Hyperspectral Signal Subspace Identification Research Articles

Unmixing of hyperspectral data for mineral detection using a hybrid method, Sar Chah-e Shur, Iran

This study aims to detect indicative minerals by spectral unmixing of the Hyperion and HyMap datasets in the Sar Chah-e Shur area. The mineral endmembers and their abundances were therefore determined using a series of hyperspectral processing algorithms. The virtual dimensionality methods including principal component analysis (PCA), minimum noise fraction (MNF), singular valued decomposition (SVD), Harsanyi-Farrand-Chang (HFC)/ (NWHFC), and Hyperspectral signal subspace identification by minimum error (HySime) were applied to estimate the number of endmembers. Five pure pixel-based methods including pixel purity index (PPI), sequential maximum angle convex cone (SMACC), simplex growing algorithm (SGA), N-FINDR, and vertex component analysis (VCA) were then applied for extracting the spectra of endmembers. Clay, serpentine, mica, and zeolite group minerals were identified which are consistent with the geological investigations in the region. The detected minerals were then mapped by the fully constrained least square (FCLS) method. The functionality of the methods and their performances on HyMap and Hyperion data were surveyed by several criteria including the number of recognized endmembers, the matching score of extracted endmembers with the reference spectrum, the agreement of the estimated abundances maps with the relevant lithological units on the geological map, and the average reconstruction error (ARE). Two hybrid maps were generated by combining individual methods that were found highly consistent with the geological map. The XRD analysis of three chips rock samples of two indicative lithological units was used to additionally check the efficiency of the applied methods.

Spectral-spatial Classification of Hyperspectral Images Using Signal Subspace Identification and Edge-preserving Filter

Hyperspectral images in remote sensing include hundreds of spectral bands that provide valuable information for accurately identify objects. In this paper, a new method of classifying hyperspectral images using spectral spatial information has been presented. Here, using the hyperspectral signal subspace identification (HYSIME) method which estimates the signal and noise correlation matrix and selects a subset of eigenvalues for the best representation of the signal subspace in order to minimize the mean square error, subsets from the main sample space have been extracted. After subspace extraction with the help of the HYSIME method, the edge-preserving filtering (EPF), and classification of the hyperspectral subspace using a support vector machine (SVM), results were then merged into the decision-making level using majority rule to create the spectral-spatial classifier. The simulation results showed that the spectral-spatial classifier presented leads to significant improvement in the accuracy and validity of the classification of Indiana, Pavia and Salinas hyperspectral images, such that it can classify these images with 98.79%, 98.88% and 97.31% accuracy, respectively.

Improving Signal Subspace Identification Using Weighted Graph Structure of Data

Signal subspace identification (SSI) is known as an important preprocessing for most remote sensing processes and its applications. Hence, a graph-based method is presented in this letter to improve identification of signal subspace and its dimension. Our proposed method reduces sensitivity to noise through integrating a weighted graph of image pixels in the cost function of the well-known hyperspectral SSI by minimum error (HySime) method to improve the accuracy of SSI. The method proposed in this letter is a very simple and yet very effective in estimating various types of hyperspectral data. The proposed method was implemented on various synthetic and real data. The results of the experiments on both types of hyperspectral data indicated the accuracy of this approach in estimating the signal subspace as compared with other well-known methods.

GPU-Based Parallel Design of the Hyperspectral Signal Subspace Identification by Minimum Error (HySime)

Signal subspace identification provides a performance improvement in hyperspectral applications, such as target detection, spectral unmixing, and classification. The HySime method is a well-known unsupervised approach for hyperspectral signal subspace identification. It computes the estimated noise and signal correlation matrices from which a subset of eigenvectors is selected to best represent the signal subspace in the least square sense. Depending on the complexity and dimensionality of the hyperspectral scene, the HySime algorithm may be computationally expensive. In this paper, we propose a massively parallel design of the HySime method for acceleration on NVIDIA's graphics processing units (GPUs). Our pure GPU-based implementation includes the optimal use of the page-locked host memory, block size, and the number of registers per thread. The proposed implementation was validated in terms of accuracy and performance using the NASA AVIRIS hyperspectral data. The benchmark with the NVIDIA GeForce GTX 580 and Tesla K20 GPUs shows significant speedups with regards to the optimized CPU-based serial counterpart. This new fast implementation of the HySime method demonstrates good potential for real-time hyperspectral applications.

Unsupervised classification strategy utilizing an endmember extraction technique for airborne hyperspectral remotely sensed imagery

Remote sensing has become an important source of urban land-use/cover classification, and as a result of their high spatial and spectral resolution, airborne hyperspectral images have been widely used to distinguish different urban classes. However, the previous studies into the classification of urban environments have mainly focused on a supervised scenario, which is limited by the selection of training samples. An unsupervised classification strategy utilizing an endmember extraction technique for airborne hyperspectral imagery is proposed by a combination of endmember extraction and k-means classification. The number of endmembers of the hyperspectral image is first estimated with the hyperspectral signal subspace identification with the minimum error method, and then the simplex growing algorithm is used to extract the endmember spectra that represent the different latent materials in the hyperspectral imagery. These latent materials were further integrated into the predefined number of classes and the k-means classification method was utilized to obtain the final classification map. Different distance measures were experimentally used in the procedure of class integration and classification to investigate the impact of initial cluster centers and further clustering criterion. The proposed strategy was compared with three traditional unsupervised classification methods, k-means, fuzzy k-means, and ISODATA, with two airborne hyperspectral images. The experimental results demonstrate that the proposed approach is more robust and outperforms the other three classification methods, and, hence, provides an innovative perspective for implementing the unsupervised classification of airborne hyperspectral imagery.

Comparative Study of Intrinsic Dimensionality Estimation and Dimension Reduction Techniques on Hyperspectral Images Using K-NN Classifier

Nowadays, hyperspectral remote sensors are readily available for monitoring the Earth's surface with high spectral resolution. The high-dimensional nature of the data collected by such sensors not only increases computational complexity but also can degrade classification accuracy. To address this issue, dimensionality reduction (DR) has become an important aid to improving classifier efficiency on these images. The common approach to decreasing dimensionality is feature extraction by considering the intrinsic dimensionality (ID) of the data. A wide range of techniques for ID estimation (IDE) and DR for hyperspectral images have been presented in the literature. However, the most effective and optimum methods for IDE and DR have not been determined for hyperspectral sensors, and this causes ambiguity in selecting the appropriate techniques for processing hyperspectral images. In this letter, we discuss and compare ten IDE and six DR methods in order to investigate and compare their performance for the purpose of supervised hyperspectral image classification by using K-nearest neighbor (K-NN). Due to the nature of K-NN classifier that uses different distance metrics, a variety of distance metrics were used and compared in this procedure. This letter presents a review and comparative study of techniques used for IDE and DR and identifies the best methods for IDE and DR in the context of hyperspectral image analysis. The results clearly show the superiority of the hyperspectral signal subspace identification by minimum, second moment linear, and noise-whitened Harsanyi-Farrand-Chang estimators, also the principal component analysis and independent component analysis as DR techniques, and the norm L1 and Euclidean distance metrics to process hyperspectral imagery by using the K-NN classifier.

Linear Spectral Mixture Analysis Based Approaches to Estimation of Virtual Dimensionality in Hyperspectral Imagery

Virtual dimensionality (VD) is a new concept which was originally developed for estimating the number of spectrally distinct signatures present in hyperspectral data. The effectiveness of the VD is determined by the technique used for VD estimation. This paper develops an orthogonal subspace projection (OSP) technique to estimate the VD. The idea is derived from linear spectral mixture analysis where a data sample vector is modeled as a linear mixture of a finite set of what is called as virtual endmembers in this paper. A similar idea was also previously investigated by the signal subspace estimate (SSE) and was later improved by hyperspectral signal subspace identification by minimum error (HySime), where the minimum mean squared error is used as a criterion to determine the VD. Interestingly, with an appropriate interpretation, the proposed OSP technique includes the SSE/HySime as its special case. In order to demonstrate its utility, experiments using synthetic images and real image data sets are conducted for performance analysis.