Skip to main content
SpringerLink
Log in

Bayesian Object Localisation in Images

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

A Bayesian approach to intensity-based object localisation is presented that employs a learned probabilistic model of image filter-bank output, applied via Monte Carlo methods, to escape the inefficiency of exhaustive search.

An adequate probabilistic account of image data requires intensities both in the foreground (i.e. over the object), and in the background, to be modelled. Some previous approaches to object localisation by Monte Carlo methods have used models which, we claim, do not fully address the issue of the statistical independence of image intensities. It is addressed here by applying to each image a bank of filters whose outputs are approximately statistically independent. Distributions of the responses of individual filters, over foreground and background, are learned from training data. These distributions are then used to define a joint distribution for the output of the filter bank, conditioned on object configuration, and this serves as an observation likelihood for use in probabilistic inference about localisation.

The effectiveness of probabilistic object localisation in image clutter, using Bayesian Localisation, is illustrated. Because it is a Monte Carlo method, it produces not simply a single estimate of object configuration, but an entire sample from the posterior distribution for the configuration. This makes sequential inference of configuration possible. Two examples are illustrated here: coarse to fine scale inference, and propagation of configuration estimates over time, in image sequences.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • 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.

    Google Scholar 

  • Bascle, B. and Deriche, R. 1995. Region tracking through image sequences. In Proc. 5th Int. Conf. on Computer Vision, Boston, pp. 302-307.

  • Baumberg, A. and Hogg, D. 1995. Generating spatiotemporal models from examples. In Proc. British Machine Vision Conf., Vol. 2, pp. 413-422.

    Google Scholar 

  • Belhumeur, P. and Kriegman, D. 1998. What is the set of images of an object under all possible illumination conditions.Int. J. Computer Vision, 28(3):245-260.

    Google Scholar 

  • Bell, A. and Sejnowski, T. 1997. Edges are the independent components of natural scenes. In Advances in Neural Information Processing Systems, MIT Press: Cambridge, MA, Vol. 9, pp. 831-837.

    Google Scholar 

  • Beymer, D. and Poggio, T. 1995. Face recognition from one example view. In Proc. 5th Int. Conf. on Computer Vision, Boston, USA, pp. 500-507.

  • Black, M. and Yacoob, Y. 1995. Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motion. In Proc. 5th Int. Conf. on Computer Vision, Boston, USA, pp. 374-381.

  • Blake, A. and Isard, M. 1998. Active Contours. Springer: New York.

    Google Scholar 

  • Blake, A., Isard, M., and Reynard, D. 1995. Learning to track the visual motion of contours. J. Artificial Intelligence, 78:101-134.

    Google Scholar 

  • Bookstein, F. 1989. Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(6):567-585.

    Google Scholar 

  • Burt, P. 1983. Fast algorithms for estimating local image properties. Computer Vision, Graphics and Image Processing, 21:368-382.

    Google Scholar 

  • Cootes, T., Taylor, C., Cooper, D., and Graham, J. 1995. Active shape models-their training and application. Computer Vision and Image Understanding, 61(1):38-59.

    Google Scholar 

  • Field, D. 1987. Relations between the statistics of natural images and the response properties of cortical cells. J. Optical Soc. of America A., 4:2379-2394.

    Google Scholar 

  • Gelfand, A. and Smith, A. 1990. Sampling-based approaches to computing marginal densities. J. Am. Statistical Assoc., 85(410):398-409.

    Google Scholar 

  • Geman, D. and Jedynak, B. 1996. An active testing model for tracking roads in satellite images. IEEE Trans. Pattern Analysis and Machine Intell., 18(1):1-14.

    Google Scholar 

  • Geman, S. and Geman, D. 1984. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 6(6):721-741.

    Google Scholar 

  • Geweke, J. 1989. Bayesian inference in econometric models using Monte Carlo integration. Econometrica, 57:1317-1339.

    Google Scholar 

  • Gordon, N., Salmond, D., and Smith, A. 1993. Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proc. F, 140(2):107-113.

    Google Scholar 

  • Grenander, U. 1976-1981. Lectures in Pattern Theory I, II and III. Springer: New York.

    Google Scholar 

  • Grenander, U., Chow, Y., and Keenan, D. 1991. HANDS. A Pattern Theoretical Study of Biological Shapes. Springer-Verlag: New York.

    Google Scholar 

  • Grenander, U. and Miller, M. 1994. Representations of knowledge in complex systems (with discussion). J. Roy. Stat. Soc. B., 56:549-603.

    Google Scholar 

  • Hager, G. and Toyama, K. 1996. Xvision: Combining imagewarping and geometric constraints for fast tracking. In Proc. 4th European Conf. Computer Vision, pp. 507-517.

  • Isard, M. and Blake, A. 1996. Visual tracking by stochastic propagation of conditional density. In Proc. 4th European Conf. Computer Vision, pp. 343-356, Cambridge: England.

  • Isard, M. and Blake, A. 1998. Condensation-Conditional density propagation for visual tracking. Int. J. Computer Vision, 28(1):5-28.

    Google Scholar 

  • Kitagawa, G. 1996. Monte Carlo filter and smoother for non-Gaussian nonlinear state space models. Journal of Computational and Graphical Statistics, 5(1):1-25.

    Google Scholar 

  • Liu, J. and Chen, R. 1995. Blind deconvolution via sequential imputations. J. Am. Stat. Soc, 90(430):567-576.

    Google Scholar 

  • Mallat, S. 1989. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11:674-693.

    Google Scholar 

  • Matthies, L., Kanade, T., and Szeliski, R. 1989. Kalman filter-based algorithms for estimating depth from image sequences. Int. J. Computer Vision, 3:209-236.

    Google Scholar 

  • Mumford, D. 1996. Pattern theory: A unifying perspective. In Perception as Bayesian Inference, D. Knill, and W. Richard (Eds.), pp. 25-62. Cambridge University Press: Cambridge.

    Google Scholar 

  • Neal, R. 2000. Annealed importance sampling. Statistics and Computing, in press.

  • Olshausen, B. and Field, D. 1996. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381:607-609.

    Google Scholar 

  • Perona, P. 1992. Steerable-scalable kernels for edge detection and junction analysis. J. Image and Vision Computing, 10(10):663-672.

    Google Scholar 

  • Ripley, B. 1992. Classification and clustering in spatial and image data. In Procs. 15 Jahrestagung von Gesellschaft fur Klassifikation. H. Goebl and M. Schader (Eds.), Springer-Verlag: NewYork.

    Google Scholar 

  • Scharstein, D. and Szeliski, R. 1998. Stereo matching with nonlinear diffusion. Int. J. Computer Vision, 28(2):155-174.

    Google Scholar 

  • Shirai, Y. and Nishimoto, Y. 1985. A stereo method using disparity histograms and multi-resolution channels. In Proc. 3rd Int. Symp. on Robotics Research, pp. 27-32.

  • Storvik, G. 1994. A Bayesian approach to dynamic contours through stochastic sampling and simulated annealing. IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(10):976-986.

    Google Scholar 

  • Sullivan, J. and Blake, A. 2000. Satistical foreground modelling for object localisation. In Proc. European Conf. Computer Vision, vol. 2, pp. 307-323.

    Google Scholar 

  • Sullivan, J., Blake, A., Isard, M., and MacCormick, J. 1999. Object localisation by Bayesian correlation. In Proc. 7th Int. Conf. on Computer Vision, pp. 1068-1075.

  • Szeliski, R. 1990. Bayesian modelling of uncertainty in low-level vision. Int. J. Computer Vision, 5(3):271-301.

    Google Scholar 

  • Vetter, T. and Poggio, T. 1996. Image synthesis from a single example image. In Proc. 4th European Conf. Computer Vision, Cambridge: England, pp. 652-659.

  • Viola, P. and Wells, W. 1993. Alignment by maximisation of mutual information. In Proc. 5th Int. Conf. on Computer Vision, pp. 16-23.

  • Witkin, A., Terzopoulos, D., and Kass, M. 1987. Signal matching through scale space. Int. J. Computer Vision, 1(2):133-144.

    Google Scholar 

  • Zhu, S. and Mumford, D. 1997. GRADE: Gibbs reaction and diffusion equation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(11):1236-1250.

    Google Scholar 

  • Zhu, S., Wu, Y., and Mumford, D. 1998. Filters, random fields and maximum entropy (FRAME). Int. J. Computer Vision, 27(2):107-126.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Engineering Science, University of Oxford, Parks Road, Oxford, OX1 3PJ, UK

    J. Sullivan, A. Blake, M. Isard & J. Maccormick

Authors
  1. J. Sullivan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. Blake
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. Isard
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. J. Maccormick
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sullivan, J., Blake, A., Isard, M. et al. Bayesian Object Localisation in Images. International Journal of Computer Vision 44, 111–135 (2001). https://doi.org/10.1023/A:1011818912717

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1011818912717

Search

Navigation