Statistical Models of Visual Shape and Motion
Sequential Monte Carlo Methods in Practice
This paper addresses some problems in the interpretation of visually observed shapes, both planar and three-dimensional, in motion. Mumford (1996), interpreting the Pattern Theory developed over a number of years by Grenander (1976), views images as pure patterns that have been distorted by a combination of four kinds of degradations. This view applies naturally to the analysis of static, two-dimensional images. The four degradations are given here, together with comments on how they need to be extended to take account of three-dimensional objects in motion.
Blake, Andrew, Michael Isard, and John MacCormick. "Statistical Models of Visual Shape and Motion." In Sequential Monte Carlo Methods in Practice, edited by Arnaud Doucet, Nando de Freitas, and Neil Gordon, 339-357. New York: Springer, 2001.