Paper
19 May 1999 Probabilistic multichannel optical flow analysis based on a multipurpose visual representation of image sequences
Oscar Nestares, Rafael Fonolla Navarro
Author Affiliations +
Proceedings Volume 3644, Human Vision and Electronic Imaging IV; (1999) https://doi.org/10.1117/12.348479
Event: Electronic Imaging '99, 1999, San Jose, CA, United States
Abstract
Directional filters are not normally used as pre-filters for optical flow estimation because orientation selectivity tends to increase the aperture problem. Despite this fact, here we apply a subband decomposition using directional spatio-temporal filters at different resolution to discriminate multiple motions at the same location. We first obtain multiple estimates of the velocity by applying the classic gradient constraint to the output of each filter. Spatio-temporal gradients of GD2 channel response are easily obtained as linear combinations of the set of 10 separable GD3 channel responses, which constitutes a multipurpose scheme for visual representation of image sequences. Then, we obtain an overdetermined linear system by imposing local constant velocity. This system is solved by least-squares yielding an estimate of the velocity and its covariance matrix. After segmenting the resulting 6 X 3 velocity estimates we combine them using Bayesian probability rules. Segmentation maintains the ability to represent multiple motions, while the combination of estimates reduces the aperture problem. Results for synthetic and real sequences are highly satisfactory. Mean errors in complex standard sequences are below those provided by most published methods.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Oscar Nestares and Rafael Fonolla Navarro "Probabilistic multichannel optical flow analysis based on a multipurpose visual representation of image sequences", Proc. SPIE 3644, Human Vision and Electronic Imaging IV, (19 May 1999); https://doi.org/10.1117/12.348479
Lens.org Logo
CITATIONS
Cited by 5 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Optical flow

Visualization

Linear filtering

Motion estimation

Motion models

Error analysis

Image visualization

Back to Top