Abstract
This paper presents a method for incrementally segmenting images over time using both intensity and motion information. This is done by formulating a model of physically significant image resgions using local constraints on intensity and motion and then finding the optimal segmentation over time using an incremental stochastic minimization technique. The result is a robust and dynamic segmentation of the scene over a sequence of images. The approach has a number of benefits. First, discontinuities are extracted and tracked simultaneously. Second, a segmentation is always available and it improves over time. Finally, by combining motion and intensity, the structural properties of discontinuities can be recovered; that is, discontinuities can be classified as surface markings or actual surface boundaries.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This work was supported in part by a grants from the National Aeronautics and Space Administration (NGT-50749 and NASA RTOP 506-47), by ONR Grant N00014-91-J-1577, and by a grant from the Whitaker Foundation.
This article was processed using the LATEX macro package with ECCV92 style.
Download to read the full chapter text
Chapter PDF
References
Black, M. J., and Anandan, P., “Robust dynamic motion estimation over time,” Proc. Comp. Vision and Pattern Recognition, CVPR-91, Maui, Hawaii, June 1991, pp. 296–302.
Blake, A. and Zisserman, A., Visual Reconstruction, The MIT Press, Cambridge, Massachusetts, 1987.
Bouthemy, P. and Lalande, P., “Detection and tracking of moving objects based on a statistical regularization method in space and time,” Proc. First European Conf. on Computer Vision, ECCV-90, Antibes, France, April 1990, pp. 307–311.
Chou, P. B., and Brown, C. M., “The theory and practice of bayesian image labeling,” Int. Journal of Computer Vision, Vol. 4, No. 3, 1990, pp. 185–210.
François, E. and Bouthemy, P., “Multiframe-based identification of mobile components of a scene with a moving camera,” Proc. Comp. Vision and Pattern Recognition, CVPR-91, Maui, Hawaii, June 1991, pp. 166–172.
Geman, D., Geman, S., Graffigne, C., and Dong, P., “Boundary detection by constrained optimization,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 7, July 1990, pp. 609–628.
Geman, S. and Geman, D., “Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-6, No. 6, November 1984.
Heitz, F. and Bouthemy, P., “Multimodal motion estimation and segmentation using Markov random fields,” Proc. IEEE Int. Conf. on Pattern Recognition, June, 1990, pp. 378–383.
Matthies, L., Szeliski, R., Kanade, T., “Kalman filter-based algorithms for estimating depth from image sequences,” Int. J. of Computer Vision, 3(3), Sept. 1989, pp. 209–236.
Murray, D. W. and Buxton, B. F., “Scene segmentation from visual motion using global optimization,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. PAMI-9, No. 2, March 1987, pp. 220–228.
Navab, N., Deriche, R., and Faugeras, O. D., “Recovering 3D motion and structure from stereo and 2D token tracking cooperation,” Proc. Int. Conf. on Comp. Vision, ICCV-90, Osaka, Japan, Dec. 1990, pp. 513–516.
Thompson, W. B., “Combining motion and contrast for segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-2 1980, pp. 543–549.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Black, M.J. (1992). Combining intensity and motion for incremental segmentation and tracking over long image sequences. In: Sandini, G. (eds) Computer Vision — ECCV'92. ECCV 1992. Lecture Notes in Computer Science, vol 588. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55426-2_54
Download citation
DOI: https://doi.org/10.1007/3-540-55426-2_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55426-4
Online ISBN: 978-3-540-47069-4
eBook Packages: Springer Book Archive