105--112, 2001.Google ScholarCross Ref
- I. Budvytis, V. Badrinarayanan, and R. Cipolla. Mot-mixture of trees probabilistic graphical model for video segmentation. In BMVC, pages 1--11, 2012.Google ScholarCross Ref
- D. Corrigan, S. Robinson, and A. Kokaram. Video Matting Using Motion Extended GrabCut. In IET European Conference on Visual Media Production (CVMP), London, UK, 2008.Google Scholar
- A. Criminisi, T. Sharp, and A. Blake. Geos: Geodesic image segmentation. In D. A. Forsyth, P. H. S. Torr, and A. Zisserman, editors, Computer Vision - ECCV 2008, 10th European Conference on Computer Vision, Marseille, France, October 12--18, 2008, Proceedings, Part I, volume 5302 of Lecture Notes in Computer Science, pages 99--112. Springer, 2008. Google ScholarDigital Library
- A. Criminisi, T. Sharp, C. Rother, and P. Pérez. Geodesic image and video editing. ACM Trans. Graph., 29(5): 134, 2010. Google ScholarDigital Library
- M. Gleicher. Image snapping. In Proceedings of SIGGRAPH 95, Computer Graphics Proceedings, Annual Conference Series, pages 183--190, aug 1995. Google ScholarDigital Library
- P. Kohli and P. H. S. Torr. Dynamic graph cuts for efficient inference in markov random fields. IEEE Trans. Pattern Anal. Mach. Intell., 29(12): 2079--2088, 2007. Google ScholarDigital Library
- A. Kokaram, B. Collis, and S. Robinson. Automated rig removal with bayesian motion interpolation. Proceedings of the IEE Journal on Vision, Image and Signal Processing, 152: 407--414, Aug 2005.Google ScholarCross Ref
- A. Kokaram, B. Collis, and S. Robinson. Practical motion based video matting. In proceedings of the IEE European Conference on Visual Media Production (CVMP'05), pages 130--136, 2005.Google Scholar
- A. Levin, D. Lischinski, and Y. Weiss. A closed form solution to natural image matting. In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 17--22 June 2006, New York, NY, USA, pages 61--68. IEEE Computer Society, 2006. Google ScholarDigital Library
- H. Li and C. Shen. Interactive color image segmentation with linear programming. Mach. Vis. Appl., 21(4): 403--412, 2010. Google ScholarDigital Library
- Y. Li, J. Sun, C.-K. Tang, and H.-Y. Shum. Lazy snapping. ACM Trans. Graph., 23(3): 303--308, 2004. Google ScholarDigital Library
- E. N. Mortensen and W. A. Barrett. Intelligent scissors for image composition. In SIGGRAPH, pages 191--198, 1995. Google ScholarDigital Library
- S. Paris and F. Durand. A topological approach to hierarchical segmentation using mean shift. In 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 18--23 June 2007, Minneapolis, Minnesota, USA. IEEE Computer Society, 2007.Google ScholarCross Ref
- B. L. Price, B. S. Morse, and S. Cohen. Livecut: Learning-based interactive video segmentation by evaluation of multiple propagated cues. In IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27--October 4, 2009, pages 779--786. IEEE, 2009.Google ScholarCross Ref
- C. Rother, V. Kolmogorov, and A. Blake. Grabcut: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph., 23(3): 309--314, 2004. Google ScholarDigital Library
- The Foundry. Furnacecore for nuke | vectorgenerator, 2013.Google Scholar
- The Foundry. Nuke and nukex | advancing the art of digital compositing, 2013.Google Scholar
- P. J. Toivanen. New geodosic distance transforms for grayscale images. Pattern Recognition Letters, 17(5): 437--450, 1996. Google ScholarDigital Library
- J. Wang, P. Bhat, A. Colburn, M. Agrawala, and M. F. Cohen. Interactive video cutout. ACM Trans. Graph., 24(3): 585--594, 2005. Google ScholarDigital Library
Index Terms
- Improved image segmentation using motion
Recommendations
An improved approach of lung image segmentation based on watershed algorithm
ICIMCS '15: Proceedings of the 7th International Conference on Internet Multimedia Computing and ServiceAs a preprocessing step of chest Computed Tomography (CT) images, lung segmentation is significant for the diagnosis of lung disease. The traditional watershed algorithm is sensitive to the noise and has the drawback of over-segmentation problem. This ...
Accurate segmentation of ultrasound images using the motion cue
ISBI'10: Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to MacroAccurate segmentation of ultrasound images is desired to measure tissue shapes and sizes. But in some cases, it is difficult to segment ultrasound images purely based on static intensity values. In this paper, we propose a novel segmentation framework ...
Biomedical Image Segmentation: A Survey
AbstractMedical Image Segmentation is the process of segmenting and detecting boundaries of anatomical structures in various types of 2D and 3D-medical images. The latter come from different modalities, such as Magnetic Resonance Imaging (MRI), X-Rays, ...
Comments