Statistical models of visual shape and motion
- 15 May 1998
- journal article
- Published by The Royal Society in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 356 (1740) , 1283-1302
- https://doi.org/10.1098/rsta.1998.0222
Abstract
The analysis of visual motion against dense background clutter is a challenging problem. Uncertainty in the positions of visually sensed features and ambiguity of feature correspondence call for a probabilistic treatment, capable of maintaining not simply a single estimate of position and shape but an entire distribution. Exact representation of the evolving distribution is possible when the distributions are Gaussian and this yields some powerful approaches. However, normal distributions are limited when clutter is present: because of their unimodality, they cannot be used to represent simultaneous alternative hypotheses.Keywords
This publication has 36 references indexed in Scilit:
- Pattern theory: A unifying perspectivePublished by Cambridge University Press (CUP) ,1996
- Learning to track the visual motion of contoursArtificial Intelligence, 1995
- Learning flexible models from image sequencesPublished by Springer Nature ,1994
- Robust multiple car tracking with occlusion reasoningPublished by Springer Nature ,1994
- A Bayesian approach to dynamic contours through stochastic sampling and simulated annealingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Techniques for online gesture recognition on workstationsImage and Vision Computing, 1993
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992
- Affine structure from motionJournal of the Optical Society of America A, 1991
- Recognition by linear combinations of modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Finding spiral structures in images of galaxiesPhilosophical Transactions A, 1990