Title
Pixelwise-Adaptive Blind Optical Flow Assuming Nonstationary Statistics
Keywords
Blind estimation; Generalized cross validation (GCV); Motion estimation; Nonstationary statistic; Optical flow
Abstract
In this paper, we address some of the major issues in optical flow within a new framework assuming nonstationary statistics for the motion field and for the errors. Problems addressed include the preservation of discontinuities, model/data errors, outliers, confidence measures, and performance evaluation. In solving these problems, we assume that the statistics of the motion field and the errors are not only spatially varying, but also unknown. We, thus, derive a blind adaptive technique based on generalized cross validation for estimating an independent regularization parameter for each pixel. Our formulation is pixelwise and combines existing first- and second-order constraints with a new second-order temporal constraint. We derive a new confidence measure for an adaptive rejection of erroneous and outlying motion vectors, and compare our results to other techniques in the literature. A new performance measure is also derived for estimating the signal-to-noise ratio for real sequences when the ground truth is unknown. © 2005 IEEE.
Publication Date
2-1-2005
Publication Title
IEEE Transactions on Image Processing
Volume
14
Issue
2
Number of Pages
222-230
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/TIP.2004.840685
Copyright Status
Unknown
Socpus ID
13244278022 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/13244278022
STARS Citation
Foroosh, Hassan, "Pixelwise-Adaptive Blind Optical Flow Assuming Nonstationary Statistics" (2005). Scopus Export 2000s. 4135.
https://stars.library.ucf.edu/scopus2000/4135