Machine Learning Methods for Land Cover Classification from Multi-Spectral Images

Abstract

Remote sensing data has played vital role in land use/land-cover applications. Many machine learning methods have been proposed to obtain different land cover classes. In this paper, we investigated the capabilities of two classifiers with object-based segmentation for land cover classification from high resolution multi-spectral images. First, graph-based minimal spanning tree segmentation was applied to segment the original image pixels into objects. From each object a set of spectral, spatial and texture features were extracted. These features were then used to train and test the artificial neural network (ANN) and support vector machine (SVM). The proposed method was evaluated on a dataset consisting of high resolution multi-spectral images with four classes (tea area, other trees, roads and builds, bare land). The experiments showed that ANN was more accuracy as it scored average accuracy of 82.60% while SVM produced 73.66%. Moreover, when postprocessing using majority analysis was applied, the average accuracy improved to 86.18%.