Object localization by Bayesian correlation
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 11, 1068-1075 vol.2
- https://doi.org/10.1109/iccv.1999.790391
Abstract
Maximisation of cross correlation is a commonly used principle for intensity based object localization that gives a single estimate of location. However, to facilitate sequential inference (e.g. over time or scale) and to allow the representation of ambiguity, it is desirable to represent an entire probability distribution for object location. Although the cross correlation itself (or some function of it) has sometimes been treated as a probability distribution, this is not generally justifiable. Bayesian correlation achieves a consistent probabilistic treatment by combining several developments. The first is the interpretation of correlation matching functions in probabilistic terms, as observation likelihoods. Second, probability distributions of filter bank responses are learned from training examples. Inescapably, response learning also demands statistical modelling of background intensities, and there are links here with image coding and Independent Component Analysis. Lastly, multi scale processing is achieved in a Bayesian context by means of a new algorithm, layered sampling, for which asymptotic properties are derived.Keywords
This publication has 14 references indexed in Scilit:
- Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Stereo Matching with Nonlinear DiffusionInternational Journal of Computer Vision, 1998
- Active ContoursPublished by Springer Nature ,1998
- Prior learning and Gibbs reaction-diffusionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Pattern theory: A unifying perspectivePublished by Cambridge University Press (CUP) ,1996
- Emergence of simple-cell receptive field properties by learning a sparse code for natural imagesNature, 1996
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995
- A theory for multiresolution signal decomposition: the wavelet representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Signal matching through scale spaceInternational Journal of Computer Vision, 1987
- Receptive fields and functional architecture of monkey striate cortexThe Journal of Physiology, 1968