Support Vector Regression with Kernel Combination for Missing Data Reconstruction - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Geoscience and Remote Sensing Letters Année : 2013

Support Vector Regression with Kernel Combination for Missing Data Reconstruction

Résumé

Over the past few years, the reconstruction of missing data due to the presence of clouds received an important attention. Applying region-based inpainting strategies or conventional regression methods, such as support vector machine (SVM) regression, may not be the optimal way. In this letter, we propose new combinations of kernel functions with which we obtain a better reconstruction. In particular in the regression, we add to the radiometric information, the position information of the pixels in the image. For each kind of information adopted in the regression, a specific kernel is selected and adapted. Adopting this new kernel combination in a support vector regression (SVR), comes out that only few support vectors (SVs) are needed to reconstruct a missing area. This means that we also perform a compression in the number of values needed for a good reconstruction. We illustrate the proposed approaches through some simulations.
Fichier non déposé

Dates et versions

hal-01058020 , version 1 (25-08-2014)

Identifiants

Citer

Luca Lorenzi, Grégoire Mercier, Farid Melgani. Support Vector Regression with Kernel Combination for Missing Data Reconstruction. IEEE Geoscience and Remote Sensing Letters, 2013, 10 (2), pp.367-371. ⟨10.1109/LGRS.2012.2206070⟩. ⟨hal-01058020⟩
55 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More