Comparison of Vector Stacking, Multi-SVMs Fuzzy Output, and Multi-SVMs Voting Methods for Multiscale VHR Urban Mapping

Abstract

The objective of this letter is to integrate multiscale information for urban mapping using very high resolution (VHR) imagery. Three multiscale fusion methods were presented: 1) vector stacking (VS); 2) multiple support vector machines (multi-SVMs) fuzzy output; and 3) multi-SVMs voting. Two kinds of spatial features were used to obtain multiscale representations of VHR images: morphological structural features and object-based approaches. In experiments, the Reflective Optics System Imaging Spectrometer-03 Pavia Center and University, the Hyperspectral Digital Imagery Collection Experiment Washington DC Mall, and the Quickbird Beijing data sets were used for algorithm validation. The experimental results revealed that, in most cases, the VS fusion outperformed other methods because it was able to create a new high-dimensional multiscale feature space and enhance the class separability. It was also shown that the multi-SVMs fuzzy fusion could optimize and reorganize the multiscale information effectively. Furthermore, multi-SVMs fuzzy output was better than multi-SVMs voting because the former was able to exploit the probabilistic output, while the latter only considered the crisp classification label. In addition, it is suggested that VS fusion is suitable for morphological features; however, for the object-based classification, the multiscale fusion methods do not necessarily yield better results than the single-scale classification in terms of accuracies.