Abstract
There has been a great deal of research interest in contour tracking over the last five years. This article combines themes from tracking theory—elastic models and stochastic filtering—with the notion of affine invariance to synthesize a substantially new and demonstrably effective framework for contour tracking.
A mechanism is developed for incorporating a shape template into a contour tracker via an affine invariant coupling. In that way the tracker becomes selective for shape and therefore able to ignore background clutter. Affine invariance ensures that the effect of varying viewpoint is accommodated. Use of a standard statistical filtering framework allows uncertainties to be treated systematically, which accommodates object flexibility and un-modeled distortions such as the deformation of a silhouette under motion.
The statistical framework also facilitates a further development. In place of heuristically determined spatial scale for feature search, both spatial scale and temporal memory are controlled automatically and in a way that is responsive to the tracking process. Typically, the tracker operates initially in a coarse scale/short memory mode while it searches for a feature. Then spatial scale diminishes to allow more precise localization while memory (temporal scale) lengths to take advantage of motion coherence. All system parameters are determined by natural assumptions and desired tracking performance, leaving none to be fixed heuristically.
Versions of the tracker have been implemented at video rate, both on SUN 4 and in parallel, using a network of 11 transputers. The theoretically established properties of automatic control of spatiotemporal scale and of affine invariance are demonstrated using the implemented tracker.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Ayache, N., Cohen, I., and Herlin, I. 1992. Medical image tracking. In A. Blake and A. Yuille, eds.,Active Vision, pp. 285–302, MIT Press: Cambridge, MA.
Bar-Shalom, Y., and Fortmann, T. 1988.Tracking and Data Association. Academic Press: San Diego, CA.
Bartels, R., Beatty, J., and Barsky, B. 1987.An Introduction to Splines for Use in Computer Graphics and Geometric Modeling. Morgan Kaufmann: San Mateo, CA.
Bennett, A., and Craw, I. 1991. Finding image features for deformable templates and detailed prior statistical knowledge. In P. Mowforth, ed.,Proc. British Machine Vision Conference, pp. 233–239, Glasgow. Springer-Verlag: London.
Blake, A. 1992. Computational modelling of hand-eye coordination,Proc. Roy. Soc. London B., 337:351–360.
Blake, A., Brady, J., Cipolla, R., Xie, Z., and Zisserman, A. 1991. Visual navigation around curved obstacles,Proc. IEEE Intern. Conf. Robot. Automat. 3:2490–2499.
Blake, A., and Yuille, A., eds. 1992.Active Vision, MIT Press: Cambridge, MA.
Blake, A., Zisserman, A. and Cipolla, R. 1992. Visual exploration of freespace. In A. Blake and A. Yuille, eds.,Active Vision, pp. 175–188, MIT Press: Cambridge, MA.
Bookstein, F.L. 1988. Thin-plane splines and the decomposition of deformations,IEEE Trans. Patt. Anal. Mach. Intell. 10:
Cipolla, R., and Blake, A. 1992. Motion planning using image divergence and deformation. In A. Blake and A. Yuille, eds.,Active Vision, pp. 39–58. MIT Press: Cambridge, MA.
Cipolla, R., and Yamamoto, M. 1990. Stereoscopic tracking of bodies in motion,Image and Vis. Comput. 8 (1):85–90.
Curwen, R. 1993.Dynamic and Adaptive Contours. Ph.D. thesis, University of Oxford.
Curwen, R., and Blake, A. 1992. Dynamic contours: real-time active splines. In A. Blake and A. Yuille, eds.,Active Vision, pp. 39–58. MIT Press: Cambridge, MA.
Dickmanns, E., and Graefe, V. 1988. Applications of dynamic monocular machine vision,Mach. Vis. Applic. 1:241–261.
Faux, I., and Pratt, M. 1979.Computational Geometry for Design and Manufacture. Ellis-Horwood (VCH Pubs: New York).
Fischler, M.A., and Elschlager, R.A. 1973. The representation and matching of pictorial structures,IEEE Trans. Computers C-22(1).
Gelb, A., ed. 1974.Applied Optimal Estimation. MIT Press: Cambridge, MA.
Grenander, U., Chow, Y., and Keenan, D.M. 1991.HANDS. A Pattern Theoretical Study of Biological Shapes. Springer-Verlag: New York.
Harris, C. 1992. Tracking with rigid models. In A. Blake, and A. Yuille, eds.,Active Vision, pp. 59–74. MIT Press: Cambridge, MA.
Harris, C., and Stennett, C. 1990. Rapid—a video-rate object tracker,Proc. 1st British Mach. Vis. Conf., pp. 73–78, Oxford.
Horn, B. 1986.Robot Vision. McGraw-Hill: New York.
Inoue, H., and Mizoguchi, H. 1985. A flexible multi window vision system for robots,Proc. 2nd Intern. Symp. Robot. Res., pp. 95–102.
Kass, M.,Witkin, A., and Terzopoulos, D. 1987. Snakes: Active contour models,Proc. 1st Intern. Conf. Comput. Vis., pp. 259–268, London.
Koenderink, J., and Van Doorn, A. 1991. Affine structure from motion,J. Opt. Soc. Amer. A. 8 (2):337–385.
Lipson, P., Yuille, A., Keeffe, D., Cavanaugh, J., Taafe, J., and Rosenthal, D. 1990. Deformable templates for feature extraction from medical images. In O. Faugeras, ed.,Proc. 1st Europ. Conf. Comput. Vis., France, pp. 413–417. Springer-Verlag: New York.
Lowe, D. 1992. Robust model-based motion tracking through the integration of search and estimation,Intern. J. Comput. Vis. 8 (2):113–122.
Maybeck, P. 1979.Stochastic Models, Estimation and Control, vol I. Academic Press: San Deigo, CA.
Menet, S., Saint-Marc, P., and Medioni, G. 1990. B-snakes: implementation and application to stereo,Proceedings DARPA, pp. 720–726.
Mundy, J., and Zisserman, A. 1992.Geometric Invariance in Computer Vision. MIT Press: Cambridge, MA.
Rao, C. 1973.Linear Statistical Inference and Its Applications, Wiley: New York.
Scott, G. 1987. The alternative snake—and other animals,Proc. 3rd Alvey Vis. Conf. pp. 341–347.
Sullivan, G. 1992. Visual interpretation of known objects in constrained scenes,Phil. Trans. Roy. Soc. London B 337:109–118.
Szeliski, R., and Terzopoulos, D. 1991. Physically based and probabilistic modeling for computer vision. In B.C. Vemuri, ed.,Proc. SPIE 1570, Geometric Methods in Computer Vision, pp. 140–152, San Diego, CA. Society of Photo-Optical Instrumentation Engineers.
Terzopoulos, D., and Metaxas, D. 1991. Dynamic 3D models with local and global deformations: deformable superquadrics,IEEE Trans. Patt. Anal. Mach. Intell. 13(7).
Thompson, D.W., and Mundy, J.L. 1987. Three-dimensional model matching from an unconstrained viewpoint,Proc. Intern. Conf. Robot. Automat., Raleigh, NC.
Ullman, S., and Basri, R. 1991. Recognition by linear combinations of models,IEEE Trans. Patt. Analy. Mach. Intell. 13(10):992–1006.
Wang, H., and Brady, M. 1992. Vision for mobile robots,Proc. Roy. Soc. London B. 337:341–350.
Yuille, A.L., Hallinan, P.W., and Cohen, D.S. 1992. Detecting facial features using deformable templates,Intern. J. Comput. Vis. 8, 2, 99–112.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Blake, A., Curwen, R. & Zisserman, A. A framework for spatiotemporal control in the tracking of visual contours. Int J Comput Vision 11, 127–145 (1993). https://doi.org/10.1007/BF01469225
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01469225