Multi-objective optimization for characterization of optical flow methods

José Delpiano, Luis Pizarro, Rodrigo Verschae, Javier Ruiz-Del-Solar

Resultado de la investigación: Contribución a una conferenciaArtículo

4 Citas (Scopus)

Resumen

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. Beyond the standard practice of manual (ad-hoc) 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. We define two performance criteria, namely the accuracy and speed of the optical flow methods. Copyright
Idioma originalInglés estadounidense
Páginas566-573
Número de páginas8
DOI
EstadoPublicada - 1 ene 2014
EventoVISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications -
Duración: 1 ene 2014 → …

Conferencia

ConferenciaVISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications
Período1/01/14 → …

Palabras clave

  • Multi-objective Optimization
  • Optical Flow

Huella Profundice en los temas de investigación de 'Multi-objective optimization for characterization of optical flow methods'. En conjunto forman una huella única.

Citar esto