Land-use classification from multiple data sources is an important problem in remote sensing. Data fusion algorithms like Semi-Supervised Manifold Alignment (SSMA) and Manifold Alignment with Schroedinger Eigenmaps (SEMA) use spectral and/or spatial features from multispectral, multimodal imagery to project each data source into a common latent space in which classification can be performed. However, in order for these algorithms to be well-posed, they require an expert user to either directly identify pairwise dissimilarities in the data or to identify class labels for a subset of points from which pairwise dissimilarities can be derived. In this paper, we propose a related data fusion technique, which we refer to as Semi-Supervised Normalized Embeddings (SSNE). SSNE is defined by modifying the SSMA/SEMA objective functions to incorporate an extra normalization term that enables a latent space to be well-defined even when no pairwise-dissimilarities are provided. Using publicly available data from the 2017 IEEE GRSS Data Fusion Contest, we show that SSNE enables similar land-use classification performance to SSMA/SEMA in scenarios where pairwise dissimilarities are available, but that unlike SSMA/SEMA, it also enables land-use classification in other scenarios. We compare the effect of applying different classification algorithms including a support vector machine (SVM), a linear discriminant analysis classifier (LDA), and a random forest classifier (RF); we show that SSMA/SEMA and SSNE robust to the use of different classifiers. In addition to comparing the classification performance of SSNE to SSMA/SEMA and comparing classification algorithm, we utilize manifold alignment to classify unknown views.
Computer Science (MS)
Department, Program, or Center
Computer Science (GCCIS)
Immel, Poppy, "Semi-Supervised Normalized Embeddings for Fusion and Land-Use Classification of Multiple View Data" (2018). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus