%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi@80/2009/08.17.15.47
%2 sid.inpe.br/sibgrapi@80/2009/08.17.15.47.33
%@doi 10.1109/SIBGRAPI.2009.20
%T Support Vectors Learning for Vector Field Reconstruction
%D 2009
%A Lage, Marcos,
%A Castro, Rener,
%A Petronetto, Fabiano,
%A Bordignon, Alex,
%A Tavares, Geovan,
%A Lewiner, Thomas,
%A Lopes, Hélio,
%@affiliation Matmídia Laboratory – Department of Mathematics, PUC–Rio – Rio de Janeiro, Brazil
%@affiliation .
%@affiliation Matmídia Laboratory – Department of Mathematics, PUC–Rio – Rio de Janeiro, Brazil
%@affiliation Matmídia Laboratory – Department of Mathematics, PUC–Rio – Rio de Janeiro, Brazil
%@affiliation Matmídia Laboratory – Department of Mathematics, PUC–Rio – Rio de Janeiro, Brazil
%@affiliation Matmídia Laboratory – Department of Mathematics, PUC–Rio – Rio de Janeiro, Brazil
%@affiliation Matmídia Laboratory – Department of Mathematics, PUC–Rio – Rio de Janeiro, Brazil
%E Nonato, Luis Gustavo,
%E Scharcanski, Jacob,
%B Brazilian Symposium on Computer Graphics and Image Processing, 22 (SIBGRAPI)
%C Rio de Janeiro, RJ, Brazil
%8 11-14 Oct. 2009
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K Vector Field, Support Vector Machine.
%X Sampled vector fields generally appear as measurements of real phenomena. They can be obtained by the use of a Particle Image Velocimetry acquisition device, or as the result of a physical simulation, such as a fluid flow simulation, among many examples. This paper proposes to formulate the unstructured vector field reconstruction and approximation through Machine-Learning. The machine learns from the samples a global vector field estimation function that could be evaluated at arbitrary points from the whole domain. Using an adaptation of the Support Vector Regression method for multi-scale analysis, the proposed method provides a global, analytical expression for the reconstructed vector field through an efficient non-linear optimization. Experiments on artificial and real data show a statistically robust behavior of the proposed technique.
%@language en
%3 57787_2.pdf