Results 1 
3 of
3
Statistical Biases in Optic Flow
 In Conference on Computer Vision and Pattern Recognition
, 1999
"... The computation of optical flow from image derivatives is biased in regions of non uniform gradient distributions. A leastsquares or total least squares approach to computing optic flow from image derivatives even in regions of consistent flow can lead to a systematic bias dependent upon the direct ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
(Show Context)
The computation of optical flow from image derivatives is biased in regions of non uniform gradient distributions. A leastsquares or total least squares approach to computing optic flow from image derivatives even in regions of consistent flow can lead to a systematic bias dependent upon the direction of the optic flow, the distribution of the gradient directions, and the distribution of the image noise. The bias a consistent underestimation of length and a directional error. Similar results hold for various methods of computing optical flow in the spatiotemporal frequency domain. The predicted bias in the optical flow is consistent with psychophysical evidence of human judgment of the velocity of moving plaids, and provides an explanation of the Ouchi illusion. Correction of the bias requires accurate estimates of the noise distribution; the failure of the human visual system to make these corrections illustrates both the difficulty of the task and the feasibility of using this disto...
PixelwiseAdaptive Blind Optical Flow Assuming Nonstationary Statistics
"... 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 performa ..."
Abstract
 Add to MetaCart
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 secondorder constraints with a new secondorder 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 signaltonoise ratio for real sequences when the ground truth is unknown. Index Terms—Blind estimation, generalized cross validation (GCV), motion estimation, nonstationary statistic, optical flow. I.
MediaMath: A Research Environment for Computer Vision
"... This paper describes MediaMath an object oriented environment for computer vision. MediaMath is an interactive, extendible interpreter for algorithm development and rapid prototyping. It contains a wide variety of vision algorithms and a comprehensive set of fundamental image operations. It provides ..."
Abstract
 Add to MetaCart
(Show Context)
This paper describes MediaMath an object oriented environment for computer vision. MediaMath is an interactive, extendible interpreter for algorithm development and rapid prototyping. It contains a wide variety of vision algorithms and a comprehensive set of fundamental image operations. It provides a syntax idealy suited for translating mathematics to working programs that run efficiently. Examples of algorithms developed in MediaMath and samples of results are included. The support of the NSERC (App. No. OGP0046645) is gratefully acknowledged. 1.