Robust dynamic motion estimation over time
- 10 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper presents a novel approach to incrementally estimating visual motion over a sequence of images. We start by formulating constraints on image motion to account for the possibility of multiple motions. This is achieved by exploiting the notions of weak continuity and robust statistics in the formulation of a minimization problem. The resulting objective function is non--convex. Traditional stochastic relaxation techniques for minimizing such functions prove inappropriate for the task....Keywords
This publication has 7 references indexed in Scilit:
- Temporally integrated surface reconstructionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A model for the detection of motion over timePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Kalman filter-based algorithms for estimating depth from image sequencesInternational Journal of Computer Vision, 1989
- A computational framework and an algorithm for the measurement of visual motionInternational Journal of Computer Vision, 1989
- Visual ReconstructionPublished by MIT Press ,1987
- A Monte carlo simulated annealing approach to optimization over continuous variablesJournal of Computational Physics, 1984
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984