DMCA
Probabilistic and Sequential Computation of Optical Flow Using Temporal Coherence (1994)
Cached
Download Links
- [ssg.mit.edu]
- [ssg.mit.edu]
- [ssg.mit.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | IEEE Transactions on Image Processing |
| Citations: | 19 - 3 self |
BibTeX
@ARTICLE{Chin94probabilisticand,
author = {Toshio M. Chin and Student Member and William C. Karl and Alan S. Willsky},
title = {Probabilistic and Sequential Computation of Optical Flow Using Temporal Coherence},
journal = {IEEE Transactions on Image Processing},
year = {1994},
pages = {3--6}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstruct- In the computation of dense optical flow fields, spatial coherence constraints are commonly used to regularize otherwise ill-posed problem formulations, providing spatial integration of data. In this paper, we present a temporal, multiframe extension of the dense optical flow estimation formulation proposed by Horn and Schunck [l] in which we use a temporal coherence constraint to yield the optimal fusing of data from multiple frames of measurements. Conceptually, at least, standard Kalman filtering algorithms are applicable to the resulting multiframe optical flow estimation problem, providing a solution that is sequential and recursive in time. Experiments are presented to demonstrate that the resulting multiframe estimates are more robust to noise than those provided by the original, singleframe formulation. In addition, we demonstrate cases where the aperture problem of motion vision cannot be resolved satisfactorily without the temporal integration of data enabled by the proposed formulation. Practically, the large matrix dimensions involved in the problem prohibit exact implementation of the optimal Kalman filter. To overcome this limitation, we present a computationally efficient, yet near optimal approximation of the exact filtering algorithm. This approximation has a precise interpretation as the sequential estimation of a reduced-order spatial model for the optical flow estimation error process at each time step and arises from an estimation-theoretic treatment of the filtering problem. Experiments also demonstrate the efficacy of this near optimal filter. I.
Keyphrases
optical flow using temporal coherence sequential computation estimation-theoretic treatment filtering problem spatial integration large matrix dimension optimal approximation reduced-order spatial model dense optical flow estimation formulation standard kalman filtering algorithm temporal integration time step motion vision cannot singleframe formulation dense optical flow field multiframe estimate problem prohibit exact implementation multiple frame ill-posed problem formulation multiframe extension spatial coherence constraint optimal fusing aperture problem multiframe optical flow estimation problem optimal kalman filter near optimal filter optical flow estimation error process exact filtering algorithm temporal coherence constraint sequential estimation precise interpretation
