User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Learning and propagation of dominant colors for fast video segmentation

Primary tabs

download
  • Open access
  • PDF
  • 7.84 M
download
  • Open access
  • PDF
  • 7.84 M
download
  • Open access
  • PDF
  • 7.84 M
Verleysen, Cédric [UCL] De Vleeschouwer, Christophe [UCL]

Color segmentation is an essential problem in image processing. While most of the recent works focus on the segmentation of individual images, we propose to use the temporal color redundancy to segment arbitrary videos. In an initial phase, a k-medoids clustering is applied on histogram peaks observed on few frames to learn the dominant colors composing the recorded scene. In a second phase, these dominant colors are used as reference colors to speed up a color-based segmentation process and, are updated on-the-fly when the scene changes. Our evaluation first shows that the proprieties of k-medoids clustering make it well suited to learn the dominant colors. Then, the efficiency and the effectiveness of the proposed method are demonstrated and compared to standard segmentation benchmarks. This assessment reveals that our approach is more than 250 times faster than the conventional mean-shift segmentation, while preserving the segmentation accuracy.

Document type Communication à un colloque (Conference Paper) – Présentation orale avec comité de sélection
Access type Accès libre
Publication date 2013
Language Anglais
Conference "Advanced Concepts for Intelligent Vision Systems", Poznan (Poland) (du 28/10/2013 au 31/10/2013)
Journal information "Lecture Notes in Computer Science" - Vol. LNCS , no.8192, p. 657 (2013)
Peer reviewed yes
issn 0302-9743
e-issn 1611-3349
Host document "Advanced Concepts for Intelligent Vision Systems, Poznan, Poland, Lecture Notes in Computer Science Volume 8192"- 657-668 (ISBN : 978-3-319-02894-1)
Publisher Springer
Publication status Publié
Affiliation UCL - SST/ICTM/ELEN - Pôle en ingénierie électrique
Keywords box- cox transform ; segmentation ; clustering ; color learning ; k-medoids
Links
  1. Alpert Sharon, Galun Meirav, Basri Ronen, Brandt Achi, Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration, 10.1109/cvpr.2007.383017
  2. Bai Xue, Wang Jue, Simons David, Sapiro Guillermo, Video SnapCut : robust video object cutout using localized classifiers, 10.1145/1531326.1531376
  3. Box, G., Cox, D.: An analysis of transformations. Journal of the Royal Statistical Society. Series B (Methodological), 211–252 (1964)
  4. Boykov Yuri, Funka-Lea Gareth, Graph Cuts and Efficient N-D Image Segmentation, 10.1007/s11263-006-7934-5
  5. Brendel William, Todorovic Sinisa, Video object segmentation by tracking regions, 10.1109/iccv.2009.5459242
  6. Carreira-Perpinan Miguel A., Gaussian Mean-Shift Is an EM Algorithm, 10.1109/tpami.2007.1057
  7. Yizong Cheng, Mean shift, mode seeking, and clustering, 10.1109/34.400568
  8. Comaniciu D., Meer P., Mean shift: a robust approach toward feature space analysis, 10.1109/34.1000236
  9. Dorea Camilo, de Queiroz Ricardo L., Depth map reconstruction using color-based region merging, 10.1109/icip.2011.6115861
  10. Ellis Liam, Zografos Vasileios, Online Learning for Fast Segmentation of Moving Objects, Computer Vision – ACCV 2012 (2013) ISBN:9783642374432 p.52-65, 10.1007/978-3-642-37444-9_5
  11. Fitzmaurice Garrett M, Lipsitz Stuart R, Parzen Michael, Approximate Median Regression via the Box-Cox Transformation, 10.1198/000313007x220534
  12. Fukuchi Ken, Miyazato Kouji, Kimura Akisato, Takagi Shigeru, Yamato Junji, Saliency-based video segmentation with graph cuts and sequentially updated priors, 10.1109/icme.2009.5202577
  13. Fulkerson Brian, Soatto Stefano, Really Quick Shift: Image Segmentation on a GPU, Trends and Topics in Computer Vision (2012) ISBN:9783642357398 p.350-358, 10.1007/978-3-642-35740-4_27
  14. Galun, Sharon, Basri, Brandt, Texture segmentation by multiscale aggregation of filter responses and shape elements, 10.1109/iccv.2003.1238418
  15. Grundmann Matthias, Kwatra Vivek, Han Mei, Essa Irfan, Efficient hierarchical graph-based video segmentation, 10.1109/cvpr.2010.5539893
  16. Huang, Y., Liu, Q., Metaxas, D.: Video object segmentation by hypergraph cut. In: Proc. of IEEE CVPR 2009, pp. 1738–1745 (2009)
  17. Li Yin, Sun Jian, Shum Heung-Yeung, Video object cut and paste, 10.1145/1073204.1073234
  18. Mignotte Max, A de-texturing and spatially constrained K-means approach for image segmentation, 10.1016/j.patrec.2010.09.016
  19. Moscheni F., Bhattacharjee S., Kunt M., Spatio-temporal segmentation based on region merging, 10.1109/34.713358
  20. Price Brian L., Morse Bryan S., Cohen Scott, LIVEcut: Learning-based interactive video segmentation by evaluation of multiple propagated cues, 10.1109/iccv.2009.5459293
  21. Multivariate Observations, ISBN:9780470316641, 10.1002/9780470316641
  22. Jianbo Shi, Malik J., Normalized cuts and image segmentation, 10.1109/34.868688
  23. Velmurugan, Computational Complexity between K-Means and K-Medoids Clustering Algorithms for Normal and Uniform Distributions of Data Points, 10.3844/jcssp.2010.363.368
  24. Verleysen, C., De Vleeschouwer, C.: Recognition of sport players’ numbers using fast color segmentation. In: Proc. of the SPIE-IS&T Electronic Imaging (SPIE 2012), vol. 8305 (2012)
  25. Wang Tinghuai, Guillem Jean-Yves, Collomosse John, Multi-label propagation for coherent video segmentation and artistic stylization, 10.1109/icip.2010.5649291
Bibliographic reference Verleysen, Cédric ; De Vleeschouwer, Christophe. Learning and propagation of dominant colors for fast video segmentation.Advanced Concepts for Intelligent Vision Systems (Poznan (Poland), du 28/10/2013 au 31/10/2013). In: Lecture Notes in Computer Science, Vol. LNCS , no.8192, p. 657 (2013)In: Advanced Concepts for Intelligent Vision Systems, Poznan, Poland, Lecture Notes in Computer Science Volume 8192, Springer2013, p.657-668
Permanent URL http://hdl.handle.net/2078.1/134475