Reducing "Structure From Motion": a General Framework for Dynamic Vision - Part 1: Modeling

Soatto, Stefano and Perona, Pietro (1996) Reducing "Structure From Motion": a General Framework for Dynamic Vision - Part 1: Modeling. Technical Report. California Institute of Technology, Pasadena, CA. [CaltechCDSTR:1996.001]

Full text available as:

	PDF - Requires Adobe Acrobat Reader or other PDF viewer.
	Postscript - Requires a viewer, such as GhostView

Abstract

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of different models and estimation techniques. We propose a framework that allows us to derive and compare all models by following the idea of dynamical system reduction. The "natural" dynamic model, derived by the rigidity constraint and the perspective projection, is first reduced by explicitly decoupling structure (depth) from motion. Then implicit decoupling techniques are explored, which consist of imposing that some function of the unknown parameters is held constant. By appropriately choosing such a function, not only can we account for all models seen so far in the literature, but we can also derive novel ones.

EPrint Type:	Monograph (Technical Report)
Uncontrolled Keywords:	Visual motion estimation, epipolar geometry, motion decoupling, compensation, fixation, parallax, output stabilization, model reduction
Subjects:	All Records
ID Code:	136
Deposited By:	Caltech Library System
Deposited On:	20 October 2006
Unique Identifier:	CaltechCDSTR:1996.001
Official Persistent URL:	http://resolver.caltech.edu/CaltechCDSTR:1996.001
Usage Policy:	You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.

Archive Staff Only: edit this record