Battiti, Roberto and Amaldi, Edoardo and Koch, Christof (1991) Computing optical flow across multiple scales: An adaptive coarse-to-fine strategy. International Journal of Computer Vision, 6 (2). pp. 133-145. ISSN 0920-5691. http://resolver.caltech.edu/CaltechAUTHORS:20130816-103133903
- Accepted Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20130816-103133903
Single-scale approaches to the determination of the optical flow field from the time-varying brightness pattern assume that spatio-temporal discretization is adequate for representing the patterns and motions in a scene. However, the choice of an appropriate spatial resolution is subject to conflicting, scene-dependent, constraints. In intensity-base methods for recovering optical flow, derivative estimation is more accurate for long wavelengths and slow velocities (with respect to the spatial and temporal discretization steps). On the contrary, short wavelengths and fast motions are required in order to reduce the errors caused by noise in the image acquisition and quantization process. Estimating motion across different spatial scales should ameliorate this problem. However, homogeneous multiscale approaches, such as the standard multigrid algorithm, do not improve this situation, because an optimal velocity estimate at a given spatial scale is likely to be corrupted at a finer scale. We propose an adaptive multiscale method, where the discretization scale is chosen locally according to an estimate of the relative error in the velocity estimation, based on image properties. Results for synthetic and video-acquired images show that our coarse-to-fine method, fully parallel at each scale, provides substantially better estimates of optical flow than do conventional algorithms, while adding little computational cost.
|Additional Information:||© 1991 Kluwer Academic Publishers. Received April 9, 1990. Revised October 15, 1990. This work was carried out while R. Battiti and E. Amaldi were in the laboratory of Prof. Geoffrey Fox at Caltech. We gratefully acknowledge his kind support. John Harris provided detailed comments, in particular for figure 1. G. Fox is partly funded by DOE grant DE-FG-03-85ER25009, NSF grant SIT-8700064 and by IBM. C. Koch is partly supported by the National Science Foundation, the Office of Naval Research, and the James S. McDonnell Foundation.|
|Group:||Koch Laboratory, KLAB|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||KLAB Import|
|Deposited On:||11 Jan 2008 03:46|
|Last Modified:||01 May 2015 19:30|
Repository Staff Only: item control page