Advanced Techniques for Unsupervised Classification of Remote Sensing Hyperspectral Images

Abstract

Hyperspectral images consisting of a broad range of contiguous spectral bands ought to be a valuable tool for land cover type mapping. However, the coarse spatial resolutions of remote sensing Hyperspectral images makes a detailed semantic interpretation and pixel-wise labeling complex. Indeed, the lack of labeled training data is a common problem that directly affects the application of supervised classification of land cover type mapping. Due to the specific conditions rooted in remote sensing hyperspectral imagery, remote sensing hyperspectral images are from high spectral dimensions covering large spatial extents. HSIs generally come with complex inter-variable non-linear dependencies. The lack of labeled data, the intrinsic high-dimensionality and the spectral non-linearity present in remote sensing hyperspectral images make any pursuant land cover type classification a challenging and uneasy task.

The primary objective of the present dissertation is to design and to implement new techniques for the classification of remote sensing hyperspectral images that can effectively perform land cover mapping. To achieve this objective, particular focus is placed on the integration of non-linear manifold learning with unsupervised classification. In this regard, this dissertation incorporates four main contributions, each achieving satisfactory results in terms of accuracy and precision of classification.

First, an outlier robust geodesic K-mean algorithm for unsupervised classification of hyperspectral imaging data is proposed. The proposed algorithm expands the standard K-means algorithm by an adaptive density-based geodesic distance that is robust to the presence of outliers and the data with varying cluster shapes. Second, a framework of multi-manifold spectral clustering based on a Weighted Principal Component Analysis is proposed. Unsupervised classification via multi-manifold learning has been an active area in several pattern recognition applications, but it has not been effectively employed in remote sensing hyperspectral image classification tasks. In this dissertation, multi-manifold spectral clustering is explored as applied in hyperspectral image classification. Third, a new variant of multi-manifold spectral clustering is proposed that exploits the Contractive Autoencoder for tangent estimation. The multi-manifold spectral clustering by the Contractive Autoencoder makes a multi-manifold-based clustering model that is more robust to local data variations and the presence of noisy data. Fourth, a bipartite-graph-based sequential spectral clustering algorithm is proposed for the unsupervised classification of large-scale remote sensing hyperspectral imaging data. The proposed sequential Spectral Clustering deals with the scalability limitations of the standard Spectral Clustering algorithm and extends its applicability to real-world large sample size hyperspectral images.

To validate the developed classification algorithms in this dissertation, several publicly available remote sensing hyperspectral images are leveraged, including hyperspectral images provided by the standard and widely used instruments such as NASA's Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) and the Reflective Optics Spectrographic Imaging System (ROSIS). The experiments on real-world hyperspectral images result in the conclusion that the proposed techniques can assist in land cover type mapping by remote sensing hyperspectral image classification.