Cluster Kernel For Learning Similarities Between Symmetric Positive Definite Matrix Time Series
Résumé
The launch of the last generation of Earth observation satellites has yield to a great improvement in the capabilities of acquiring Earth surface images, providing series of multitem-poral images. To process these time series images, many machine learning algorithms have been proposed in the literature such as warping based methods and recurrent neu-ral networks (LSTM,. . .). Recently, based on an ensemble learning approach, the time series cluster kernel (TCK) has been proposed and has shown competitive results compared to the state-of-the-art. Unfortunately, it does not model the spectral/spatial dependencies. To overcome this problem, this paper aims at extending the TCK approach by modeling the time series of second-order statistical features (SO-TCK). Experimental results are conducted on different benchmark datasets, and land cover classification with remote sensing satellite time series over the Reunion Island.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...