Abstract
We develop a modified particle filter which is shown to be effective at searching the high-dimensional configuration spaces (c. 30 + dimensions) encountered in visual tracking of articulated body motion. The algorithm uses a continuation principle, based on annealing, to introduce the influence of narrow peaks in the fitness function, gradually. The new algorithm, termed annealed particle filtering, is shown to be capable of recovering full articulated body motion efficiently. A mechanism for achieving a soft partitioning of the search space is described and implemented, and shown to improve the algorithm’s performance. Likewise, the introduction of a crossover operator is shown to improve the effectiveness of the search for kinematic trees (such as a human body). Results are given for a variety of agile motions such as walking, running and jumping.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Blake, A. and Isard, M. 1998. Active Contours. Springer.
Cham, T.-J. and Rehg, J.M. 1999. Dynamic feature ordering for ef-ficient registration. In Proc. 7th Int’l Conf. on Computer Vision, Corfu, vol. 2, pp. 1084-1091.
Cham, T.-J. and Rehg J.M. 1999. A multiple hypothesis approach to figure tracking. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 239-245.
Deutscher, J., Blake, A., North, B., and Bascle, B. 1999. Tracking through singularities and discontinuities by random sampling. In Proc. 7th Int. Conf. on Computer Vision, vol. 2, pp. 1144-1149.
Deutscheer, Blake, A., and Reid, I.D. 2000. Articulated body motion capture by annealed particle filtering. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 126-133.
Deutscher, J., Davison, A.J., and Reid, I.D. 2001. Automatic parti-tioning of high dimensional search spaces associated with articu-lated body motion capture. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 669-676.
Deutscher, J., Isard, M., and MacCormick, J. 2002. Automatic cam-era calibration from a single manhattan image. In Proc. 7th Euro-pean Conf. on Computer Vision, Copenhagen, vol. 4, pp. 175-188.
Drummond, T. and Cipolla, R. 2001. Real-time tracking of highly articulated suctures in the presence of noisy measurements. In Proc. 8th Int’l Conf. on Computer Vision, Vancouver, pp. 315-320.
Gavrila, D. and Davis, L.S. 1996. 3d model-based tracking of humans in action: A multi-view approach. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 73-80.
Harris, C.G. 1992. Tracking with rigid models. In Active Vision. A. Blake and A. Yuille (Eds.), MIT Press: Cambridge, MA.
Isard, M.A. and Blake, A. 1996. Visual tracking by stochastic prop-agation of conditional density. In Proc. 4th European Conf. on Computer Vision, Cambridge, England, p. 343-356.
Kirkpatrick, S., Gellatt, C.D., and Vecchi, M.P. 1983. Optimisation by simulated annealing. Science, 220(4598):671-680.
Lyons, D. 2002. A qualitative approach to computer sign language recognition. Master’s thesis, University of Oxford.
MacCormick, J. 2000. Probabilistic models and stochastic algorithms for visual hacking. PhD thesis, University of Oxford.
MacCormick, J. and Blake, A. 1999. A probabilistic exclusion prin-ciple for tracking multiple objects. In Proc. 7th Int. Conf. on Com-purter Vision, vol. 1, pp. 572-578.
MacCormick, J. and Isaru-d, M. 2000. Partitioned sampling, articulated objects and interface-quality hand hacking. In Proc. 6th European Conf. on Computer Vision, Dublin, vol. 2, pp. 3-19.
Metropolis, N., Rosenbluth, AW., Rosenbluth, M.N., Teller, A.H., and Teller, E. 1953. Equations of state calculations by fast corm-putting machine. J. Chern. Phys., 21:1087-1091.
Mikic, I., Trivedi, M., hunter, E., and Cosman, P. 2001. Articulated body posture estimation from multi-camera voxel data. In Proc. International Journal of Computer Vision KL3179-05/5384380 of the IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 455-462.
Neal, R.M. 2001. Annealed importance sampling. Statistics and Computing, ( 11):125-139.
Plankers, R. and Fua, P. 2003. Articulated soft objects for multi-view shape and motion capture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(10).
Sidenbladh, H., Black, M.J., and Fleet, D.J. 2000. Stochastic track-ing of 3D human figures using 2D image motion. In Proc. 6th European Conf. on Computer Vision, Dublin, vol. 2, pp. 702-718.
Sidenbladh, H., Black, M.J., and Sigal, L. 2002. Implicit probabilistic models of human motion for synthesis and tracking. In Proc. 7th European Conf.i on Computer Vision, Copenhagen, vol. 1, pp. 784-800.
Sminchisescu, C. and Triggs, B. 2001. Covariance scaled sampling for monocular 3d body tracking. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 447-454.
Sminchisescu, C. and Triggs, B. 2002. Hyperdynamics importance sampling. In Proc. 7th European Conf. on Computer Vision, Copenhagen, vol. 1, pp. 769-783.
Sminchisescu, C. and Triggs, B. 2003. Kinematic jump processes for monocular 3d human tracking. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 69-76.
Sullivan, J., Blake, A., Isard, M., and MacConnick, J. 1999. Object localization by bayesian correlation. In Proc. 7th Int. Conf. on Computer Vision, vol. 2, pp. 1068-1075.
Wachter, S. and Nagel, IH. 1999. Tracking persons in monocular image sequences. Computer Vision and Image Understanding, 74(3):174-192.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Deutscher, J., Reid, I. Articulated Body Motion Capture by Stochastic Search. Int J Comput Vision 61, 185–205 (2005). https://doi.org/10.1023/B:VISI.0000043757.18370.9c
Issue Date:
DOI: https://doi.org/10.1023/B:VISI.0000043757.18370.9c