Statistical Foreground Modelling for Object Localisation

A Bayesian approach to object localisation is feasible given suitable likelihood models for image observations. Such a likelihood involves statistical modelling--and learning--both of the object foreground and of the scene background. Statistical background models are already quite well understood. Here we propose a "conditioned likelihood" model for the foreground, conditioned on variations both in object appearance and illumination. Its effectiveness in localising a variety of objects is demonstrated.

[1]  J. Hammersley,et al.  Monte Carlo Methods , 1965 .

[2]  Peter J. Burt,et al.  Fast algorithms for estimating local image properties , 1982, Comput. Graph. Image Process..

[3]  Peter J. Burt,et al.  Fast algorithms for estimating local image properties , 1982, Comput. Graph. Image Process..

[4]  B. Barsky,et al.  An Introduction to Splines for Use in Computer Graphics and Geometric Modeling , 1987 .

[5]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[6]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Ulf Grenander,et al.  Hands: A Pattern Theoretic Study of Biological Shapes , 1990 .

[8]  Pietro Perona.  Steerable-scalable kernels for edge detection and junction analysis , 1992, Image Vis. Comput..

[9]  D. Mackay,et al.  Bayesian methods for adaptive models , 1992 .

[10]  Paul A. Viola.  Alignment by maximisation of mutual information , 1993 .

[11]  William T. Freeman,et al.  The generic viewpoint assumption in a framework for visual perception , 1994, Nature.

[12]  Timothy F. Cootes,et al.  A unified approach to coding and interpreting face images , 1995, Proceedings of IEEE International Conference on Computer Vision.

[13]  Rachid Deriche,et al.  Region tracking through image sequences , 1995, Proceedings of IEEE International Conference on Computer Vision.

[14]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[15]  Donald Geman,et al.  An Active Testing Model for Tracking Roads in Satellite Images , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  R. Baddeley,et al.  Searching for filters with 'interesting' output distributions: an uninteresting direction to explore? , 1996, Network.

[17]  D. Mumford.  Perception as Bayesian Inference: Pattern theory: A unifying perspective , 1996 .

[18]  Andrew Blake,et al.  Statistical mosaics for tracking , 1996, Image Vis. Comput..

[19]  Terrence J. Sejnowski,et al.  Edges are the Independent Components of Natural Scenes , 1996, NIPS.

[20]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[21]  D. Mumford.  Pattern theory: a unifying perspective , 1996 .

[22]  Gregory D. Hager,et al.  X Vision: Combining Image Warping and Geometric Constraints for Fast Visual Tracking , 1996, ECCV.

[23]  Joshua B. Tenenbaum,et al.  Learning bilinear models for two-factor problems in vision , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[24]  Song-Chun Zhu,et al.  Prior Learning and Gibbs Reaction-Diffusion , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[26]  Andrew Blake,et al.  Separability of pose and expression in facial tracking and animation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[27]  Eero P. Simoncelli,et al.  Modeling Surround Suppression in V1 Neurons with a Statistically Derived Normalization Model , 1998, NIPS.

[28]  Michael Isard,et al.  Active Contours , 2000, Springer London.

[29]  Song-Chun Zhu,et al.  GRADE: Gibbs reaction and diffusion equations , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[30]  Michael Isard,et al.  Object localization by Bayesian correlation , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.