Ruyi Feng

Non-Local Sparse Unmixing for Hyperspectral Remote Sensing Imagery

Sparse unmixing is a promising approach that acts as a semi-supervised unmixing strategy by assuming that the observed image signatures can be expressed in the form of linear combinations of a number of pure spectral signatures that are known in advance. However, conventional sparse unmixing involves finding the optimal subset of signatures for the observed data in a very large standard spectral library, without considering the spatial information. In this paper, a new sparse unmixing algorithm based on non-local means, namely non-local sparse unmixing (NLSU), is proposed to perform the unmixing task for hyperspectral remote sensing imagery. In NLSU, the non-local means method, as a regularizer for sparse unmixing, is used to exploit the similar patterns and structures in the abundance image. The NLSU algorithm based on the sparse spectral unmixing model can improve the spectral unmixing accuracy by incorporating the non-local spatial information by means of a weighting average for all the pixels in the abundance image. Five experiments with three simulated and two real hyperspectral images were performed to evaluate the performance of the proposed algorithm in comparison to the previous sparse unmixing methods: sparse unmixing via variable splitting and augmented Lagrangian (SUnSAL) and sparse unmixing via variable splitting augmented Lagrangian and total variation (SUnSAL-TV). The experimental results demonstrate that NLSU outperforms the other algorithms, with a better spectral unmixing accuracy, and is an effective spectral unmixing algorithm for hyperspectral remote sensing imagery.

Adaptive Spatial Regularization Sparse Unmixing Strategy Based on Joint MAP for Hyperspectral Remote Sensing Imagery

Sparse unmixing, as a recently developed spectral unmixing approach, has been successfully applied based on the assumption that the observed image signatures can be expressed in an efficient linear sparse regression with the potentially very large endmember spectral library. To improve the unmixing accuracy, spatial information has been incorporated in the sparse unmixing formulation by adding an appropriate spatial regularization for the hyperspectral remote sensing imagery. However, for the traditional spatial regularization sparse unmixing (SRSU) algorithms, it is a difficult task to set appropriate user-defined regularization parameters in real applications, and this often has a high computational cost. To overcome the difficulty of the regularization parameter selection, the adaptive spatial regularization sparse unmixing (ASRSU) strategy based on the joint maximum a posteriori (JMAP) estimation technique is proposed in this paper. In ASRSU, the SRSU problem is formulated in the framework of JMAP with an appropriate prior model. ASRSU considers the regularization parameters and the abundances jointly by an alternating iterative process, and the relationships between the regularization parameters and the abundances are obtained from the JMAP model. Based on the ASRSU strategy, two ASRSU algorithms are presented: the adaptive total variation spatial regularization sparse unmixing algorithm and the adaptive nonlocal means filtering sparse unmixing algorithm. The experimental results demonstrate that the two proposed ASRSU algorithms based on JMAP can adaptively obtain optimal or near-optimal regularization parameters for the three simulated datasets and the two real hyperspectral remote sensing images.

Nonlocal Total Variation Subpixel Mapping for Hyperspectral Remote Sensing Imagery

Subpixel mapping is a method of enhancing the spatial resolution of images, which involves dividing a mixed pixel into subpixels and assigning each subpixel to a definite land-cover class. Traditionally, subpixel mapping is based on the assumption of spatial dependence, and the spatial correlation information among pixels and subpixels is considered in the prediction of the spatial locations of land-cover classes within the mixed pixels. In this paper, a novel subpixel mapping method for hyperspectral remote sensing imagery based on a nonlocal method, namely nonlocal total variation subpixel mapping (NLTVSM), is proposed to use the nonlocal self-similarity prior to improve the performance of the subpixel mapping task. Differing from the existing spatial regularization subpixel mapping technique, in NLTVSM, the nonlocal total variation is used as a spatial regularizer to exploit the similar patterns and structures in the image. In this way, the proposed method can obtain an optimal subpixel mapping result and accuracy by considering the nonlocal spatial information. Compared with the classical and state-of-the-art subpixel mapping approaches, the experimental results using a simulated hyperspectral image, two synthetic hyperspectral remote sensing images, and a real hyperspectral image confirm that the proposed algorithm can obtain better results in both visual and quantitative evaluations.

Adaptive Sparse Subpixel Mapping With a Total Variation Model for Remote Sensing Imagery

Subpixel mapping, which is a promising technique based on the assumption of spatial dependence, enhances the spatial resolution of images by dividing a mixed pixel into several subpixels and assigning each subpixel to a single land-cover class. The traditional subpixel mapping methods usually utilize the fractional abundance images obtained by a spectral unmixing technique as input and consider the spatial correlation information among pixels and subpixels. However, most of these algorithms treat subpixels separately and locally while ignoring the rationality of global patterns. In this paper, a novel subpixel mapping model based on sparse representation theory, namely, adaptive sparse subpixel mapping with a total variation model (ASSM-TV), is proposed to explore the possible spatial distribution patterns of subpixels by considering these subpixels as an integral patch. In this way, the proposed method can obtain the optimal subpixel mapping result by determining the most appropriate subpixel spatial pattern. However, the number of possible spatial configurations of subpixels can increase sharply with large-scale factors, and therefore, in ASSM-TV, the subpixel mapping is considered as a sparse representation problem. A preconstructed discrete cosine transform dictionary, which consists of piecewise smooth subpixel patches and textured patches, is utilized to express the original subpixel mapping observation in a sparse representation pattern. The total variation prior model is designed as a spatial regularization constraint to characterize the relationship between a subpixel and its neighboring subpixels. In addition, a joint maximum a posteriori model is proposed to adaptively select the regularization parameters. Compared with the other traditional and state-of-the-art subpixel mapping approaches, the experimental results using a simulated image, three synthetic hyperspectral remote sensing images, and two real remote sensing images demonstrate that the proposed algorithm can obtain better results, in both visual and quantitative evaluations.

An Improved Nonlocal Sparse Unmixing Algorithm for Hyperspectral Imagery

As a result of the spatial consideration of the imagery, spatial sparse unmixing (SU) can improve the unmixing accuracy for hyperspectral imagery, based on the application of a spectral library and sparse representation. To better utilize the spatial information, spatial SU methods such as SU via variable splitting augmented Lagrangian and total variation (SUnSAL-TV) and nonlocal SU (NLSU) have been proposed. However, the spatial information considered in these algorithms comes from the estimated abundance maps, which will change along with the iterations. As the spatial correlations of the imagery are fixed and certain, the spatial relationships obtained from the variable abundances are not reliable during the process of optimization. To obtain more precise and fixed spatial relationships, an improved weight calculation NLSU (I-NLSU) algorithm is proposed in this letter by changing the spatial information acquisition source from the variable estimated abundances to the original hyperspectral imagery. A noise-adjusted principal component analysis strategy is also applied for the feature extraction in the proposed algorithm, and the obtained principal components are the foundation of the spatial relationships. The experimental results of both simulated and real hyperspectral data sets indicate that the proposed I-NLSU algorithm outperforms the previous spatial SU methods.

Spatial-Temporal Sub-Pixel Mapping Based on Swarm Intelligence Theory

In the past decades, sub-pixel mapping algorithms have been extensively developed due to the large number of different applications. However, most of the sub-pixel mapping algorithms are based on single-temporal images, and the results are usually compromised without auxiliary information due to the ill-posed problem of sub-pixel mapping. In this paper, a novel spatial-temporal sub-pixel mapping algorithm based on swarm intelligence theory is proposed for multitemporal remote sensing imagery. Swarm intelligence theory involves clonal selection sub-pixel mapping (CSSM), which evolves the solution by emulating the biological advantage of the human immune system, and differential evolution sub-pixel mapping (DESM), which optimizes the solution by intelligent operations and heuristic searching in the solution pool. In addition, considering the under-determined problem of sub-pixel mapping, the spatial-temporal sub-pixel mapping method is used to obtain the distribution information at a fine spatial resolution from the bitemporal image pair, which exactly regularizes the ill-posed problem. Furthermore, the short-interval temporal information and the fine spatial distribution information within the bitemporal image pair can be integrated for further use, such as timely and detailed land-cover change detection (LCCD). To verify the validation of the swarm intelligence theory based spatial-temporal sub-pixel mapping algorithm, the proposed algorithm was compared with several traditional sub-pixel mapping algorithms, in both synthetic and real image experiments. The experimental results confirm that the proposed algorithm outperforms the traditional approaches, achieving a better sub-pixel mapping result both qualitatively and quantitatively, as well as improving the subsequent LCCD performance.

Rolling Guidance Based Scale-Aware Spatial Sparse Unmixing for Hyperspectral Remote Sensing Imagery

Spatial regularization based sparse unmixing has been attracted much attention and has achieved improved fractional abundance results. However, the traditional approach to spatial consideration can only suppress discrete wrong unmixing points and smooth an abundance map with low-contrast changes, and it has no concept of scale difference. As the different levels of structures and edges in remote sensing have different meanings and importance, to better extract the different levels of spatial details, rolling guidance based scale-aware spatial sparse unmixing (RGSU), is proposed in this paper to extract and recover the different levels important structures and details in the hyperspectral remote sensing image unmixing procedure. Differing from the existing spatial regularization based sparse unmixing approaches, the proposed method considers the different levels of edges by combining a Gaussian filter-like method to realize small-scale structure removal with a joint bilateral filtering process to account for the spatial domain and range domain correlations. The experimental results obtained with both simulated and real hyperspectral images show that the proposed method achieves a better performance and produces more accurate abundance maps, as well as higher quantitative results, when compared to the current state-of-the-art sparse unmixing algorithms

A unified sub-pixel mapping model integrating spectral unmixing for hyperspectral imagery

Traditional sub-pixel mapping methods were imposed on the fraction image which was generated with spectral unmixing techniques. Obviously, the capability of sub-pixel mapping was limited by the accuracy of the obtained fraction image. In this paper, a unified sub-pixel mapping model was proposed by integrating the spectral unmixing to implement on the low-resolution hyperspectral imagery directly. In this way, the sub-pixel mapping result can be obtained from the original hyperspectral imagery while not the fraction image. The proposed algorithm was tested on the synthetic and real hyperspectral images and experimental results demonstrate that the proposed approach outperform the other three traditional sub-pixel mapping algorithms which was based on the fraction image, and hence provide an effective option for improving the accuracy of sub-pixel mapping of hyperspectral imagery.

Differentiable sparse unmixing based on Bregman divergence for hyperspectral remote sensing imagery

Sparse unmixing has been successfully applied to hyperspectral remote sensing imagery based on the assumption that the observed image signatures can be expressed in a linear sparse regression with a large standard spectral library. Prior work for sparse unmixing usually utilizes L1 norm or Laplacian distribution to promote sparsity. Unfortunately, the L1 norm is not differentiable, which may lead to unstable results. In this paper, we adopt Bregman divergence for sparse unmixing, which is a differentiable, smoother prior. Based on the Maximum A Posterior (MAP) estimation, the proposed method has achieved sparse, stable and precise fractional abundances. The experimental results both simulated dataset and the real hyperspectral image demonstrate the effectiveness of the proposed differentiable sparse unmixing algorithm.

Complete dictionary online learning for sparse unmixing

Sparse unmixing has been successfully applied to hyperspectral remote sensing imagery, based on an available standard spectral library. However, as the number of hyperspectral remote sensors increases, more and more hyperspectral remote sensing images are requiring analysis without the use of a corresponding standard spectral library. To address this problem, sparse unmixing with a complete dictionary online self-learning technique is proposed in this paper. This paper focuses on complete dictionary, which can tackle the unmixing problem with exactly atoms needed in the dataset and online learning means to process the specific data, or the current single hyperspectral remote sensing imagery, at real time. The proposed method addresses the sparse unmixing problem by considering the physical meaning of atoms in the complete dictionary, as well as a non-negative constraint for the abundance. Compared with the classical dictionary learning approaches in sparse representation theory, the experiments with two simulated hyperspectral datasets and a real dataset confirmed the effectiveness of the proposed method.