Multi-objective optimization for parameter selection and characterization of optical flow methods

Jose Delpiano, Luis Pizarro, Rodrigo Verschae, Javier Ruiz-del-Solar

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Optical flow methods are among the most accurate techniques for estimating displacement and velocity fields in a number of applications that range from neuroscience to robotics. The performance of any optical flow method will naturally depend on the configuration of its parameters, and for different applications there are different trade-offs between the corresponding evaluation criteria (e.g. the accuracy and the processing speed of the estimated optical flow). Beyond the standard practice of manual selection of parameters for a specific application, in this article we propose a framework for automatic parameter setting that allows searching for an approximated Pareto-optimal set of configurations in the whole parameter space. This final Pareto-front characterizes each specific method, enabling proper method comparison and proper parameter selection. Using the proposed methodology and two open benchmark databases, we study two recent variational optical flow methods. The obtained results clearly indicate that the method to be selected is application dependent, that in general method comparison and parameter selection should not be done using a single evaluation measure, and that the proposed approach allows to successfully perform the desired method comparison and parameter selection.

Original languageEnglish
Pages (from-to)1067-1078
Number of pages12
JournalApplied Soft Computing Journal
Volume46
DOIs
StatePublished - 1 Sep 2016

Bibliographical note

Funding Information:
This research was partially funded by Universidad de los Andes FAI grant #05/2013 , and the FONDECYT Projects 1130153 and 3120218 (CONICYT, Chile).

Publisher Copyright:
© 2016 Elsevier B.V.

Keywords

  • Multi-objective optimization
  • Optical flow
  • Parameter selection

Fingerprint

Dive into the research topics of 'Multi-objective optimization for parameter selection and characterization of optical flow methods'. Together they form a unique fingerprint.

Cite this