Abstract
A computer vision system has been developed for real-time motion tracking of 3-D objects, including those with variable internal parameters. This system provides for the integrated treatment of matching and measurement errors that arise during motion tracking. These two sources of error have very different distributions and are best handled by separate computational mechanisms. These errors can be treated in an integrated way by using the computation of variance in predicted feature measurements to determine the probability of correctness for each potential matching feature. In return, a best-first search procedure uses these probabilities to find consistent sets of matches, which eliminates the need to treat outliers during the analysis of measurement errors. The most reliable initial matches are used to reduce the parameter variance on further iterations, minimizing the amount of search required for matching more ambiguous features. These methods allow for much larger frame-to-frame motions than most previous approaches. The resulting system can robustly track models with many degrees of freedom while running on relatively inexpensive hardware. These same techniques can be used to speed verification during model-based recognition.
Similar content being viewed by others
References
Bray, A.J. 1990. Tracking objects using image disparities, Image Vis. Comput. 8(1):4–9.
Brooks, R.A. 1981. Symbolic reasoning among 3-D models and 2-D images, Artificial Intelligence 17:285–348.
Canny, J. 1986. A computational approach to edge detection, IEEE Trans. Patt. Anal. Mach. Intell. 8(6):679–698.
Dickmanns, E., and Graefe, V. 1988. Dynamic monocular machine vision, Mach. Vis. Appl. 1:223–240.
Duda, R.O., and Hart, P.E. 1973. Pattern Classification and Scene Analysis. Wiley: New York.
Gennery, D. 1981. A feature-based scene matcher, Proc. 7th Intern. Joint Conf. Artif. Intell. Vancouver, Canada, 667–673.
Gennery, D. 1982. Tracking known three-dimensional objects, Proc. 2nd Nation. Conf. Artif. Intell., Pittsburgh, 13–17.
Grimson, E., and Lozano-Pérez, T. 1987. Localizing overlapping parts by searching the interpretation tree. IEEE Trans. Patt. Anal. Mach. Intell. 9:469–482.
Lowe, D.G. 1985. Perceptual Organization and Visual Recognition. Kluwer Academic Publishers: Boston, MA.
Lowe, D.G. 1987. Three-dimensional object recognition frm single two-dimensional images, Artificial Intelligence 31(3):355–395.
Lowe, D.G., 1991. Fitting parameterized three-dimensional models to images, IEEE Trans. Patt. Anal. Mach. Intell. 13(5):441–450.
Marr, D., and Hildreth, E. 1980. Theory of edge detection, Proc. Roy. Soc. London, B207:187–217.
Stephens, R.S. 1990. Real-time 3D object tracking, Image Vis. Comput. 8(1):91–96.
Thompson, D.W., and Mundy, J.L. 1988. Model-based motion analysis: Motion from motion, Robotics Research: The 4th Intern. Symp., R. Bolles and B. Roth, eds., MIT Press: Cambridge, MA, 299–309.
Verghese, G., and Dyer, C.R. 1988. Real-time model-based tracking of three-dimensional objects, Univ. of Wisconsin, Computer Sciences, Tech. Rept. 806.
Verghese, G., Gale, K., and Dyer, C.R. 1990. Real-time, paralielmotion tracking of three-dimensional objects from spatiotemporal image sequences, in Parallel Algorithms for Machine Intelligence and Vision, Kumar et al., eds., Springer-Verlag: New York.
Wu, J.J., Rink, R.E., Caelli, T.M., and Gourishankar, V.G., 1989. Recovery of the 3-D location and motion of a rigid object through camera image (an extended Kalman filter approach), Intern. J. Comput. Vis. 2(4):373–394.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Lowe, D.G. Robust model-based motion tracking through the integration of search and estimation. Int J Comput Vision 8, 113–122 (1992). https://doi.org/10.1007/BF00127170
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00127170