Hyperspectral Anomaly Detection Using Combined Similarity Criteria

Hyperspectral imagery systems have the ability to collect 3D digital images with rich spatial and spectral information. Anomaly detection is one of the interesting applications over last two decades in hyperspectral imagery. In this paper, we propose Collaborative Representation-Based with Outlier Removal Anomaly Detector (CRBORAD) method for HSI Anomaly Detection. We use both spectral and spatial information for detecting anomalies instead of using only spectral information that was introduced in our previous work. The proposed detector can adaptively estimate the background by its adjacent pixels within a sliding dual window. Before estimating background pixels, we remove outlier pixels that are significantly different from majority of pixels. It leads us to precise background approximation and better accuracy for detecting anomalies in subsequent stages. The residual image is constituted by subtracting the predicted background from the original HSI, and anomalies can be determined in the residual image, finally. Kernel extension of the proposed approach is also presented. We implemented the proposed algorithms on San Diego airport hyperspectral data. CRBORAD results are illustrated using receiver-operating-characteristic (ROC) curves, Area Under Curve (AUC) values and intuitive images. Comparing the results of the current study with four popular and previous methods shows that CRBORAD provides us an accurate method for detecting anomalies.

Spectral mixture analysis (also called spectral unmixing) is one of the important and effective techniques to estimate abundance fractions of materials present in the hyperspectral imagery. Linear spectral mixture modeling is widely used in solving the spectral unmixing problems as its conciseness and clarity of physical meaning. This paper presents a novel algorithm to produce fully constrained (i.e. non-negative and sum to one constrained) abundance using the barycentric coordinates in the n-simplex. To impose non-negative constraint on the abundance, the proposed method use a serious of orthogonal projections to find the fully constrained solution, which takes into account the geometric structure of hyperspectral data set. The proposed algorithm is in line with the least squares criterion. The efficiency and effectiveness of the resulting unmixing algorithm is demonstrated using both synthetic and real hyperspectral images.

This article proposes a symmetric sparse representation (SSR) method to extract pure endmembers from hyperspectral imagery (HSI). The SSR combines the features of the linear unmixing model and the sparse subspace clustering model of endmembers, and it assumes that the desired endmembers and all the HSI pixel points can be sparsely represented by each other. It formulates the endmember extraction problem into a famous program of archetypal analysis, and accordingly, extracting pure endmembers can be transformed as finding the archetypes in the minimal convex hull containing all the HSI pixel points. The vector quantization scheme is adopted to help in carefully choosing the initial pure endmembers, and the archetypal analysis program is solved using the simple projected gradient algorithm. Seven state-of-the-art methods are implemented to make comparisons with the SSR on both synthetic and real hyperspectral images. Experimental results show that the SSR outperforms all the seven methods in spectral angle distance and root-mean-square error, and it can be a good alternative choice for extracting pure endmembers from HSI data.

Kernel-based regularized-angle spectral matching for target detection in hyperspectral imagery

Optimum removal in ion-beam figuring

In this paper, we propose a collaborative representation-based binary hypothesis model with multi-features learning (CRTDBH-MTL) for target detection in hyperspectral imagery. The proposed method contained the following aspects. First, two complementary features extracted by different algorithms are implemented for describing hyperspectral imageries. Next, we apply these features into the unified collaborative representation-based binary hypothesis model (CRTDBH) to acquire a collaborative vector (CV) for each feature. Once the CV is obtained, the sample can be sparsely represented by the training samples from the background-only dictionary under the null hypothesis and the training samples from the target and background dictionaries under the alternative hypothesis. Finally, spatial correlation and spectral similarity of adjacent neighboring pixels are exploited to improve the detection performance. The experimental results suggest that the proposed algorithm shows an outstanding detection performance.

Abstract. In this study, correlation clustering is introduced to hyperspectral imagery for unsupervised classification. The main advantage of correlation clustering lies in its ability to simultaneously perform feature reduction and clustering. This algorithm also allows selection of different sets of features for different clusters. This framework provides an effective way to address the issues associated with the high dimensionality of the data. ORCLUS, a correlation clustering algorithm, is implemented and enhanced by making use of segmented principal component analysis (SPCA) instead of principal component analysis (PCA). Further, original implementation of ORCLUS makes use of eigenvectors corresponding to smallest eigenvalues whereas in this study eigenvectors corresponding to maximum eigenvalues are used, as traditionally done when PCA is used as feature reduction tool. Experiments are conducted on three real hyperspectral images. Preliminary analysis of algorithms on real hyperspectral imagery shows ORCLUS is able to produce acceptable results.

Matched filter, which models background variability using the statistics of the entire image with the assumption of rare and small targets, often fails when the target materials are frequently present in the image data. In this study, an iterative matched filtering technique is proposed which can effectively reduce the contamination of background statistics by target signal without any complicated spectral or spatial pre-processing. It applies matched filter iteratively with gradual exclusion of target-like pixels from background characterization based on the matched filtered score. Experimental results using the real airborne hyperspectral image data and simulated data with artificial mineral targets show that the proposed method can dramatically improve the detection performance. Though the statistical complexity of background materials is not investigated, it is expected to be used as a simple and practical technique for improving the detection performance of matched filter by reducing target leakage effect when the target materials are frequently present in the image data. This technique also can be directly adopted by other extensions of matched filters such as constrained energy minimization (CEM) and adaptive cosine estimator (ACE).

Abstract. Anomaly detection has been of great interest in hyperspectral imagery analysis. Most conventional anomaly detectors merely take advantage of spectral and spatial information within neighboring pixels. In this paper, two methods of Unsupervised Nearest Regularized Subspace-based with Outlier Removal Anomaly Detector (UNRSORAD) and Local Summation UNRSORAD (LSUNRSORAD) are proposed, which are based on the concept that each pixel in background can be approximately represented by its spatial neighborhoods, while anomalies cannot. Using a dual window, an approximation of each testing pixel is a representation of surrounding data via a linear combination. The existence of outliers in the dual window will affect detection accuracy. Proposed detectors remove outlier pixels that are significantly different from majority of pixels. In order to make full use of various local spatial distributions information with the neighboring pixels of the pixels under test, we take the local summation dual-window sliding strategy. The residual image is constituted by subtracting the predicted background from the original hyperspectral imagery, and anomalies can be detected in the residual image. Experimental results show that the proposed methods have greatly improved the detection accuracy compared with other traditional detection method.

Hyperspectral imagery (HSI) denoising is a popular research topic in remote sensing. In this paper, we propose a novel method for HSI denoising by performing Minimum Noise Fraction (MNF) to the original HSI data cube, thresholding the noisy output bands with the Video Non-Local Bayes (VNLB) algorithm, and then conducting the inverse MNF transform to obtain the denoised data cube. Our experiments demonstrate that the proposed method usually achieves the best denoising results among several existing denoising methods for two HSI data cubes. In addition, it is much faster for HSI denoising than the VNLB algorithm which was originally developed for video denoising.

Surface water is an essential carrier for the balance of ecosystems and human existence. As applied hyperspectral remote sensing has improved, the research into water extraction from the hyperspectral image gradually attracted more attention. However, delineating water from the hyperspectral image is challenging due to shadows of buildings and trees, and other dark pixels. Furthermore, water indexes that come from multispectral imagery are directly applied to hyperspectral imagery leads to some defects, such as underutilized abundant information and higher misclassifications. Here, we proposed a decision tree water index (DTWI) method to extract water bodies from hyperspectral imagery. Combining the threshold of the near-infrared reflectance and the magnitude of the difference between reflectance of 700 and 730 nm, the DTWI method could effectively extract water from hyperspectral imagery. Three hyperspectral images derived from the study areas within the city, a mixture of city and suburban zone, and suburban zone only, were applied to test the feasibility and flexibility of this method in various sensors and environments. Four alternative methods were used to verify the robustness of the proposed method, including hyperspectral difference water index, normalized difference water index, shaded building index, and support vector machine (SVM). Our results indicated that the proposed method was better suited to extracting water bodies from hyperspectral imagery when compared with other methods and could effectively capture water on different hyperspectral sensors, various heterogeneous surroundings, and multi-spatial scales. The proposed DTWI method has high stability in threshold and band selection, which is comparable to the SVM method in the mean overall accuracy and kappa coefficient (DTWI: 0.98 and 0.81; SVM: 0.98 and 0.82). For the view of elapsed time, calculation, and applicability, the proposed method has the potential of better utilization and rapid response for water extraction in hyperspectral imagery.

One of the universally studied research topics is a reversible data hiding approach because of its wide applications in medical image transmission, cloud computing as well as in military services. In the introduced scheme stated in this paper, a new RDH scheme in encrypted images is proposed which ensures a good embedding rate without compromising the bit error rate. The scheme introduced in this manuscript uses a new measure that is computationally efficient and ensures real-time performance. In the proposed scheme, the original image is divided into blocks and in each block, one secret message bit is hidden by the data hider. All the pixels in the image block are categorized into two classes: black pixels and white pixels based on the predefined checkerboard pattern. The data hiding is performed by mapping the pixel values in the white position to a new value, only if the data hider wants to hide a secret bit 1. At the time of data extraction and image recovery, the closeness between the adjacent pixels is analyzed by considering a pair of adjacent black pixels and white pixels from the quantized image blocks. The overall experimental study of the proposed scheme is carried out using the standard images from the USC-SIPI image dataset managed by the University of Southern California.

The presence of the multiplicative speckle noise, intrinsic to Electronic Speckle Pattern Interferometry (ESPI), limits the quality of ESPI measurements. Of many algorithms proposed to reduce the speckle noise in the image, only few recognize the statistical properties of the speckle noise and the multiplicative relation between the underlying cosinusoidal pattern and the speckle interferogram. Local averaging is a limited approach because of the possibly very high differences between the adjacent pixels in relation to the mean signal value, which corresponds to particularly low signal to noise ratio. In this paper we test an approach based on the non-local means algorithm, which is a global weighted averaging scheme based on the pixels neighborhoods (patches) similarity criterion.

Hyperspectral imagery (HSI) creates a lot of applications in target or anomaly detection due to their rich spectral content. Generally, one scene of an HSI contains more than one class. Therefore, the Gaussian distribution assumption of the background fails. Furthermore, the high dimensionality of data makes background modelling more difficult by increasing redundancy and disturbances. In this paper, a segmented-distance based anomaly detection method is proposed for HSI. The proposed method is based on segmentation and takes advantage of the statistical properties of the segmented areas to suppress the false-alarms. In addition to that, nonlinear feature extraction based on convolutional stacked auto-encoder (SAE) neural networks are implemented to extract deep and nonlinear relations from the input data. Both 1-D and 2-D convolutional layers are investigated. The proposed method is tested on the three different datasets. The experimental results show that the integration of segmentation and deep feature extraction generally performs better than other state-of-the-art methods.

Previous multi-view spectral clustering methods are a two-step strategy, which first learns a fixed common representation (or common affinity matrix) of all the views from original data and then conducts k-means clustering on the resulting common affinity matrix. The two-step strategy is not able to output reasonable clustering performance since the goal of the first step (i.e., the common affinity matrix learning) is not designed for achieving the optimal clustering result. Moreover, the two-step strategy learns the common affinity matrix from original data, which often contain noise and redundancy to influence the quality of the common affinity matrix. To address these issues, in this paper, we design a novel One-step Multi-view Spectral Clustering (OMSC) method to output the common affinity matrix as the final clustering result. In the proposed method, the goal of the common affinity matrix learning is designed to achieving optimal clustering result and the common affinity matrix is learned from low-dimensional data where the noise and redundancy of original high-dimensional data have been removed. We further propose an iterative optimization method to fast solve the proposed objective function. Experimental results on both synthetic datasets and public datasets validated the effectiveness of our proposed method, comparing to the state-of-the-art methods for multi-view clustering.