Spatial dependence in the observation of visual contours
Two challenging problems in object recognition are: to output structures that can be interpreted statistically; and to degrade gracefully under occlusion. This paper proposes a new method for addressing both problems simultaneously. Specifically, a likelihood ratio termed the Markov discriminant is used to make statistical inferences about partially occluded objects. The Markov discriminant is based on a probabilistic model of occlusion which introduces spatial dependence between observations on the object boundary. This model is a Markov random field, which acts as the prior for Bayesian estimation of the posterior using Markov chain Monte Carlo (MCMC) simulation. The method takes as its starting point a “contour discriminant” designed to differentiate between a target and random background clutter.
KeywordsPosterior Distribution Markov Chain Monte Carlo Importance Sampling Markov Random Field Measurement Line
Unable to display preview. Download preview PDF.
- 1.A. Amir and M. Lindenbaum. Grouping based non-additive verification. Technical Report 9518, Center for Intelligent Systems, Technion, 1996.Google Scholar
- 2.D. Chandler. Introduction to Statistical Mechanics. Oxford University Press, 1987.Google Scholar
- 4.U. Grenander. Lectures in Pattern Theory I, II and III. Springer, 1976–1981.Google Scholar
- 5.W.E.L. Grimson, D.P. Huttenlocher, and D.W. Jacobs. A study of affine matching with bounded sensor error. In Proc. 2nd European Conf. Computer Vision, pages 291–306, 1992.Google Scholar
- 7.T.K. Leung, M.C. Burl, and P. Perona. Finding faces in cluttered scenes using random graph matching. In Proc. IEEE PAMI Conf., pages 637–644, Cambridge, June 1995.Google Scholar
- 9.J.P. MacCormick and A. Blake. A probabilistic contour discriminant for object localisation. In Proc. 8th Int. Conf. Computer Vision, Jan 1998.Google Scholar
- 11.B.D. Ripley. Stochastic simulation. New York: Wiley, 1987.Google Scholar
- 12.C. Rothwell. Reasoning about occlusions during hypothesis verification. In Proc. 4th European Conf. Computer Vision, pages 599–609, April 1996.Google Scholar
- 13.I. Shimshoni and J. Ponce. Probabilistic 3D object recognition. In Proc. 5th Int. Conf. Computer Vision, pages 488–493, 1995.Google Scholar
- 14.G. Winkler. Image analysis, random fields and dynamic Monte Carlo methods. Springer, 1995.Google Scholar