Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging

Edge-preserving features (EPFs) obtained by the application of edge-preserving filters to hyperspectral images (HSIs) have been found very effective in characterizing significant spectral and spatial structures of objects in a scene. However, a direct use of the EPFs can be insufficient to provide a complete characterization of spatial information when objects of different scales are present in the considered images. Furthermore, the edge-preserving smoothing operation unavoidably decreases the spectral differences among objects of different classes, which may affect the following classification. To overcome these problems, in this paper, a novel principal component analysis (PCA)-based EPFs (PCA-EPFs) method for HSI classification is proposed, which consists of the following steps. First, the standard EPFs are constructed by applying edge-preserving filters with different parameter settings to the considered image, and the resulting EPFs are stacked together. Next, the spectral dimension of the stacked EPFs is reduced with the PCA, which not only can represent the EPFs in the mean square sense but also highlight the separability of pixels in the EPFs. Finally, the resulting PCA-EPFs are classified by a support vector machine (SVM) classifier. Experiments performed on several real hyperspectral data sets show the effectiveness of the proposed PCA-EPFs, which sharply improves the accuracy of the SVM classifier with respect to the standard edge-preserving filtering-based feature extraction method, and other widely used spectral-spatial classifiers.

PCA-Based Edge-Preserving Features for Hyperspectral Image Classification

Convolutional neural network (CNN) is well known for its capability of feature learning and has made revolutionary achievements in many applications, such as scene recognition and target detection. In this paper, its capability of feature learning in hyperspectral images is explored by constructing a five-layer CNN for classification (C-CNN). The proposed C-CNN is constructed by including recent advances in deep learning area, such as batch normalization, dropout, and parametric rectified linear unit (PReLU) activation function. In addition, both spatial context and spectral information are elegantly integrated into the C-CNN such that spatial-spectral features are learned for hyperspectral images. A companion feature-learning CNN (FL-CNN) is constructed by extracting fully connected feature layers in this C-CNN. Both supervised and unsupervised modes are designed for the proposed FL-CNN to learn sensor-specific spatial-spectral features. Extensive experimental results on four benchmark data sets from two well-known hyperspectral sensors, namely airborne visible/infrared imaging spectrometer (AVIRIS) and reflective optics system imaging spectrometer (ROSIS) sensors, demonstrate that our proposed C-CNN outperforms the state-of-the-art CNN-based classification methods, and its corresponding FL-CNN is very effective to extract sensor-specific spatial-spectral features for hyperspectral applications under both supervised and unsupervised modes.

Learning Sensor-Specific Spatial-Spectral Features of Hyperspectral Images via Convolutional Neural Networks

As a widely used approach for feature extraction and data reduction, Principal Components Analysis (PCA) suffers from high computational cost, large memory requirement and low efficacy in dealing with large dimensional datasets such as Hyperspectral Imaging (HSI). Consequently, a novel Folded-PCA is proposed, where the spectral vector is folded into a matrix to allow the covariance matrix to be determined more efficiently. With this matrix-based representation, both global and local structures are extracted to provide additional information for data classification. Moreover, both the computational cost and the memory requirement have been significantly reduced. Using Support Vector Machine (SVM) for classification on two well-known HSI datasets and one Synthetic Aperture Radar (SAR) dataset in remote sensing, quantitative results are generated for objective evaluations. Comprehensive results have indicated that the proposed Folded-PCA approach not only outperforms the conventional PCA but also the baseline approach where the whole feature sets are used.

Novel Folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing

Due to the remarkable achievements obtained by deep learning methods in the fields of computer vision, an increasing number of researches have been made to apply these powerful tools into hyperspectral image (HSI) classification. So far, most of these methods utilize a pre-training stage followed by a fine-tuning stage to extract deep features, which is not only tremendously time-consuming but also depends largely on a great deal of training data. In this study, we propose an efficient deep learning based method, namely, Random Patches Network (RPNet) for HSI classification, which directly regards the random patches taken from the image as the convolution kernels without any training. By combining both shallow and deep convolutional features, RPNet has the advantage of multi-scale, which possesses a better adaption for HSI classification, where different objects tend to have different scales. In the experiments, the proposed method and its two variants RandomNet and RPNet–single are tested on three benchmark hyperspectral data sets. The experimental results demonstrate the RPNet can yield a competitive performance compared with existing methods.

Hyperspectral image classification via a random patches network

As a very recent technique for time-series analysis, singular spectrum analysis (SSA) has been applied in many diverse areas, where an original 1-D signal can be decomposed into a sum of components, including varying trends, oscillations, and noise. Considering pixel-based spectral profiles as 1-D signals, in this letter, SSA has been applied in hyperspectral imaging for effective feature extraction. By removing noisy components in extracting the features, the discriminating ability of the features has been much improved. Experiments show that this SSA approach supersedes the empirical mode decomposition technique from which our work was originally inspired, where improved results in effective data classification using support vector machine are also reported.

/pdf/singular-spectrum-analysis-for-effective-feature-extraction-3vb7k2in98.pdf

Singular Spectrum Analysis for Effective Feature Extraction in Hyperspectral Imaging

Speckle noise is an inherent but annoying property in the synthetic aperture radar (SAR) imaging. In this paper we investigate the influence of speckle on the classical convolutional neural network (CNN) for SAR target classification. Then a dual stage coupled CNN architecture, named despeckling and classification coupled CNNs (DCC-CNNs), is proposed to distinguish multiple categories of ground targets in SAR images with strong and varying speckle. It first applies the despeckling sub-network for noise reduction. After that, residual speckle features as well as target information would be learned by the classification sub-network in order to solve the noise robustness problem of CNN. Besides, a new quantitative measure is developed for the quality assessment of SAR target images. It takes into account structural properties of the speckled SAR image of the target of interest and consistency with visual perception. Finally, a series of comparative experiments and discussions are carried out to validate the proposed assessment criterion and DCC-CNNs. Using synthetic SAR images based on the public MSTAR datasets, results show that the overall classification accuracy for ten ground target classes could be higher than 82% at a variety of speckle noise levels.

Ground Target Classification in Noisy SAR Images Using Convolutional Neural Networks

As a recent approach for time series analysis, singular spectrum analysis (SSA) has been successfully applied for feature extraction in hyperspectral imaging (HSI), leading to increased accuracy in pixel-based classification tasks. However, one of the main drawbacks of conventional SSA in HSI is the extremely high computational complexity, where each pixel requires individual and complete singular value decomposition (SVD) analyses. To address this issue, a fast implementation of SSA (F-SSA) is proposed for efficient feature extraction in HSI. Rather than applying pixel-based SVD as conventional SSA does, the fast implementation only needs one SVD applied to a representative pixel, i.e., either the median or the mean spectral vector of the HSI hypercube. The result of SVD is employed as a unique transform matrix for all the pixels within the hypercube. As demonstrated in experiments using two well-known publicly available data sets, almost identical results are produced by the fast implementation in terms of accuracy of data classification, using the support vector machine (SVM) classifier. However, the overall computational complexity has been significantly reduced.

/pdf/fast-implementation-of-singular-spectrum-analysis-for-1mgwupxhdh.pdf

Jun Wang

Papers

Novel Folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing

Singular Spectrum Analysis for Effective Feature Extraction in Hyperspectral Imaging

Ground Target Classification in Noisy SAR Images Using Convolutional Neural Networks

Fast Implementation of Singular Spectrum Analysis for Effective Feature Extraction in Hyperspectral Imaging