Abstract
This paper addresses the problem of tracking an image partition along a sequence. We consider the case in which the regions composing such a partition display texture homogeneity properties. Several issues in dynamic scene analysis or in image sequence coding can motivate this kind of development. A general-purpose methodology involving a region-level motion-based graph representation of the partition is presented. This graph is built from both the topology of the spatial segmentation map and from spatial and temporal features related to the regions. The motion-based graph labeling is formalized within a Markovian approach. This framework is applied to the tracking of-texture-based segmentation maps which are obtained at a pixel level using also a MRF-based method. Results on synthetic and real-world image sequences are shown, and provide a first validation of the proposed approach.
This study is supported in part by DRET Agency (Direction de la Recherche Et de la Technologie — French Ministry of Defense) through a student grant.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
S. Ayer, P. Schroeter, and J. Bigün. Segmentation of moving objets by robust motion parameter estimation over multiple frames. In Proc. of Third European Conference on Computer Vision, pages 316–327, Stockholm, Sweden, May 1994.
R. Azencott and C. Graffigne. Non supervised segmentation using multi-level Markov random fields. In Proc. of the 11th Int. Conf. on Pattern Recognition, pages 201–204, The Hague, August 1992.
M. Basseville. Distance measures for signal processing and pattern recognition. Signal Processing, 18(4):349–369, December 1989.
M.J. Black. Combining intensity and motion for incremental segmentation and tracking over long image sequences. In Proc. of Second European Conference on Computer Vision, pages 485–493, Santa Margherita Ligure, Italy, May 1992.
P. Bouthemy and E. FranÇois. Motion segmentation and qualitative dynamic scene analysis from an image sequence. International Journal of Computer Vision, 10(2):1578–182, April 1993.
P.B. Chou and C.M. Brown. The theory and practise of Bayesian image modelling. International Journal of Computer Vision, 4:185–210, 1990.
I.J. Cox and S.L. Hingorani. An efficient implementation of Reid's multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence, 18(2):138–150, February 1996.
F. Dufaux, F. Moscheni, and A. Lippman. Spatio-temporal segmentation based on motion and static segmentation. In Proc of Second Int. Conf. of Image Processing, pages 306–309, Washington, October 1995.
V. Garcia-Garduño and C. Labit. On the tracking of regions over time for very low bit rate image sequence coding. In Proc. of PCS'94, pages 257–260, Sacramento, CA, USA, September 1994.
F. Heitz and P. Bouthemy. Multimodal estimation of discontinuous optical flow using Markov random fields. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(12):1217–1232, December 1993.
C. Hennebert, V. Rebuffel, and P. Bouthemy. A hierarchical approach for scene segmentation based on 2d motion. In Proc. of the 13th Int. Conf. on Pattern Recognition, pages 218–222, Vienna, August 1996.
M. Irani, B. Rousso, and S. Peleg. Detecting and tracking multiple moving objects using temporal integration. In Proc. of Second European Conference on Computer Vision, pages 282–287, Santa Margherita Ligure, Italy, May 1992.
C. Kervrann and F. Heitz. A Markov random field model-based approach to unsupervised texture segmentation using local and global spatial statistics. IEEE Trans. on Image Processing, 4(6):856~862, June 1995.
F. Meyer and P. Bouthemy. Region-based tracking using affine motion models in long image sequences. CVGIP: Image Understanding, 60(2):119–140, September 1994.
J.M Odobez and P. Bouthemy. MRF-based motion segmentation exploiting a 2D motion model robust estimation. In Proc of Second Int. Conf. of Image Processing, pages 628–631, Washington, October 1995.
J.M Odobez and P. Bouthemy. Robust multiresolution estimation of parametric motion models. Journal of Visual Communication and Image Representation, 6(4):348–365, December 1995.
C. Toklu, A.T. Erdem, M.I Sezan, and A.M. Tekalp. Tracking motion and intensity variations using hierarchical 2-d mesh modeling for synthetic object transfiguration. Graphical Models and Image Processing, 58(6):553–573, November 1996.
J.Y.A Wang and E.H Adelson. Representing moving images with layers. IEEE Trans. on Image Processing, 3(5):625–638, September 1994.
L. Wu, J. Benois-Pineau, Ph. Delagnes, and D. Barba. Spatio-temporal segmentation of image sequences for object-oriented low bit-rate image coding. Signal Processing: Image Communication, 8:513–543, September 1996.
W. Xiong and C. Graffigne. A hierarchical method for detection of moving objects. In Proc of First Int. Conf. of Image Processing, pages 795–799, Austin, November 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gelgon, M., Bouthemy, P. (1997). A region-level motion-based graph representation and labeling for tracking a spatial image partition. In: Pelillo, M., Hancock, E.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 1997. Lecture Notes in Computer Science, vol 1223. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62909-2_94
Download citation
DOI: https://doi.org/10.1007/3-540-62909-2_94
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62909-2
Online ISBN: 978-3-540-69042-9
eBook Packages: Springer Book Archive