Abstract
Video segmentation can be defined as the process of partitioning video into spatio-temporal objects that are homogeneous in some feature space, with the choice of features being very important to the success of the segmentation process. Fuzzy segmentation is a semi-automatic region-growing segmentation algorithm that assigns to each element in an image a grade of membership in an object. In this paper, we propose an extension of the multi-object fuzzy segmentation algorithm to segment pre-acquired color video shots. The color features are selected from channels belonging to different color models using two different heuristics: one that uses the correlations between the color channels to maximize the amount of information used in the segmentation process, and one that chooses the color channels based on the separation of the clusters formed by the seed spels for all possible color spaces. Motion information is also incorporated into the segmentation process by making use of dense optical flow maps. We performed experiments on synthetic videos, with and without noise, as well as on some real videos. The experiments show promising results, with the segmentations of real videos produced using hybrid color spaces being more accurate than the ones produced using three other color models. We also show that our method compares favorably to a state-of-the art video segmentation algorithm.
Similar content being viewed by others
Notes
The segmentations produced by this methods were obtained using the web service provided at http://neumann.cc.gt.atl.ga.us/segmentation/.
References
Moghaddam H, Lerallut J (1998) Volume visualization of the heart using MRI 4D cardiac images. J Comput Inform Tech 6:215–228
Carvalho B, Gau C, Herman G, Kong T (1999) Algorithms for fuzzy segmentation. Pattern Anal Appl 2(1):73–81
Carvalho B, Garduño E, Herman G (2001) Multiseeded fuzzy segmentation on the face centered cubic grid. In: Singh S, Murshed N, Kropatsch W (eds) Advances in pattern recognition: second international conference—ICAPR 2001 (LNCS 2013). Springer, Rio de Janeiro, pp 339–348
Carvalho BM, Oliveira LM, Garduno E (2006) Semi-automatic single particle segmentation on electron micrographs. In: International symposium on biomedical imaging: from nano to macro, IEEE, Washington, DC, pp 1024–1027
Herman GT, Carvalho BM (2001) Multiseeded segmentation using fuzzy connectedness. IEEE Trans Pattern Analy Mach Intell 23(5):460–474
Udupa J, Samarasekera S (1996) Fuzzy connectedness and object definition: theory, algorithms, and applications in image segmentation. Gr Models Image Process 58:246–261
Rosenfeld A (1979) Fuzzy digital topology. Inf Control 40(1):76–87
Herman G (1998) Geometry of digital spaces. Birkhäuser, Boston
Tekalp A (1995) Digital video processing. Prentice Hall, Upper Saddle River
Bovik AC (2005) Handbook of image and video processing, 2nd edn. Elsevier Academic Press, Burlington, pp 471–489 (Ch. 4.10)
Carvalho BM, Herman GT, Kong TY (2005) Simultaneous fuzzy segmentation of multiple objects. Discrete Appl Math 151(1–3):55–77
Carvalho BM, Oliveira LM, Andrade GS (2006) Fuzzy segmentation of color video shots. in: 13th international conference on discrete geometry for computer imagery (LNCS), vol 4245. Springer, Berlin, pp 494–500
Zadeh LA (1965) Fuzzy sets. Inf Control 8:338–353
Johnson S (1967) Hierarchical clustering schemes. Psychometrika 32:241–254
Cheng H, Jiang H, Sun Y, Wang J (2001) Color image segmentation: advances and prospects. Pattern Recognit 34(12):2259–2281
Gauch J, Hsia C (1992) A comparison of three color image segmentation algorithm in four color space. In: SPIE visual communications and image processing ’92, vol 1818, pp 1168–1181
Liu J, Yang YH (1994) Multiresolution color image segmentation. IEEE Trans Pattern Anal Mach Intell 16(3):689–700
VandenBroucke N, Macaire L, Posaire J (1998) Color pixels classification in an hybrid color space. In: IEEE conference on image processing, IEEE, pp 176–180
Vandenbroucke N, Macaire L, Postaire JG (2003) Color image segmentation by pixel classification in an adapted hybrid color space: application to soccer image analysis. Comput Vis Image Underst 90(2):190–216
Khan S, Shah M (2001) Object based segmentation of video using color, motion and spatial information. Comput Vis Pattern Recognit IEEE 2:746–751
Horn B, Schunck B (1981) Determinig optical flow. Artifi Intell 17:185–203
Lucas B, Kanade T (1981) An iterative image registration technique with an application to stereo vision. In: 7th international joint conference on artificial intelligence, pp 674–679
Singh A (1991) Optic flow computation: a unified perspective. IEEE Computer Society Press, Los Alamitos
Beauchemin SS, Barron JL (1995) The computation of optical flow. ACM Comput Surv 27(3):433–466
Anandan P (1989) A computational framework and an algorithm for the measurement of visual motion. Int J Comput Vis 2:283–310
McCane B, Novins K, Crannitch D, Galvin B (2001) On benchmarking optical flow. Comput Vis Image Underst 84:126–143
Proesmans M, Gool LJV, Pauwels EJ, Oosterlinck A (1994) Determination of optical flow and its discontinuities using non-linear diffusion. In: ECCV ’94: Proceedings of the third European conference-volume II on computer vision, Springer, London, pp 295–304
Baker S, Roth S, Scharstein D, Black M, Lewis J, Szeliski R (2007) A database and evaluation methodology for optical flow. In: International conference on computer vision, pp 1–8
Galvin B, McCane B, Novins K, Mason D, Mills S (1998) Recovering motion fields: an evaluation of eight optical flow algorithms. in: Proceedings of ninth British machine vision conference, Southhampton, pp 195–204
Lempitsky V, Roth S, Rother C (2008) FusionFlow: Discrete-continuous optimization for optical flow estimation, Computer Vision and Pattern Recognition. IEEE Comput Soc Conf 0:1–8
Heitz F, Bouthemy P (1993) Multimodal estimation of discontinuous optical flow using Markov random fields. IEEE Trans Pattern Anal Mach Intell 15:1217–1232
Black M, Anandan P (1996) The robust estimation of multiple motions: parametric and piecewise-smooth flow fields. Comput Vis Image Underst 63:75–104
Udupa J, Saha P, Lotufo R (2002) Relative fuzzy connectedness and object definition: theory, algorithms, and applications in image segmentation. IEEE Trans Pattern Anal Mach Intell 24:1485–1500
Gwosdek P, Zimmer H, Grewenig S, Bruhn A, Weickert J (2010) A highly efficient GPU implementation for variational optic flow based on the Euler–Lagrange framework, Technocal Representative 267. Saarland University
Gomes R, Oliveira L, Britto-Neto L, Santos T, Carvalho B, Goncalves L (2009) Producing stylized videos using the AnimVideo rendering tool. Int J Imaging Syst Technol 19:100–110
Hair JF, Black B, Babin B, Anderson R, Tatham R (2005) Multivariate data analysis, 6th edn. Prentice Hall, Upper Saddle River
Grundmann M, Kwatra V, Han M, Essa I (2010) Efficient hierarchical graph-based video segmentation. IEEE CVPR, pp 2141–2148
Werlberger M, Trobin W, Pock T, Wedel A, Cremers D, Bischof H (2009) Anisotropic Huber-L1 optical flow. In: Proceedings of the British machine vision conference (BMVC), London, pp 1–11
CVRG (2013) Optical flow algorithm evaluation. http://of-eval.sourceforge.net. Acessed Jan
Kim JB, Kim HJ (2003) Efficient region-based motion segmentation for a video monitoring system. Pattern Recogn Lett 24(1–3):113–128
Brito-Neto L, Carvalho B (2007) Message in a bottle: stylized rendering of sand movies. In: XX Brazilian symposium on computer graphics and image processing, pp 11–18
Gomes R, Souza T, Carvalho B (2007) Mosaic animations from video inputs. In: Pacific-Rim symposium on image and video technology. LNCS 4872, pp 87–99
Carvalho B, Herman G, Kong T (2005) Simultaneous fuzzy segmentation of multiple objects. Discrete Appl Math 151:55–77
Dupuis A, Vasseur P (2006) Image Segmentation by Cue Selection and Integration. Image Vis Comput 10:1053–1064
Grady L (2006) Random walks for image segmentation, pattern analysis and machine intelligence. IEEE Trans 28(11):1768–1783
Acknowledgments
Bruno M. Carvalho: Supported by FAPERN/CNPq PRONEM Grant 610006/2010, CNPq Universal Grant 486951/2012-0, INCT-MACC and PROCAD grants. Edgar Garduño: This work is supported in part by the DGAPA-UNAM under Grant IN101108.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Carvalho, B.M., Garduño, E., Santos, T.S. et al. Fuzzy segmentation of video shots using hybrid color spaces and motion information. Pattern Anal Applic 17, 249–264 (2014). https://doi.org/10.1007/s10044-013-0359-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-013-0359-1