Probabilistic motion estimation based on temporal coherence Journal Article

Authors: Burgi, P. Y.; Yuille, A. L.; Grzywacz, N. M.
Article Title: Probabilistic motion estimation based on temporal coherence
Abstract: We develop a theory for the temporal integration of visual motion motivated by psychophysical experiments. The theory proposes that input data are temporally grouped and used to predict and estimate the motion flows in the image sequence. This temporal grouping can be considered a generalization of the data association techniques that engineers use to study motion sequences. Our temporal grouping theory is expressed in terms of the Bayesian generalization of standard Kalman filtering. To implement the theory, we derive a parallel network that shares some properties of cortical networks. Computer simulations of this network demonstrate that our theory qualitatively accounts for psychophysical experiments on motion occlusion and motion outliers. In deriving our theory, we assumed spatial factorizability of the probability distributions and made the approximation of updating the marginal distributions of velocity at each point. This allowed us to perform local computations and simplified our implementation. We argue that these approximations are suitable for the stimuli we are considering (for which spatial coherence effects are negligible).
Journal Title: Neural computation
Volume: 12
Issue: 8
ISSN: 0899-7667
Publisher: Unknown  
Journal Place: United States
Date Published: 2000
Start Page: 1839
End Page: 1867
Language: eng
Notes: J2: Neural Comput