This paper describes a novel application of Statistical Learning Theory (SLT) to control model complexity inflow estimation. SLT provides analytical generalization bounds suitable for practical model selection from small and noisy data sets of image measurements (normalflow). The method addresses the aperture problem by using the penalized risk (ridge regression). We demonstrate an application of this method on both synthetic and real image sequences and use it for motion interpolation and extrapolation. Our experi- mental results show that our approach compares favorably against alternative model selection methods such as the Akaike 's final prediction error, Schwartz's criterion, Gen- eralized cross-validation, and Shibata 's model selector.
|Original language||English (US)|
|Number of pages||7|
|Journal||Proceedings of the IEEE International Conference on Computer Vision|
|State||Published - 2003|
|Event||NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION - Nice, France|
Duration: Oct 13 2003 → Oct 16 2003