Ensemble of extreme learning machine for remote sensing image classification

There are only a few of labeled training samples in the remote sensing image classification. Therefore, it is a highly challenging problem that finds a good classification method which could achieve high accuracy to deal with these data. In this paper, we propose a new remote sensing image classification method based on extreme learning machine (ELM) ensemble. In order to promote the diversity within the ensemble, we adopt feature segmentation and then feature extraction with nonnegative matrix factorization (NMF) to the original data firstly. Then ELM is chosen as base classifier to improve the classification efficiency. The experimental results show that the proposed algorithm not only has high classification accuracy, but also handles the adverse impact of a few of labeled training samples in the classification of remote sensing image well both on the remote sensing image and UCI data.