Preserving accurate motion contours with reliable parameter selection

The use of decreasing functions, for mitigating the regularization at image contours, is typical in many recent optical flow methods. However, finding the correct parameter for getting the best of this strategy is challenging. Most of the methods use default parameters that are conservative, providi...

Full description

Saved in:
Bibliographic Details
Published in2014 IEEE International Conference on Image Processing (ICIP) pp. 209 - 213
Main Authors Sanchez, Javier, Salgado, Agustin, Monzon, Nelson
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2014
Subjects
Adaptive optics
Computer vision
Discontinuity-Preserving
Estimation
Image Motion Analysis
Integrated optics
Motion Estimation
Nonlinear optics
Optical Flow
Optical imaging
Online AccessGet full text

Cover

More Information
Summary:The use of decreasing functions, for mitigating the regularization at image contours, is typical in many recent optical flow methods. However, finding the correct parameter for getting the best of this strategy is challenging. Most of the methods use default parameters that are conservative, providing results that are not better than traditional approaches. Configurations that clearly enhance discontinuities may produce instabilities in the computed optical flows. This is due to the fact that the regularization process may get cancelled, yielding an ill-posed problem. In this work, we analyze the problem of instabilities and propose a method for efficiently determining the value of the parameter. We show that this approach allows us to obtain well preserved discontinuities at the same time that it avoids the ill-posed problem. The experiments with synthetic sequences demonstrate that the results are accurate and the selected parameter is close to the optimal value.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2014.7025041