Test Pixel Research Articles

Region‐division‐based joint sparse representation classification for hyperspectral images

In this article, a region-division-based joint sparse representation classification (RDJSRC) method is proposed to solve the heterogeneous region problem in the joint sparse representation classification (JSRC) method used in hyperspectral image (HSI) classification. The RDJSRC method incorporates regional information, obtained by the hidden Markov random field (HMRF), into the JSRC to reduce the interference of heterogeneous pixels in the neighbourhood of the test pixel and finally improve the classification performance. The framework of this method is as follows. The first several principal components (PCs) are initially selected to be the new HSI by transforming the original HSI with the PC analysis algorithm. Then, the regional information containing the spatial structure of the HSI is obtained by applying the HMRF algorithm to the first PC. Through incorporating this regional information into the JSRC procedure, the initial label of the test pixel can be jointly determined by the new HSI pixels within the homogeneity in the search window. Ultimately, the final label of the test pixel is determined by a voting strategy based on multiple classification results. Compared with several classification methods, experimental results, indicate that this method achieves improvement from 2 to 3% in HSI classification.

Robust Hyperspectral Image Domain Adaptation With Noisy Labels

In hyperspectral image (HSI) classification, domain adaptation (DA) methods have been proved effective to address unsatisfactory classification results caused by the distribution difference between training (i.e., source domain) and testing (i.e., target domain) pixels. However, these methods rely on accurate labels in source domain, and seldom consider the performance drop resulted by noisy label, which often happens since labeling pixel in HSI is a challenging task. To improve the robustness of DA method to label noise, we propose a new unsupervised HSI DA method, which is constructed from both feature-level and classifier-level. First, a linear transformation function is learned in feature-level to align the source (domain) subspace with the target (domain) subspace. Then, a robust low-rank representation based classifier is developed to well cope with the features obtained from the aligned subspace. Since both subspace alignment and the classifier are immune to noisy labels, the proposed method obtains good classification results when confronting with noisy labels in source domain. Experimental results on two DA benchmarks demonstrate the effectiveness of the proposed method.

Regularized Multiple Sparse Bayesian Learning for Hyperspectral Target Detection

The sparse representation method has been successfully applied in the field of hyperspectral image target detection. It assumes that target detection can be achieved by using target and background libraries to represent test pixels. Under this formulation, the presentation of the target and background signatures can be solved by L1-norm minimization of the weight coefficient and the target detection output is simply achieved by the difference between the two representation residuals. In this paper, a regularized multiple sparse Bayesian learning (RMSBL) method for hyperspectral target detection is proposed, which is established by Bayesian inference using the conditional posterior distributions of the model parameters under a hierarchical Bayesian model. According to the cost function for multiple sparse Bayesian learning, the presentation of the target and background signatures can be obtained by an L2,1-norm iterative minimization method. And the target detection result can be achieved with the difference between the two representation residuals. Four groups of hyperspectral datasets are used for simulation experiments. The results are compared with those of other common detection algorithms. The experimental results demonstrate that the RMSBL algorithm has higher detection performance.

Hyperspectral image classification by combining local binary pattern and joint sparse representation

ABSTRACTThis paper proposes a new hyperspectral classification method that combines the joint sparse representation classifier (JSRC) and local binary pattern (LBP) (JSR-LBP). The proposed method uses a statistical histogram of the LBP feature spectrum as a feature vector for classification and recognition. Using the LBP method let us extract the local texture feature of an image more accurately and effectively because of the forceful robustness to light. The proposed method JSR-LBP mainly includes the following steps: First, the JSRC is used to obtain the representation residuals of different pixels. Then, the LBP value is calculated for every pixel in the whole image to generate the LBP histogram; the LBP histogram of the test sample can be obtained from a series of binary codes that are generated using statistics. Next, the Bhattacharyya coefficient is employed to measure the similarity between the test and training samples unlike the traditional classifiers as -nearest neighbor that usually employ the Euclidean distance as similarity metric, and a regularization parameter is then introduced to achieve the balance between the JSRC and LBP. Finally, the test pixel’s label is determined by applying the final residual. Experimental results performed on three real hyperspectral images data demonstrate the outstanding performance of the proposed approach compared to other broader classifiers.

Anomaly Detection for Hyperspectral Imagery Based on the Regularized Subspace Method and Collaborative Representation

Most of the conventional anomaly detectors only take advantage of the spectral information and do not consider the spatial information within neighboring pixels. Recently, the spectral-spatial based local summation anomaly detection (LSAD) algorithm has achieved excellent detection performances. In order to obtain various local spatial distributions with the neighboring pixels of the pixels under test, the LSAD algorithm exploits a multiple-window sliding filter, which can be computationally expensive and time-consuming. In this paper, to address these issues, two modified LSAD-based methods are proposed. The first method, called local summation unsupervised nearest regularized subspace with an outlier removal anomaly detector (LSUNRSORAD), is based on the concept that each pixel in the background can be approximately represented by its spatial neighborhood. The second method, called local summation anomaly detection based on collaborative representation and inverse distance weight (LSAD-CR-IDW), uses the surrounding pixels collected inside the outer window, while outside the inner window, to linearly represent the test pixel and introduces collaborative representation and inverse distance weight to further improve the computational speed and detection precision, respectively. The proposed methods were applied to a synthetic dataset and three real datasets. The experimental results show that the proposed methods have a better detection accuracy and computational speed when compared with the LSAD algorithm and others.

A probabilistic fusion of a support vector machine and a joint sparsity model for hyperspectral imagery classification

Hyperspectral imagery (HSI) is now in use for a wide range of applications such as land cover classification, climate change studies and environmental monitoring; however, the acquisition of HSI is still costly, and the curse of dimensionality i.e. the phenomenon that the amount of required training samples increases exponentially as the dimensionality increases linearly, makes it difficult to exploit the full potential of machine learning in HSI classification. To resolve the problem, we propose a novel framework for spatial-spectral HSI classification in this article. A soft support vector machine (SVM) and a probabilistic joint sparsity model (JSM) are proposed to compute a posteriori probabilities of the test pixels, respectively; and the probability scores are then fused by a linear opinion pool. Furthermore, a Markov random field (MRF) model is used as a maximum a posteriori (MAP) segmentation method for further regularization of the neighbor information to derive the labels for pixels. Extensive experiments conducted on three commonly-used benchmarking data sets show that the proposed probabilistic fusion method outperforms a number of well-known spatial-spectral HSI classification techniques.

Kernel Joint Sparse Representation Based on Self-Paced Learning for Hyperspectral Image Classification

By means of joint sparse representation (JSR) and kernel representation, kernel joint sparse representation (KJSR) models can effectively model the intrinsic nonlinear relations of hyperspectral data and better exploit spatial neighborhood structure to improve the classification performance of hyperspectral images. However, due to the presence of noisy or inhomogeneous pixels around the central testing pixel in the spatial domain, the performance of KJSR is greatly affected. Motivated by the idea of self-paced learning (SPL), this paper proposes a self-paced KJSR (SPKJSR) model to adaptively learn weights and sparse coefficient vectors for different neighboring pixels in the kernel-based feature space. SPL strateges can learn a weight to indicate the difficulty of feature pixels within a spatial neighborhood. By assigning small weights for unimportant or complex pixels, the negative effect of inhomogeneous or noisy neighboring pixels can be suppressed. Hence, SPKJSR is usually much more robust. Experimental results on Indian Pines and Salinas hyperspectral data sets demonstrate that SPKJSR is much more effective than traditional JSR and KJSR models.

The Dark Side of Penumbral Microjets: Observations in Hα

Abstract We present data of 10 penumbral microjets (PMJs) observed in a Hα, Ca ii 8542 Å, and Fe i 6302 Å line pair with the Swedish 1 m Solar Telescope (SST) with CRISP and Ca ii K with SST/CHROMIS in active region NOAA 12599 on 2016 October 12 at μ = 0.68. All four Stokes parameters of the Ca ii 8542 Å and Fe i 6302 Å lines were observed and a series of test pixels were inverted using the Stockholm inversion code. Our analysis revealed for the first time that PMJs are visible in Hα, where they appear as dark features with average line-of-sight (LOS) upflows of 1.1 ± 0.6 km s−1, matching the LOS velocities from the inversions. Based on the Hα observations we extend the previous average length and lifetime of PMJs to 2815 ± 530 km and 163 ± 25 s, respectively. The plane-of-sky (POS) velocities of our PMJs of up to 17 km s−1 tend to give increased velocities with distance traveled. Furthermore, two of our PMJs with significant Stokes V signal indicate that the PMJs possess an increased LOS magnetic field of up to 100 G compared to the local pre-/post- PMJ magnetic field, which propagates as quickly as the PMJs’ POS velocities. Finally, we present evidence that PMJs display an on average 1 minute gradual precursory brightening that only manifests itself in the cores of the Ca ii lines. We conclude that PMJs are not ordinary jets but likely are manifestations of heat fronts that propagate at the local Alfvén velocity.

A Constrained Sparse Representation Model for Hyperspectral Anomaly Detection

In this paper, we propose a novel sparsity-based algorithm for anomaly detection in hyperspectral imagery. The algorithm is based on the concept that a background pixel can be approximately represented as a sparse linear combination of its spatial neighbors while an anomaly pixel cannot if the anomalies are removed from its neighborhood. To be physically meaningful, the sum-to-one and nonnegativity constraints are imposed to abundance vector based on the linear mixture model, and the upper bound constraint on sparsity level is removed for better recovery of the test pixel. First, the proposed method utilizes the redundant background information to automatically remove anomalies from the background dictionary. Then, the reconstruction error obtained by the new background dictionary is directly used for anomaly detection. Moreover, a kernel version of the proposed method is also derived to completely exploit the nonlinear feature of hyperspectral data. An important advantage of the proposed methods is their capability to adaptively model the background even when some anomaly pixels are involved. Extensive experiments have been conducted on three real hyperspectral data sets. It is demonstrated that the proposed detectors achieve a promising detection performance with a relatively low computational cost.

Development of the SLRI beam test facility for characterization of monolithic active pixel sensors

Abstract Synchrotron Light Research Institute (SLRI) has successfully constructed a new experimental station, a Beam Test Facility (BTF), to the current SLRI accelerator complex. SLRI-BTF is capable of producing electron test beams with the number of electrons ranging from a few to millions of electrons per spill and with tunable energy from 40 MeV up to 1.2 GeV. The required intensity and energy of the test beam are obtained using a combination of a metal target to reduce high-intensity primary beam and a synchrotron booster to accelerate secondary beam to desired energy. The repetition rate of the test beam is up to 0.5 Hz depending on the selected energy and the pulse width is 90 ns. SLRI-BTF targets to service electron test beams with defined intensity and energy for testing and calibration of high-energy particle detectors as well as other beam diagnostic instrumentations. In commissioning, a pixel sensor telescope was employed as a detector to measure the number of electrons and as a preparation to investigate efficiency of mono active pixel sensors. The results confirm production of the low multiplicity of high-energy electrons at SLRI-BTF and the efficiency of a test pixel sensor is successfully calculated.

A New Steganography Method Using Integer Wavelet Transform and Least Significant Bit Substitution

Abstract Steganography is a data hiding technique, which is used for securing data. Both spatial and transform domains are used to implement a steganography method. In this paper, a novel transform domain method is proposed to provide a better data hiding method. The method uses a multi-resolution transform function, integer wavelet transform (IWT) that decomposes an image into four subbands: low-low, low-high, high-low and high-high subband. The proposed method utilizes only the three subbands keeping the low-low subband untouched which helps to improve the quality of the stego image. The method applies a coefficient value differencing approach to determine the number of secret bits to be embedded in the coefficients. The method shows a good performance in terms of embedding capacity, imperceptibility and robustness. A number of metrics are computed to show the quality of the stego image. It can also withstand RS steganalysis, Chi-squared test and Subtractive Pixel Adjacency Matrix steganalysis successfully. The deformation of the histogram and Pixel Difference Histogram for different embedding percentages are also demonstrated, which show a significant similarity with the original cover image. The proposed method shows an achievement of 2.3bpp embedding capacity with a good quality of stego image.

Dual-Path Network-Based Hyperspectral Image Classification

Recently, convolutional neural networks (CNNs) as a powerful tool have been introduced for classification of hyperspectral images (HSIs). However, it fails to take the feature redundancy into consideration. Hence, for the pixel-wise HSI classification, the CNN-based methods may not effectively extract the discriminative features from the complex scene in HSIs. In order to overcome this problem, in this letter, a novel dual-path network (DPN)-based HSI classification method is proposed, in which the DPN combines the advantages of the residual network and dense convolutional network. First, the principal component analysis is utilized to extract significant components of HSI. Second, training image patches centered on labeled pixels are constructed to train the DPN. Finally, the labels of test pixels are predicted by using the trained network. Experiments conducted on two hyperspectral data sets demonstrate the state-of-the-art performance of the proposed method over other compared methods in terms of classification accuracies.

Fabrication of 12 µm pixel-pitch 1280 × 1024 extended short wavelength infrared focal plane array using heterojunction type-II superlattice-based photodetectors

We present an intial demonstration of a 1280 × 1024 extended short-wavelength infrared focal plane array (FPA) imager with 12 μm pixel-pitch based on type–II InAs/AlSb/GaSb superlattice heterojunction photodetectors, with a novel bandstructure-engineered photo-generated carrier extractor as the window layer in the hetero structure to efficiently extract the photo-generated carriers. This heterostructure with a larger bandgap top window/contact layer leads to the device having lower dark current density compared to conventional pn junction devices. The large format FPA was fabricated with 12 μm pixel-pitch using a developed fabrication process. Test pixels fabricated separately exhibit 100% cut–off wavelengths of ∼2.22, ∼2.34 μm, and ∼2.45 μm at 150, 200 K, and 300 K. The test devices achieve saturated quantum efficiency values under zero bias of 54.3% and 68.4% at 150 and 300 K, under back-side illumination and without any anti-reflection coating. At 150 K, these photodetectors exhibit dark current density of 1.63 × 10−7 A cm−2 under −20 mV applied bias providing a specific detectivity of 1.01 × 1011 cm · Hz1/2/W at 1.9 μm.

Self-Paced Joint Sparse Representation for the Classification of Hyperspectral Images

In this paper, a self-paced joint sparse representation (SPJSR) model is proposed for the classification of hyperspectral images (HSIs). It replaces the least-squares (LS) loss in the standard joint sparse representation (JSR) model with a weighted LS loss and adopts a self-paced learning (SPL) strategy to learn the weights for neighboring pixels. Rather than predefining a weight vector in the existing weighted JSR methods, both the weight and sparse representation (SR) coefficient associated with neighboring pixels are optimized by an alternating iterative strategy. According to the nature of SPL, in each iteration, neighboring pixels with nonzero weights (i.e., easy pixels) are included for the joint SR of a testing pixel. With the increase of iterations, the model size (i.e., the number of selected neighboring pixels) is enlarged and more neighboring pixels from easy to complex are gradually added into the JSR learning process. After several iterations, the algorithm can be terminated to produce a desirable model that includes easy homogeneous pixels and excludes complex inhomogeneous pixels. Experimental results on two benchmark hyperspectral data sets demonstrate that our proposed SPJSR is more accurate and robust than existing JSR methods, especially in the case of heavy noise.

Local adaptive joint sparse representation for hyperspectral image classification

In this paper, a local adaptive joint sparse representation (LAJSR) model is proposed for the classification of hyperspectral remote sensing images. It improves the original joint sparse representation (JSR) method in both the signal and dictionary construction phase and sparse representation phase. Given a testing pixel, a similar signal set is constructed by picking a few of the most similar pixels from its spatial neighborhood. The original training dictionary consists of training samples from different classes and is extended by adding spatial neighbors of each training sample. A local adaptive dictionary is built by selecting the most representative atoms from the extended dictionary that are correlated to the similar signal set. In the LAJSR framework, the selected similar signals are simultaneously represented by the local adaptive dictionary, and the obtained sparse representation coefficients are further weighted by a sparsity concentration index vector which aims to concentrate and highlight the coefficients on the expected class. Experimental results on two benchmark hyperspectral data sets have demonstrated that the proposed LAJSR method is much more effective than existing JSR and SVM methods, especially in the case of small sample sizes.

Hyperspectral image classification using spectral mixing metrics representation

ABSTRACTThis letter presents new classification methods that effectively fuse the spectral mixing metrics and joint sparse representation (JSR) (SMMR) for hyperspectral image (HSI), in which SMMR combines the spectral information divergence (SID) with transformed spectral angle mapper (SAM), namely that SID is multiplied by the tangent of the SAM (SMMRtg) and the sine of SAM (SMMRsn), respectively. The proposed methods SMMRtg and SMMRsn mainly include the following steps. First, the SIDtan(SAM) and SIDsin(SAM) of the spectral bands among test and training samples are calculated that respectively depend on two different function versions. Second, the JSR model is utilized to obtain the representation residuals of different pixels for the test set. Third, a regularization parameter is employed to achieve a balance in SMMR. Finally, the label of the test pixel is determined by the eventual decision function of two proposed methods. Experimental results on the Indian Pines and Washington DC datasets demonstrate that the proposed methods achieve superior performance compared with several previous methods.

Multiobjective-Based Sparse Representation Classifier for Hyperspectral Imagery Using Limited Samples

Recent studies about hyperspectral imagery (HSI) classification usually focus on extracting more representative features or combining joint spectral–spatial information. However, besides feature extraction, developing more powerful classifiers can also contribute to the accuracies of HSI classification. In this paper, we propose a multiobjective-based sparse representation classifier (MSRC) for HSI data, which mainly tries to address two problems: 1) pixel mixing and 2) lacking abundant labeled samples. MSRC is motivated by the SRC, and further integrating the idea of hyperspectral unmixing. Different from the traditional SRC-based methods, the novelty of MSRC consists of the optimization process, i.e., we directly handle the L0-norm problem without any relaxation. The sparse term is not considered as a regularization operation. Instead, we transform the problem of weight vector estimation to subset selection, and propose a multiobjective-based method to optimize the L0-norm sparse problem. The residual term and sparse term are regarded as two parallel objective functions that are optimized simultaneously. We further utilize the linear mixing model to represent test pixels based on the selected atoms. The final class labels are determined according to the abundance estimation results by nonnegative least squares. Owing to the characteristics of the multiobjective method and the binary property of the sparse solution vector, MSRC does not require too many training samples to build the dictionary. Moreover, theoretically, MSRC can be easily improved to extended version such as combining spatial information.

Hyperspectral Anomaly Detection Using Collaborative Representation With Outlier Removal

Recently, collaborative representation detector (CRD) has been popularly used for hyperspectral anomaly detection. For the original CRD, the least squares solution becomes more unstable when more classes, i.e., samples for anomaly detection are involved, and the detection error is likely to happen if the test pixel is an anomalous pixel and several samples from background are similar anomalous. In this paper, we propose a hyperspectral anomaly detection method that uses CRD with principal component analysis (PCA) for removing outlier (PCAroCRD). According to the different background modeling methods, global and local versions are proposed. In the proposed algorithm, the spatial-domain PCA is adopted to extract main pixel information of global/local background that will be used as samples for collaborative representation, and simultaneously the information of abnormal pixels in global/local background can be removed. Fewer useful samples can also keep the detection result stable. Experimental results indicate that the PCAroCRD outperforms the original CRD, kernel version of CRD, advanced CRD (CRDBORAD), morphology-based CRD, Global Reed–Xiaoli (RX) algorithm, and the Local RX.

Hyperspectral Image Classification via Weighted Joint Nearest Neighbor and Sparse Representation

The $k$ -nearest neighbor ( $k$ -NN) method relies on Euclidean distance as a classification measure to obtain the labels of the test samples. Recently, many studies show that joint region of test samples can make full use of the spatial information of hyperspectral image. However, traditional joint $k$ -NN algorithm holds that the weight of the each test sample in a local region is identical, which is not reasonable, since each test sample may have different importance and distribution. To solve this problem, a weighted joint nearest neighbor and sparse representation method is proposed in this paper, which consists of the following steps: first, a Gaussian weighted function has been introduced into the joint region of test pixels so as to obtain the weighted joint Euclidean distance. Next, the sparse representation-based method is adopted to obtain the representation residuals. Finally, a decision function is applied to achieve the balance between the weighted joint Euclidean distance and residual of the sparse representation. Experiments performed on the four real HSI datasets have demonstrated that the proposed methods can achieve better performance than several previous methods.

KNN-Based Representation of Superpixels for Hyperspectral Image Classification

Superpixel segmentation has been demonstrated to be a powerful tool in hyperspectral image (HSI) classification. Each superpixel region can be regarded as a homogeneous region, which is composed of a series of spatial neighboring pixels. However, a superpixel region may contain the pixels from different classes. To further explore the optimal representations of superpixels, a new framework based on two k selection rules is proposed to find the most representative training and test samples. The proposed method consists of the following four steps: first, a superpixel segmentation algorithm is performed on the HSI to cluster the pixels with similar spectral features into the same superpixel. Then, a domain transform recursive filtering is used to extract the spectral-spatial features of the HSI. Next, the k nearest neighbor (KNN) method is utilized to select k <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> representative training samples and k <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> test pixels for each superpixel, which can effectively overcome the within-class variations and between-class interference, respectively. Finally, the class label of superpixels can be determined by measuring the averaged distances among the selected training and test samples. Experiments conducted on four real hyperspectral datasets show that the proposed method provides competitive classification performances with respect to several recently proposed spectral-spatial classification methods.