Repeatability of hyperspectral imaging systems—quantification and improvement

This paper addresses a generic problem in remote sensing by aerial hyperspectral imaging systems, that is, very low spatial and spectral repeatability of image cubes. Most analysts are either unaware of this problem or just ignore it. Hyperspectral image cubes acquired in consecutive flights over the same target should ideally be identical. In practice, two consecutive flights over the same target usually yield significant differences between the image cubes. These differences are due to variations in: target characteristics, solar illumination, atmospheric conditions and errors of the imaging system proper. Manufacturers of remote sensing imaging systems use sophisticated equipment to accurately calibrate their instruments, using optimal illumination and constant environment conditions. From a user's perspective, these calibration procedures are only of marginal interest because repeatability is ‘target dependent’. The analyst of hyperspectral imagery is primarily interested in the reliability of the end product, i.e. the repeatability of two image cubes consecutively acquired over the same target, after radiometric calibration, geo‐referencing and atmospheric corrections. Clearly, when the non‐repeatability variance is similar in magnitude to the variance of the spectral or spatial information of interest, it would be impossible to use it for classification or quantification prediction modelling. We present a simple approach for objective assessment of spatial and spectral repeatability by multiple image cube acquisitions, wherein the imaging system views a barium sulphate (BaSO₄) painted panel illuminated by a halogen lamp and by consecutive flights over a reference target. The data analysis is based on several indexes, which were developed for quantifying the spectral and spatial repeatability of hyperspectral image cubes and for detecting outlier voxels. The spectral repeatability information can be used to average less repeatable spectral bands or to exclude them from the analysis. The spatial repeatability information may be used for identifying less repeatable regions of the target. Outlier voxels should be excluded from the analysis because they are grossly erroneous data. Modus operandi for image cube acquisitions is provided, whereby the repeatability may be improved. Spatial and spectral averaging algorithms and software were developed for increasing the repeatability of image cubes in post‐processing.     

Using low‐spectral‐resolution images to acquire simulated hyperspectral images

We propose a method to acquire simulated hyperspectral images using low‐spectral‐resolution images. Hyperspectral images provide more spectral information than low‐spectral‐resolution images, because of the additional spectral bands used for data acquisition in hyperspectral imaging. Unfortunately, original hyperspectral images are more expensive and more difficult to acquire. However, some research questions require an abundance of spectral information for ground monitoring, which original hyperspectral images can easily provide. Hence, we need to propose a method to acquire simulated hyperspectral images, when original hyperspectral images are especially necessary. Since low‐spectral‐resolution images are readily available and cheaper, we develop a method to acquire simulated hyperspectral images using low‐spectral‐resolution images. With simulated hyperspectral images, we can acquire more ‘hidden’ information from low‐spectral‐resolution images. Our method uses the principles of pixel‐mixing to understand the compositional relationship of spectrum data to an image pixel, and to simulate radiation transmission processes. To this end, we use previously obtained data (i.e. spectrum library) and the sorting data of objects that are derived from a low‐spectral‐resolution image. Using the simulation of radiation transmission processes and these different data, we acquire simulated hyperspectral images. In addition, previous analyses of simulated remotely sensed images do not use quantitative statistical measures, but use qualitative methods, describing simulated images by sight. Here, we quantitatively assess our simulation by comparing the correlation coefficients of simulated images and real images. Finally, we use simulated hyperspectral images, real Hyperion images, and their corresponding ALI images to generate several classification images. The classification results demonstrate that simulated hyperspectral data contain additional information not available in the multispectral data. We find that our method can acquire simulated hyperspectral images quickly.     

A non-negative low-rank representation for hyperspectral band selection

Hyperspectral images are widely used in real applications due to their rich spectral information. However, the large volume brings a lot of inconvenience, such as storage and transmission. Hyperspectral band selection is an important technique to cope with this issue by selecting a few spectral bands to replace the original image. This article proposes a novel band selection algorithm that first estimates the redundancy through analysing relationships among spectral bands. After that, spectral bands are ranked according to their relative importance. Subsequently, in order to remove redundant spectral bands and preserve the original information, a maximal linearly independent subset is constructed as the optimal band combination. Contributions of this article are listed as follows: (1) A new strategy for band selection is proposed to preserve the original information mostly; (2) A non-negative low-rank representation algorithm is developed to discover intrinsic relationships among spectral bands; (3) A smart strategy is put forward to adaptively determine the optimal combination of spectral bands. To verify the effectiveness, experiments have been conducted on both hyperspectral unmixing and classification. For unmixing, the proposed algorithm decreases the average root mean square errors (RMSEs) by 0.05, 0.03, and 0.05 for the Urban, Cuprite, and Indian Pines data sets, respectively. With regard to classification, our algorithm achieves the overall accuracies of 77.07% and 89.19% for the Indian Pines and Pavia University data sets, respectively. These results are close to the performance with original images. Thus, comparative experiments not only illustrate the superiority of the proposed algorithm, but also prove the validity of band selection on hyperspectral image processing.     

结合空间光谱预处理和约束非负矩阵分解的高光谱图像混合像元分解

目的 混合像元问题在高光谱遥感图像处理分析中普遍存在,非负矩阵分解的方法被引入到高光谱图像解混中。本文提出结合空间光谱预处理和约束非负矩阵分解的混合像元分解流程。方法 结合空间光谱预处理的约束非负矩阵分解,如最小体积约束、流行约束等,通过加入邻域的空间和光谱信息进行预处理获得更优的预选端元,从而对非负矩阵分解的解混结果进行优化。结果 在5组不同信噪比的模拟数据实验中,空间预处理（SPP）和空间光谱预处理（SSPP）均能够有效提高约束非负矩阵分解（最小体积约束的非负矩阵分解和图正则非负矩阵分解）的解混结果,其中SPP在不同信噪比的情况下都能优化约束非负矩阵分解的结果,而SSPP在低信噪比的情况下,预处理效果更佳。利用美国内华达州Cuprite矿区数据进行真实数据实验,SPP提高了约束非负矩阵分解的解混精度,而SSPP在复杂场景下,解混精度更佳。模拟数据和真实数据的实验均表明,空间光谱预处理能够有效地提高约束非负矩阵分解的解混精度,特别是对于信噪比较低的情况下,融合空间和光谱信息对噪声有很好的鲁棒性。结论 本文对约束非负矩阵分解的解混算法添加空间光谱预处理,利用高光谱遥感数据的空间和光谱信息,优化预选端元,加入空间光谱预处理的非负矩阵解混实验流程,在复杂场景情况下,对噪声具有较好的鲁棒性。     

Kernel sparse representation for hyperspectral unmixing based on high mutual coherence spectral library

ABSTRACT

Sparse regression is now a popular method for hyperspectral unmixing relying on a prior spectral library. However, it is limited by the high mutual coherence spectral library which contains high similarity atoms. In order to improve the accuracy of sparse unmixing with a high mutual coherence spectral library, a new algorithm based on kernel sparse representation unmixing model with total variation constraint is proposed in this paper. By constructing an appropriate kernel function to expand similarity measure scale, library atoms and hyperspectral data are mapped to kernel space where sparse regression algorithms are then applied. Experiments conducted with both simulated and real hyperspectral data sets indicate that the proposed algorithm effectively improves the unmixing performance when using a high mutual coherence spectral library because of its ability to precisely extract endmembers in hyperspectral images. Compared with other state-of-the-art algorithms, the proposed algorithm obtains low reconstruction errors in pixels with different mixed degree.     

Fast determination of the number of endmembers for real-time hyperspectral unmixing on GPUs

Spectral unmixing is a very important task for remotely sensed hyperspectral data exploitation. It amounts at identifying a set of spectrally pure components (called endmembers) and their associated per-pixel coverage fractions (called abundances). A challenging problem in spectral unmixing is how to determine the number of endmembers in a given scene. Several automatic techniques exist for this purpose, including the virtual dimensionality (VD) concept or the hyperspectral signal identification by minimum error (HySime). Due to the complexity and high dimensionality of hyperspectral scenes, these techniques are computationally expensive. In this paper, we develop new fast implementations of VD and HySime using commodity graphics processing units. The proposed parallel implementations are validated in terms of accuracy and computational performance, showing significant speedups with regards to optimized serial implementations. The newly developed implementations are integrated in a fully operational unmixing chain which exhibits real-time performance with regards to the time that the hyperspectral instrument takes to collect the image data.     

Optimization of minimum volume constrained hyperspectral image unmixing on CPU–GPU heterogeneous platform

Hyperspectral unmixing is essential for efficient hyperspectral image processing. Nonnegative matrix factorization based on minimum volume constraint (MVC-NMF) is one of the most widely used methods for unsupervised unmixing for hyperspectral image without the pure-pixel assumption. But the model of MVC-NMF is unstable, and the traditional solution based on projected gradient algorithm (PG-MVC-NMF) converges slowly with low accuracy. In this paper, a novel parallel method is proposed for minimum volume constrained hyperspectral image unmixing on CPU–GPU Heterogeneous Platform. First, a optimized unmixing model of minimum logarithmic volume regularized NMF is introduced and solved based on the second-order approximation of function and alternating direction method of multipliers (SO-MVC-NMF). Then, the parallel algorithm for optimized MVC-NMF (PO-MVC-NMF) is proposed based on the CPU–GPU heterogeneous platform, taking advantage of the parallel processing capabilities of GPUs and logic control abilities of CPUs. Experimental results based on both simulated and real hyperspectral images indicate that the proposed algorithm is more accurate and robust than the traditional PG-MVC-NMF, and the total speedup of PO-MVC-NMF compared to PG-MVC-NMF is over 50 times.     

A novel FPGA-based architecture for the estimation of the virtual dimensionality in remotely sensed hyperspectral images

A challenging problem in spectral unmixing is how to determine the number of endmembers in a given scene. One of the most popular ways to determine the number of endmembers is by estimating the virtual dimensionality (VD) of the hyperspectral image using the well-known Harsanyi–Farrand–Chang (HFC) method. Due to the complexity and high dimensionality of hyperspectral scenes, this task is computationally expensive. Reconfigurable field-programmable gate arrays (FPGAs) are promising platforms that allow hardware/software codesign and the potential to provide powerful onboard computing capabilities and flexibility at the same time. In this paper, we present the first FPGA design for the HFC-VD algorithm. The proposed method has been implemented on a Virtex-7 XC7VX690T FPGA and tested using real hyperspectral data collected by NASA’s Airborne Visible Infra-Red Imaging Spectrometer over the Cuprite mining district in Nevada and the World Trade Center in New York. Experimental results demonstrate that our hardware version of the HFC-VD algorithm can significantly outperform an equivalent software version, which makes our reconfigurable system appealing for onboard hyperspectral data processing. Most important, our implementation exhibits real-time performance with regard to the time that the hyperspectral instrument takes to collect the image data.     

Hyperspectral unmixing employing l1−l2 sparsity and total variation regularization

ABSTRACT

Hyperspectral unmixing is essential for image analysis and quantitative applications. To further improve the accuracy of hyperspectral unmixing, we propose a novel linear hyperspectral unmixing method based on l₁?l₂ sparsity and total variation (TV) regularization. First, the enhanced sparsity based on the l₁?l₂ norm is explored to depict the intrinsic sparse characteristic of the fractional abundances in a sparse regression unmixing model because the l₁?l₂ norm promotes stronger sparsity than the l₁ norm. Then, TV is minimized to enforce the spatial smoothness by considering the spatial correlation between neighbouring pixels. Finally, the extended alternating direction method of multipliers (ADMM) is utilized to solve the proposed model. Experimental results on simulated and real hyperspectral datasets show that the proposed method outperforms several state-of-the-art unmixing methods.     

一种用于线性光谱解混算法验证的模拟数据生成方法

线性光谱解混已成为一种通用的光谱解混方法并已发展出大量算法,对这些算法进行客观评价,是该算法得到推广应用的重要基础。由于实测数据获取困难且花费很大,大多数研究中广泛采用模拟数据进行算法验证。针对目前常用的基于Dirichlet分布的模拟方法在实际应用中遇到的问题,结合实验分析了Dirichlet分布的参数设置对模拟结果的影响,进一步结合高光谱数据在其特征空间中的单形体几何特征,探讨了实际应用中参数取值受到的限制,并通过分析Dirichlet分布概率密度函数值的空间分布特征,提出参数的合适取值范围为(0,1.5)。     

Real-time anomaly detection in hyperspectral images using multivariate normal mixture models and GPU processing

Hyperspectral imaging, which records a detailed spectrum of light arriving in each pixel, has many potential uses in remote sensing as well as other application areas. Practical applications will typically require real-time processing of large data volumes recorded by a hyperspectral imager. This paper investigates the use of graphics processing units (GPU) for such real-time processing. In particular, the paper studies a hyperspectral anomaly detection algorithm based on normal mixture modelling of the background spectral distribution, a computationally demanding task relevant to military target detection and numerous other applications. The algorithm parts are analysed with respect to complexity and potential for parallellization. The computationally dominating parts are implemented on an Nvidia GeForce 8800 GPU using the Compute Unified Device Architecture programming interface. GPU computing performance is compared to a multi-core central processing unit implementation. Overall, the GPU implementation runs significantly faster, particularly for highly data-parallelizable and arithmetically intensive algorithm parts. For the parts related to covariance computation, the speed gain is less pronounced, probably due to a smaller ratio of arithmetic to memory access. Detection results on an actual data set demonstrate that the total speedup provided by the GPU is sufficient to enable real-time anomaly detection with normal mixture models even for an airborne hyperspectral imager with high spatial and spectral resolution.     

Unmixing-based content retrieval system for remotely sensed hyperspectral imagery on GPUs

This paper presents a new unmixing-based retrieval system for remotely sensed hyperspectral imagery. The need for this kind of system is justified by the exponential growth in the volume and number of remotely sensed data sets from the surface of the Earth. This is particularly the case for hyperspectral images, which comprise hundreds of spectral bands at different (almost contiguous) wavelength channels. To deal with the high computational cost of extracting the spectral information needed to catalog new hyperspectral images in our system, we resort to efficient implementations of spectral unmixing algorithms on commodity graphics processing units (GPUs). Spectral unmixing is a very popular approach for interpreting hyperspectral data with sub-pixel precision. This paper particularly focuses on the design of the proposed framework as a web service, as well as on the efficient implementation of the system on GPUs. In addition, we present a comparison of spectral unmixing algorithms available in the system on both CPU and GPU architectures.     

Hyperspectral-cube-based mobile face recognition: A comprehensive review

With the hyperspectral sensor technology evolving and becoming more cost-effective, hyperspectral imaging offers new opportunities for robust face recognition. Hyperspectral face cubes contain much more spectral information than face images from common RGB color cameras. Hyperspectral face recognition is robust to the impacts, such as illumination, pose, occlusion, and spoofing, which can heavily avoid the limitations of the visible-image-based face recognition.In this paper, we summarize the spectrum properties of hyperspectral face cubes and survey the hyperspectral face recognition methods in the literature. We categorize them into major groups for better understanding. We overview the existing hyperspectral face datasets, and establish our own dataset. We also discuss efficient neural networks used for mobile face recognition and conduct experiments on mobile hyperspectral face recognition. Results show that under harsh conditions like large illumination changing and pose variation, hyperspectral-cube-based methods have higher recognition accuracy than visible-image-based methods. Finally, we deliver insightful discussions and prospects for future works on mobile hyperspectral face recognition.     

Spatial-Spectral Preprocessing based on Nonnegative Matrix Factorization to Unmix Hyperspectral Data

Non-negative Matrix Factorization (NMF)method of blind spectral unmixing can obtain the spectrum and abundance of the endmember by synchronous optimization,without supervising the selection of endmember.Therefore,NMF has been developed rapidly in the application of hyperspectral unmixing.However,traditional blind spectral unmixing NMF method tends to fall into the local optimum and it is difficult to obtain a stable optimal solution.In this paper,we propose an improved Non-negative Matrix Factorization (NMF)method based on Spatial\|Spectal Preprocessing for spectral unmixing of hyperspectral data (SSPP-NMF).First,the SSPP algorithm is used to combine spatial and spectral information to select reasonable and effective dataset.Then,the NMF algorithm is used to unmix this dataset to obtain the final optimized endmember spectrum.Finally,the Non\|Negative Least Squares (NNLS)method is used to obtain the final abundance of the whole study area.The validity and applicability of the proposed method were analyzed based on a set of synthetic hyperspectral data and real hyperspectral images;and then the results were compared with that from three algorithms including the existing NMF algorithm,MVC\|NMF algorithm and ATGP-NMF algorithm.Results show that compared with ATGP-NMF and MVC-NMF,the SSPP algorithm can effectively suppress the influence of noise,significantly improve the performance of the NMF method of blind spectral unmixing algorithm.     

Efficient sparse unmixing analysis for hyperspectral imagery based on random projection

Hyperspectral imagery including rich spectral information could be applied to detect and identify objects at a distance. In this paper, we concentrate on the surface material identification of interested objects within the domain of space object identification (SOI) and geological survey. One of the approaches is the unmixing analysis that identifies the components (called endmembers) in each pixel and estimates their corresponding fractional abundances, and then, we could obtain the space distributions of substances. To solve this problem, we present an approach in a semi-supervised fashion, by assuming that the measured spectrum is expressed in the form of linear combination of a number of pure spectral signatures in a spectral library and the fractional abundances are their weights. Thus, the abundances are sparse and we propose a sparse regression model to realize the sparse unmixing analysis. We apply random projection technique to accelerate the sparse unmixing process and use split Bregman iteration to optimize the objective function. Our algorithm is tested and compared with other classic algorithms by using simulated hyperspectral images and a real-world image.     

A novel l 1/2 sparse regression method for hyperspectral unmixing

Hyperspectral unmixing (HU) is a popular tool in remotely sensed hyperspectral data interpretation, and it is used to estimate the number of reference spectra (end-members), their spectral signatures, and their fractional abundances. However, it can also be assumed that the observed image signatures can be expressed in the form of linear combinations of a large number of pure spectral signatures known in advance (e.g. spectra collected on the ground by a field spectro-radiometer, called a spectral library). Under this assumption, the solution of the fractional abundances of each spectrum can be seen as sparse, and the HU problem can be modelled as a constrained sparse regression (CSR) problem used to compute the fractional abundances in a sparse (i.e. with a small number of terms) linear mixture of spectra, selected from large libraries. In this article, we use the l _1/2 regularizer with the properties of unbiasedness and sparsity to enforce the sparsity of the fractional abundances instead of the l ₀ and l ₁ regularizers in CSR unmixing models, as the l _1/2 regularizer is much easier to be solved than the l ₀ regularizer and has stronger sparsity than the l ₁ regularizer (Xu et al. 2010). A reweighted iterative algorithm is introduced to convert the l _1/2 problem into the l ₁ problem; we then use the Split Bregman iterative algorithm to solve this reweighted l ₁ problem by a linear transformation. The experiments on simulated and real data both show that the l _1/2 regularized sparse regression method is effective and accurate on linear hyperspectral unmixing.     

基于Hessian图正则稀疏NMF的高光谱解混

基于非负矩阵分解(Nonnegative Matrix Factorization, NMF)的高光谱解混(Hyperspectral Unmixing,HU)方法引起了大家的关注,因为可以将一个非负高光谱图像(Hyperspectral Imagery, HSI)数据矩阵分解为两个非负矩阵的乘积,分别对应于端元矩阵和丰度系数矩阵。目前,图约束的NMF算法已经被证明对高光谱解混是有效的,因为它们可以捕获HSI的几何特性。为了挖掘数据在混合过程中的几何结构和稀疏性,提出了一种稀疏的Hessian图正则化NMF(SHGNMF)算法。SHGNMF算法是将丰度矩阵的L1/2正则化器和Hessian图正则化项都添加到每个NMF模型中,同时采用乘法更新规则。最后用模拟数据和真实数据进行实验,验证了所提出的SHGNMF算法相对于其他NMF算法的优越性。     

On Endmember Identification in Hyperspectral Images Without Pure Pixels: A Comparison of Algorithms

Hyperspectral imaging is an active area of research in Earth and planetary observation. One of the most important techniques for analyzing hyperspectral images is spectral unmixing, in which mixed pixels (resulting from insufficient spatial resolution of the imaging sensor) are decomposed into a collection of spectrally pure constituent spectra, called endmembers weighted by their correspondent fractions, or abundances. Over the last years, several algorithms have been developed for automatic endmember extraction. Many of them assume that the images contain at least one pure spectral signature for each distinct material. However, this assumption is usually not valid due to spatial resolution, mixing phenomena, and other considerations. A?recent trend in the hyperspectral imaging community is to design endmember identification algorithms which do not assume the presence of pure pixels. Despite the proliferation of this kind of algorithms, many of which are based on minimum enclosing simplex concepts, a rigorous quantitative and comparative assessment is not yet available. In this paper, we provide a comparative analysis of endmember extraction algorithms without the pure pixel assumption. In our experiments we use synthetic hyperspectral data sets (constructed using fractals) and real hyperspectral scenes collected by NASA’s Jet Propulsion Laboratory.     

Further results on dissimilarity spaces for hyperspectral images RF-CBIR

Content-Based Image Retrieval (CBIR) systems are powerful search tools in image databases that have been little applied to hyperspectral images. Relevance feedback (RF) is an iterative process that uses machine learning techniques and user’s feedback to improve the CBIR systems performance. We pursued to expand previous research in hyperspectral CBIR systems built on dissimilarity functions defined either on spectral and spatial features extracted by spectral unmixing techniques, or on dictionaries extracted by dictionary-based compressors. These dissimilarity functions were not suitable for direct application in common machine learning techniques. We propose to use a RF general approach based on dissimilarity spaces which is more appropriate for the application of machine learning algorithms to the hyperspectral RF-CBIR. We validate the proposed RF method for hyperspectral CBIR systems over a real hyperspectral dataset.     

基于光谱距离聚类的高光谱图像解混算法

为了解决实际高光谱解混（HU）中噪声对解混精度的影响和光谱、空间信息利用不足的问题,提出了一种改进的基于光谱距离聚类的群稀疏非负矩阵分解的解混算法。首先,引入了基于最小误差的高光谱信号辨识算法（Hysime）,通过计算特征值的方式估计信号矩阵和噪声矩阵;然后,提出了一种简单的基于光谱距离的聚类算法,对多个波段生成的光谱反射率距离值小于某一值的相邻像元进行合并聚类生成空间群结构;最后,在生成的群结构基础上进行稀疏化非负矩阵分解。实验分析表明,对于模拟数据和实际数据而言,该算法都比传统算法产生更小的均方根误差（RMSE）和光谱角距离（SAD）,能够产生优于同类算法的解混效果。