Uncertainty Analysis for the Classification of Multispectral Satellite Images Using SVMs and SOMs

Abstract

Abstract-Classification of multispectral remotely sensed data with textural features is investigated with a special focus on uncertainty analysis in the produced land-cover maps. Much effort has already been directed into the research of satisfactory accuracyassessment techniques in image classification, but a common approach is not yet universally adopted. We look at the relationship between hard accuracy and the uncertainty on the produced answers, introducing two measures based on maximum probability and α quadratic entropy. Their impact differs depending on the type of classifier. In this paper, we deal with two different classification strategies, based on support vector machines (SVMs) and Kohonen's self-organizing maps (SOMs), both suitably modified to give soft answers. Once the multiclass probability answer vector is available for each pixel in the image, we studied the behavior of the overall classification accuracy as a function of the uncertainty associated with each vector, given a hard-labeled test set. The experimental results show that the SVM with one-versus-one architecture and linear kernel clearly outperforms the other supervised approaches in terms of overall accuracy. On the other hand, our analysis reveals that the proposed SOM-based classifier, despite its unsupervised learning procedure, is able to provide soft answers which are the best candidates for a fusion with supervised results.

Mapping Cropland Abandonment in the Aral Sea Basin with MODIS Time Series

“…The fusion considers the probabilistic a-posteriori values estimating class membership at the pixel level by the RF [94] and the SVM [95]. Depending on the algorithm, the way these ''softened'' Because of the agro-ecological gradients and the variety of management practices in the ASB, spectral signatures varied spatially and could lower the recognition ability by a single global classifier.…”

“…The fusion considers the probabilistic a-posteriori values estimating class membership at the pixel level by the RF [94] and the SVM [95]. Depending on the algorithm, the way these "softened" outputs are calculated differ from each other: in the RF framework, it is defined as the number of trees in the RF ensemble voting for the final class [94], in SVM classification, it is based on the distances of the samples to the OSH in the feature space [95,96].…”

VPRS-Based Regional Decision Fusion of CNN and MRF Classifications for Very Fine Resolution Remotely Sensed Images

“…Information on uncertainty is also very useful for classification map users, because if it is available, at least in some generalised form, users can better target their attention and effort. Currently, classification model uncertainty is assessed mainly using measures such as the difference between the first and second largest class membership value [26], Shannon's entropy [27], α-quadratic entropy [28], and so on, but there is generally a lack of objective and automatic approaches to partition and label the correct and incorrect classification regions.…”

An information-based criterion to measure pixel-level thematic uncertainty in land cover classifications

“…In the random forest framework it is defined as the number of trees in the ensemble voting for the final class (Loosvelt et al 2012a). In support vector machine classifications it is based on the distances of the samples to the optimal separating hyperplane in the feature space (Giacco et al 2010), while for the multi-layer perceptron it is based on the activation levels (Brown et al 2009). If these measures are not posterior probabilities per se, they can be regarded as such.…”

“…Waldner et al (2015a) showed that correctly classified pixels tend to display a lower uncertainty NUC than misclassified pixels. Studies such as those by Giacco et al (2010) and Löw et al (2013), (2015b) relied on the a-quadratic entropy H a ðpÞ. This measure is based on the concept of the multiplicative class introduced by Pal and Bezdek (1994), with…”