4 December 2019 in IEEE Geoscience and Remote Sensing Letters
Unmixing is a key but difficult issue in hyperspectral image (HSI) processing, and many unmixing methods have been proposed. However, an effective introduction of the spatial context in unmixing remains a challenge but is a necessary condition for many real scene applications. In this letter, a new nonnegative matrix factorization (NMF) method that combines nonlocal spatial information with spatial group sparsity (NLNMF) is proposed. Each superpixel generated by the simple linear iterative clustering (SLIC) segmentation method was used as a group. The search region of the nonlocal means method was adaptively set using a superpixel label from each spectrum to find the similar spectra to reestimate the reference spectrum. Additionally, the sparsity of spectra in the same superpixel was considered to be the same. Experiment results for synthetic and real HSI showed that the proposed method not only can more accurately estimate the endmember and abundance compared with other unmixing methods but also has good performance regarding antinoise.
6 February 2020 in IEEE Transactions on Geoscience and Remote Sensing
Although efficient hyperspectral image (HSI) denoising relies on complete and accurate description and modeling the spatial-spectral signal in HSI, the current approaches do not fully account for key characteristics of HSI, i.e., the mixed spectra effect, the spatial nonstationarity effect, and noise variance heterogeneity effect. To address this issue, this article presents a linear spectral mixture model with nonlocal means constraint (LSMM-NLMC), with the following advantages. First, LSMM-NLMC can effectively learn the signal in mixed pixels in HSI by estimating clean endmembers and abundances for image restoration. Second, LSMM-NLMC can efficiently address nonstationary spatial correlation effect by imposing NLMC on the latent scene signal. Last, LSMM-NLMC provides accurate noise characterization by accounting for noise variance heterogeneity effect using a band-dependent noise model and a band-weighted Mahalanobis distance for similarity measurement. A novel optimization method based on the expectation-maximization (EM) algorithm and the purified means approach is used to efficiently solve the resulting maximum a posterior (MAP) problem. The experiments on both simulated and real HSI data sets demonstrate that the visual quality and denoising accuracy are significantly improved by the proposed LSMM-NLMC compared with previous methods.
31 May 2024 in IEEE Geoscience and Remote Sensing Letters
Large-scale hyperspectral image (HSI) clustering is a challenging and attention-grabbing problem. Most existing methods are difficult to solve high dimensionality and computational complexity in HSI. In this paper, an innovative algorithm, termed superpixel-based low-rank constrained bipartite graph learning (SLCBG) is introduced, to efficiently achieve large-scale HSI clustering. Specifically, to solve the problem of massive data and high computational memory of large-scale HSI, superpixel segmentation is adopted to obtain superpixels in this paper. The spectral distance is measured using Mahalanobis distance to better obtain the overall distribution features of HSI. Secondly, k -means is used to generate anchors based on the superpixel data, and anchor graph is constructed for each view to better represent the whole HSI. Finally, tensor Schatten- p norm and nuclear norm minimization constraints are introduced to search for the low-rank structure graphs within and between views in HSI; thus, obtaining a consensus graph with clear connectivity components for realizing clustering. Experimental results on three HSI showed the superiority of SLCBG with OA of 49.20%, 75.48% and 68.59%, respectively.
18 July 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Although a graph-based semisupervised learning (SSL) approach can utilize limited numbers of labeled samples for hyperspectral image (HSI) classification, it is difficult to use the large amount of pixels in an HSI to construct a large-scale graph. In this article, we therefore propose a superpixel-based graph model for HSI classification, using anchor graph regularization to improve the extraction of local and nonlocal spatial information. To avoid the large-scale graph problem, the superpixel-based graph model constructs a scalable anchor graph using a small number of anchor points for graph-based SSL. The proposed approach consists of three key components: First, local and nonlocal features are extracted from the principal components of an HSI using the locally grouped order pattern and the nonlocal binary pattern approaches. Second, the extracted features are combined with the original spectral information and used as input to an improved simple line iteration clustering method to obtain superpixels, the centers of which are used as anchors in the anchor graph approach. Third, we use superpixel-based graph regularization to model the global information among the superpixels for better predictions of the label of each unlabeled pixel sample. Experimental results demonstrate that the proposed approach outperforms other state-of-the-art semisupervised HSI classification approaches for cases with a limited quantity of labeled samples.