Endmember extraction using the physics-based multi-mixture pixel model

Endmember extraction (EE) plays a crucial part in the hyperspectral unmixing (HU) process. To obtain satisfactory EE results, the EE can be considered as the multiobjective optimization problem to optimize the volume maximization (VM) and root-mean-square error (RMSE) simultaneously. However, it is often quite challenging to balance the conflict of these objectives. In order to tackle the challenges of multiobjective EE, we present a (μ + λ) multiobjective differential evolution algorithm ((μ + λ)-MODE) based on ranking multiple mutations. In the (μ + λ)-MODE algorithm, ranking multiple mutations are adopted to create the mutant vectors via the scaling factor pool to enhance the population diversity. Moreover, mutant vectors employ the binary crossover operator to generate the trial vectors through a crossover control parameter pool in (μ + λ)-MODE to take advantage of the good information of the population. In addition, (μ + λ)-MODE utilizes the fast nondominated sorting approach to sort the parent and trial vectors, and then selects the elitism offspring as the next population via the (μ + λ) selection strategy. Eventually, experimental comparative results in three real HSIs reveal that our proposed (μ + λ)-MODE is superior to other EE methods.

PDF HTML阅读 XML下载 导出引用 引用提醒 基于Hyperion的锡林郭勒草原光合植被、非光合植被覆盖度估算 DOI: 10.5846/stxb201308142075 作者: 作者单位: 中国科学院遥感与数字地球研究所,中国科学院遥感与数字地球研究所,中国科学院遥感与数字地球研究所 作者简介: 通讯作者: 中图分类号: 基金项目: 国家科技支撑计划(2011BAH23B04);国家科技重大专项(21-Y30B05-9001-13/15) Estimating fractional cover of photosynthetic vegetation and non-photosynthetic vegetation in the Xilingol steppe region with EO-1 hyperion data Author: Affiliation: Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences,Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences,Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:掌握草原生态系统光合植被覆盖度(fPV)与非光合植被覆盖度(fNPV)时空动态对了解干旱半干旱草原生态系统特征(覆盖状况、火灾负载、载畜量、干扰及恢复等)及进行科学、有效地草地资源管理具有重要的意义。选取锡林郭勒典型草原为试验区,以Hypeiron高光谱数据为数据源,利用NDVI-CAI三元线性混合模型对试验区fPV和fNPV的时空动态分布进行了估算,并对不同端元选择方法(最小包含端元特征法、纯净象元指数法和实测法)对估算结果的影响进行了比较分析。研究结果表明,NDVI-CAI三元线性混合模型是同时估测锡林郭勒草原fPV和fNPV的有效方法,且估算的fPV和fNPV的季节变化与牧草的物候发育特征相吻合。不同端元选择方法对估算精度具有一定的影响,其中基于最小包含端元特征法提取端元进行估算的精度最高,fPV估算的均方根误差RMSE=4.57,估算精度EA=91.2%;fNPV估算的RMSE=5.90,EA=67.91%(样本数N=52)。 Abstract:Quantitative estimation of the spatial and temporal dynamics of the fractional cover of photosynthetic vegetation (fPV) and non-photosynthetic vegetation (fNPV) in semi-arid grasslands is critical for understanding grassland conditions such as vegetation abundance, drought severity, fire fuel load, stocking rate, and disturbance events and recovery. It is also important for scientific grassland resource management. Over the past several decades, remote sensing has become an important tool for estimating the fractional cover of vegetation, which is a key descriptor of ecosystem function. However, most efforts have been devoted to the estimation of fPV rather than fNPV, although the latter is equally important, especially in arid and semi-arid ecosystems. This study describes a linear unmixing approach for estimating fPV and fNPV in the Xilingol steppe region with hyperspectral and field investigation data. Five Hyperion images acquired on April 4, May 20, July 27, August 30, and November 15 in 2012 and a field-measured spectral library were utilized to explore the spectral feature space of fPV and fNPV in order to validate the feasibility of a linear unmixing model. This model is based on two complementary spectral indices of vegetation that have been used in remote sensing analyses to discriminate green and dry vegetation from soils: the Normalized Difference Vegetation Index (NDVI) and the Cellulose Absorption Index (CAI). Different end-member extraction methods, including the Minimum-Volume Enclosing (MVE) method, the Pixel Purity Index (PPI) method, and a field measurement method, were adopted to retrieve the end-member values of photosynthetic vegetation, non-photosynthetic vegetation, and bare soil, respectively, from NDVI and CAI. Then, the influence of end-member extraction on the accuracy of the fPV and fNPV estimation was evaluated through comparison with field-measured fPV and fNPV values acquired from classifications performed on fisheye photos (N=52). Subsequently, the optimum unmixing strategy was utilized to retrieve the temporal dynamics of fPV and fNPV in a fenced area, where the grassland was not influenced by human activities, so that the usefulness of these fractional coverage indices could be validated by checking their consistency with the phenology of natural grassland. The result shows that the linear unmixing model based on NDVI and CAI was effective for estimating fPV and fNPV in the Xilingol steppe region. The NDVI-CAI feature space follows a triangular distribution, where the three vertexes represent photosynthetic vegetation, non-photosynthetic vegetation, and bare soil, meeting the essential requirements of the linear unmixing model. The estimation accuracy was different for the different end-member extraction methods. The MVE-based estimation had the highest accuracy, with estimated accuracy of 91.2% and 67.91% for fPV and fNPV, respectively, followed by the PPI-based estimation (91.0% and 59.5% for fPV and fNPV, respectively) and the field-measurement-based estimation (86.2% and 56.7% for fPV and fNPV, respectively). In general, the estimation accuracy was higher for fPV than fNPV, and the field-measured end-member performed worse than the image end-member, which was probably due to the inconsistency between the field-measured spec and the Hyperion spec. Additionally, the temporal dynamics of fPV and fNPV were confirmed to be consistent with the phenological seasonal change in natural grasslands. Therefore, the method proposed here can be used to monitor the temporal and spatial variations of fPV and fNPV in semi-arid grasslands. 参考文献 相似文献 引证文献

Abstract. An essential step in the characterization of surface materials using hyperspectral image analysis is image classification using endmembers. Spectral unmixing is the best method for hyperspectral image classification. This method assumes that the pixel-topixel variability in scene results from varying proportions of spectral endmembers. Spectral endmembers can be derived from the imagery or measurements in the laboratory or field. The primary objective of this paper was to assess the ability of extracted endmembers against some different solutions for extraction of endmembers for hyperspectral image classification. In this paper, we compared the Pixel Purity Index (PPI) and the Sequential Maximum Angle Convex Cone (SMACC) as two popular methods of endmember extraction with library and field spectral. We used spectral information divergence for detection desirable endmembers from field spectral. For accuracy assessment of spectral mixture analysis and production of endmember abundance images for each of methods, the linear spectral unmixing algorithm is used. After a comparison between the results of these methods, it has been verified that field spectral have a better classification result in comparing with other endmember extraction methods. Also, the PPI has reliable results as an automatic endmember extraction method in comparing.

The spatial resolution of hyperspectral data is low, so there are a large number of mixed pixels, which is also one of the main reasons that reduce the accuracy of hyperspectral image target classification. Hyperspectral unmixing is an important subject in the field of remote sensing. Hyperspectral unmixing generally consists of three steps: reduction, endmember extraction and inversion. As one of the key steps of hyperspectral unmixing, efficient and rapid endmember extraction is an important object in hyperspectral remote sensing. In this paper, the endmember extraction of hyperspectral data is implemented based on PCA and a new SGA algorithm, which solves the dimension limitation of traditional SGA algorithm and the new SGA algorithm without data redundancy caused by data dimensionality reduction.

Endmember extraction is an important task for hyperspectral analysis; the accurate identification of endmembers enables efficient spectral unmixing and classification. In the paper, a new endmember extraction algorithm based on a modified MSS approach with LP error as initial spectrum selection algorithm, and OPD measure as similarity is proposed. The endmembers extracted by modified MSS are more similar than that of MSS algorithm; from the experiments results, it has proved that our proposed method outperforms the existed MSS and N-FINDR algorithms.

Spectral unmixing is one of the most important techniques for analyzing hyperspectral images. Many of the hyperspectral unmixing algorithms developed in recent years have been developed under an assumption that pure pixels exist, and some algorithms, such as N-finder algorithm (N-FINDR) and vertex component analysis (VCA), can only search data points in this case. However, the pure-pixel assumption may be seriously violated for highly mixed data. Whether a pure pixel exists or not, the endmember extraction can be regarded as an optimization problem. In this paper, we incorporate the linear mixture model (LMM) and particle swarm optimization (PSO) to develop LMM constrained PSO (LMMC-PSO) for endmember extraction from highly mixed data. The main contribution of the proposed method is that we redefine the particle motion rules. Each particle in LMMC-PSO moves in the search space according to the LMM, rather than with a velocity. The LMM is one kind of relationship between endmembers and mixed pixels, which can help guide efforts to build a path from mixed pixels to endmembers in PSO. The proposed algorithm was tested and evaluated with both synthetic and real hyperspectral data sets. The experimental results indicated that the proposed method obtains better results with highly mixed data than the algorithms of VCA, minimum volume constrained nonnegative matrix factorization, minimum volume simplex analysis (MVSA), robust MVSA, the convex analysis-based minimum volume enclosing simplex, and simplex identification via variable splitting and augmented Lagrangian.

The endmember extraction is a challenging problem in spectral unmixing (SU) of a mixed pixel in hyperspectral imagery. There are plenty of attempts to solve the endmember extraction problem. Still, the pure pixel assumption-based algorithms have probably been used most in solving the endmember extraction of SU due to the light computational burden. These pure pixel assumption-based algorithms usually follow one of the criteria: (1) Maximum simplex volume or (2) Extreme projection on a subspace. We propose a novel integrated framework that uses both the criteria mentioned above and the proposed one is referred to as the Convexity-based Pure Index (CPI) algorithm. The CPI generates a fixed number of convex sets based on the number of available bands in the hyperspectral image. The algorithm defines the purity score based on the availability of pixels in the convex sets for the two-band data. The CPI has been compared with contemporary algorithms such as Automatic Target Generation Process (ATGP), Vertex Component Analysis (VCA), Pixel Purity Index (PPI), Successive Volume MAXimization (SVMAX), Alternating Volume MAXimization (AVMAX), TRIple-P: P-norm based Pure Pixel identification (TRIP), Successive Decoupled Volume Max–Min (SDVMM), Negative ABundance-Oriented (NABO), and Entropy-based Convex Set Optimization (ECSO). The metrics, Spectral Angle Distance (SAD) and Spectral Information Divergence (SID) used in the comparison were improved up to 5.9% and 9%, respectively. The CPI outperforms prevailing algorithms on real benchmark data and new AVIRIS-NG data. The robustness of the CPI is also tested for various noisy synthetic data. The efficacy of the proposed algorithm is also tested by using qualitative analysis by visualizing the spectra comparison, and abundance maps for all real data.

Endmember extraction is the process of selecting a collection of pure signature spectra of the materials present in a hyperspectral scene. Most of the spectral-based endmember extraction methods relay on the ability to discriminate between pixels based on their spectral characteristics and the assumption that pure pixels exist in the image. In some cases, though pure pixels are available inside image, spectral complexity of the image (e.g. low spectral contrast) makes it difficult to extract the best endmember candidates from hyperspectral imagery. This paper investigates the use of statistical convex partitioning (SCP) as a preprocessing tool for endmember extraction. The SCP method comprises three main steps: 1) partitioning input hyperspectral data set into partitions or so called convex regions using K-mean clustering algorithm; 2) finding the best candidate endmembers for each convex region; and, 3) comparing and listing of candidate endmembers extracted from each partition in order of spectral similarity. In order to demonstrate the performance of the proposed method, the sequential maximum angle convex cone (SMACC) algorithm was used to extract endmembers of each partition and the results were compared to pixel purity index (PPI). Optimum number of convex regions as well as the impact of different dimensionality reduction transforms, principal component analysis (PCA), minimum noise fraction (MNF), and independent component analysis (ICA) were also investigated. Experimental results on both simulated and real AVIRIS hyperspectral image indicate that SCP is an effective method to preprocess hyperspectral data spectrally and extract low contrast and similar endmembers effectively.

Endmember extraction is a key step in hyperspectral unmixing. This paper proposes a new endmember extraction framework based on the swarm intelligence algorithm. We adopt a discrete structure because pixels exist within a discrete frame. Traditional swarm intelligence algorithms produce stacked solutions based on similar endmembers in the same class. We introduce a “distance” factor into the objective function to limit the number of endmembers per class. We then propose three endmember extraction methods based on the artificial bee colony (ABC), ant colony optimization (ACO) and particle swarm optimization (PSO) algorithms. Experiments with both simulated and actual hyperspectral image data indicate that the proposed framework can significantly improve the accuracy of endmember extraction.

An investigation has been undertaken of the effects of selective grain sorting on the ability of factor analyses to identify source end-members within heavy-mineral assemblages. Q-mode factor analysis of samples randomly collected from the beach at Otter Rock, Oregon, yielded two factors; one is dominated by augite, hornblende and hypersthene, and the second consists of garnet plus zircon. These factors correspond closely to selective-sorting patterns of minerals on this beach determined from a series of samples along a beach profile collected during a period of beach-face erosion. Factor analysis of those profile samples showed that the garnet and zircon are associated with the high-density opaques which tend to concentrate at the landward limit of wave run-up, while the lower densit augite, etc., are transported to the outer surf zone. Factor analyses were also performed on a synthetic data set which simulates the along-coast mixing of mineral assemblages from four spatially distinct sources. Analyses involved pure mixtures of source end-members, mixtures where random errors were introduced to simulate counting uncertainties, and mixtures of the end-members where systematic changes were added to simulate the effects of local grain sorting. The results indicate that sorting can significantly affect the results from factor analyses, with new factors introduced and with random irregularities produced in the spatial patterns of the factors.

Hyperspectral image unmixing is an important part of hyperspectral data analysis. The mixed pixel decomposition consists of two steps, endmember (the unique signatures of pure ground components) extraction and abundance (the proportion of each endmember in each pixel) estimation. Recently, a Discrete Particle Swarm Optimization algorithm (DPSO) was proposed for accurately extract endmembers with high optimal performance. However, the DPSO algorithm shows very high computational complexity, which makes the endmember extraction procedure very time consuming for hyperspectral image unmixing. Thus, in this paper, the DPSO endmember extraction algorithm was parallelized, implemented on the CUDA (GPU K20) platform, and evaluated by real hyperspectral remote sensing data. The experimental results show that with increasing the number of particles the parallelized version obtained much higher computing efficiency while maintain the same endmember exaction accuracy.

Spectral unmixing is an important problem for remotely sensed hyperspectral data exploitation. Automatic spectral unmixing can be viewed as a three-stage problem, where the first stage is subspace identification, the next one is endmember extraction, and the final one is abundance estimation. In this sequence, endmember extraction is the most challenging problem. Many researchers have attempted to extract endmembers from hyperspectral images using spectral information only. However, it is well known that the inclusion of spatial information can improve the endmember extraction task. In this article, we introduce a new endmember extraction algorithm that exploits both spectral and spatial information. A main innovation of the proposed algorithm is that spatial information is exploited using entropy, while spectral information is exploited using convex set optimization. In the literature, none of the spatial–spectral algorithms has used entropy as spatial information. The inclusion of this entropy-based spatial information improves the accuracy of the endmember extraction process. The results obtained by the proposed algorithm are compared (using a variety of metrics) with those obtained by other state-of-the-art methods, using both synthetic and real datasets. Our experimental results demonstrate that the proposed algorithm outperforms many available algorithms.

Abstract. Endmember extraction integrated with spatial information has been concerned on some research recently. In this paper we studies an improved endmember extraction method with spatial preprocessing module which use watershed with normalized cuts to avoid over- segmentation and produce accurate results from spectral mixture analysis. The spatial-spectral endmember extraction method which used the advantages of image segmentation generates the preliminary results and provides important knowledge for future research.

Introduced in this paper is the utilization of support vector machines (SVMs) to semiautomatically perform endmember extraction from hyperspectral data. The strengths of SVM are exploited to provide a fast and accurate calculated representation of high-dimensional data sets that may consist of multiple distributions. Once this representation is computed, the number of distributions can be determined without prior knowledge. For each distribution, an optimal transform can be determined that preserves informational content while reducing the data dimensionality and, hence, the computational cost. Finally, endmember extraction for the whole data set is accomplished. Results indicate that this SVM-based endmember extraction algorithm has the capability of semiautonomously determining endmembers from multiple clusters with computational speed and accuracy while maintaining a robust tolerance to noise.

Hyperspectral unmixing (HU) has become an important technique in exploiting hyperspectral data since it decomposes a mixed pixel into a collection of endmembers weighted by fractional abundances. The endmembers of a hyperspectral image (HSI) are more likely to be generated by independent sources and be mixed in a macroscopic degree before arriving at the sensor element of the imaging spectrometer as mixed spectra. Over the past few decades, many attempts have focused on imposing auxiliary regularizes on the conventional nonnegative matrix factorization (NMF) framework in order to effectively unmix these mixed spectra. As a promising step toward finding an optimum regularizer to extract endmembers, this paper presents a novel blind HU algorithm, referred to as Kurtosis-based Smooth Nonnegative Matrix Factorization (KbSNMF) which incorporates a novel regularizer based on the statistical independence of the probability density functions of endmember spectra. Imposing this regularizer on the conventional NMF framework promotes the extraction of independent endmembers while further enhancing the parts-based representation of data. Experiments conducted on diverse synthetic HSI datasets (with numerous numbers of endmembers, spectral bands, pixels, and noise levels) and three standard real HSI datasets demonstrate the validity of the proposed KbSNMF algorithm compared to several stateof- the-art NMF-based HU baselines. The proposed algorithm exhibits superior performance especially in terms of extracting endmember spectra from hyperspectral data; therefore, it could uplift the performance of recent deep learning HU methods which utilize the endmember spectra as supervisory input data for abundance extraction.