HYPERSPECTRAL IMAGE KERNEL SPARSE SUBSPACE CLUSTERING WITH SPATIAL MAX POOLING OPERATION

In this paper, we present a kernel sparse subspace clustering with spatial max pooling operation (KSSC-SMP) algorithm for hyperspectral remote sensing imagery. Firstly, the feature points are mapped from the original space into a higher dimensional space with a kernel strategy. In particular, the sparse subspace clustering (SSC) model is extended to nonlinear manifolds, which can better explore the complex nonlinear structure of hyperspectral images (HSIs) and obtain a much more accurate representation coefficient matrix. Secondly, through the spatial max pooling operation, the spatial contextual information is integrated to obtain a smoother clustering result. Through experiments, it is verified that the KSSC-SMP algorithm is a competitive clustering method for HSIs and outperforms the state-of-the-art clustering methods.

Download Full-text

Spatial distribution preserving-based sparse subspace clustering for hyperspectral image

International Journal of Wavelets Multiresolution and Information Processing ◽

10.1142/s0219691319400101 ◽

2019 ◽

Vol 17 (02) ◽

pp. 1940010

Author(s):

Yiyang Ding ◽

Anyong Qin ◽

Zhaowei Shang ◽

Jiye Qian

Keyword(s):

Spatial Distribution ◽

Spatial Information ◽

Hyperspectral Image ◽

Subspace Clustering ◽

Original Data ◽

Coefficient Matrix ◽

Intrinsic Structure ◽

Affine Subspaces ◽

Novel Approach ◽

Sparse Subspace Clustering

The high dimensionality and heterogeneity of the hyperspectral image (HSI) make a challenge to the application of machine learning methods, such as sparse subspace clustering (SSC). SSC is designed to represent data as an union of affine subspaces, while it cannot capture the latent structure of the given data. In Mosers theory, the distribution can represent the intrinsic structure efficiently. Hence, we propose a novel approach called spatial distribution preserving-based sparse subspace clustering (SSC-SDP) in this paper for HSI data, which can help sparse representation preserve the underlying manifold structure. Specifically, the density constraint is added by minimizing the inconsistency of the densities estimated in the HSI data and the corresponding sparse coefficient matrix. In addition, we incorporate spatial information into the density estimation of the original data, and the optimization solution based on alternating direction method of multipliers (ADMM) is devised. Three HSI data sets are conducted to evaluate the performance of our SSC-SDP compared with other state-of-art algorithms.

Download Full-text

Spectral-Spatial Sparse Subspace Clustering Based on Three-Dimensional Edge-Preserving Filtering for Hyperspectral Image

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001419550036 ◽

2019 ◽

Vol 33 (03) ◽

pp. 1955003 ◽

Cited By ~ 4

Author(s):

Ailin Li ◽

Anyong Qin ◽

Zhaowei Shang ◽

Yuan Yan Tang

Keyword(s):

Spatial Information ◽

Hyperspectral Image ◽

Three Dimensional ◽

Subspace Clustering ◽

Coefficient Matrix ◽

Simple Method ◽

Edge Preserving ◽

Sparse Coefficient ◽

Similarity Graph ◽

Sparse Subspace Clustering

Integrating spatial information into the sparse subspace clustering (SSC) models for hyperspectral images (HSIs) is an effective way to improve clustering accuracy. Since HSI is a three-dimensional (3D) cube datum, 3D spectral-spatial filtering becomes a simple method for extracting the spectral-spatial information. In this paper, a novel spectral-spatial SSC framework based on 3D edge-preserving filtering (EPF) is proposed to improve the clustering accuracy of HSI. First, the initial sparse coefficient matrix is obtained in the sparse representation process of the classical SSC model. Then, a 3D EPF is conducted on the initial sparse coefficient matrix to obtain a more accurate coefficient matrix by solving an optimization problem based on ADMM, which is used to build the similarity graph. Finally, the clustering result of HSI data is achieved by applying the spectral clustering algorithm to the similarity graph. Specifically, the filtered matrix can not only capture the spectral-spatial information but the intensity differences. The experimental results on three real-world HSI datasets demonstrated that the potential of including the proposed 3D EPF into the SSC framework can improve the clustering accuracy.

Download Full-text

Enhanced Sparse Subspace Clustering by Manifold Regularization for Hyperspectral Image

Proceedings of the 2019 International Conference on Artificial Intelligence and Computer Science - AICS 2019 ◽

10.1145/3349341.3349449 ◽

2019 ◽

Author(s):

Tongxu Zhou ◽

Jipan Yang ◽

Lu Liang

Keyword(s):

Hyperspectral Image ◽

Subspace Clustering ◽

Manifold Regularization ◽

Sparse Subspace Clustering

Download Full-text

Sparse Subspace Clustering in Hyperspectral Images using Incomplete Pixels

TecnoLógicas ◽

10.22430/22565337.1205 ◽

2019 ◽

Vol 22 (46) ◽

pp. 1-14 ◽

Cited By ~ 1

Author(s):

Jorge Luis Bacca ◽

Henry Arguello

Keyword(s):

Spatial Information ◽

Hyperspectral Image ◽

Subspace Clustering ◽

Unsupervised Classification ◽

Hyperspectral Images ◽

Image Clustering ◽

Spectral Signature ◽

Spectral Image ◽

Sparse Subspace Clustering

Spectral image clustering is an unsupervised classification method which identifies distributions of pixels using spectral information without requiring a previous training stage. The sparse subspace clustering-based methods (SSC) assume that hyperspectral images lie in the union of multiple low-dimensional subspaces. Using this, SSC groups spectral signatures in different subspaces, expressing each spectral signature as a sparse linear combination of all pixels, ensuring that the non-zero elements belong to the same class. Although these methods have shown good accuracy for unsupervised classification of hyperspectral images, the computational complexity becomes intractable as the number of pixels increases, i.e. when the spatial dimension of the image is large. For this reason, this paper proposes to reduce the number of pixels to be classified in the hyperspectral image, and later, the clustering results for the missing pixels are obtained by exploiting the spatial information. Specifically, this work proposes two methodologies to remove the pixels, the first one is based on spatial blue noise distribution which reduces the probability to remove cluster of neighboring pixels, and the second is a sub-sampling procedure that eliminates every two contiguous pixels, preserving the spatial structure of the scene. The performance of the proposed spectral image clustering framework is evaluated in three datasets showing that a similar accuracy is obtained when up to 50% of the pixels are removed, in addition, it is up to 7.9 times faster compared to the classification of the data sets without incomplete pixels.

Download Full-text

A fast and accurate similarity-constrained subspace clustering algorithm for land cover segmentation

10.36227/techrxiv.14414789 ◽

2021 ◽

Author(s):

Carlos Hinojosa ◽

Esteban Vera ◽

Henry Arguello

Keyword(s):

Land Cover ◽

High Performance ◽

Clustering Algorithm ◽

Spatial Information ◽

Subspace Clustering ◽

Coefficient Matrix ◽

Clustering Methods ◽

Spatial Homogeneity ◽

Discrimination Capability ◽

Unsupervised Deep Learning

Accurate land cover segmentation of spectral images is challenging and has drawn widespread attention in remote sensing due to its inherent complexity. Although significant efforts have been made for developing a variety of methods, most of them rely on supervised strategies. Subspace clustering methods, such as Sparse Subspace Clustering (SSC), have become a popular tool for unsupervised learning due to their high performance. However, the computational complexity of SSC methods prevents their use on large spectral remotely sensed datasets. Furthermore, since SSC ignores the spatial information in the spectral images, its discrimination capability is limited, hampering the clustering results' spatial homogeneity. To address these two relevant issues, in this paper, we propose a fast algorithm that obtains a sparse representation coefficient matrix by first selecting a small set of pixels that best represent their neighborhood. Then, it performs spatial filtering to enforce the connectivity of neighboring pixels and uses fast spectral clustering to get the final segmentation. Extensive simulations with our method demonstrate its effectiveness in land cover segmentation, obtaining remarkable high clustering performance compared with state-of-the-art SSC-based algorithms and even novel unsupervised-deep-learning-based methods. Besides, the proposed method is up to three orders of magnitude faster than SSC when clustering more than 2x10<sup>4</sup> spectral pixels.

Download Full-text

Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image

Remote Sensing ◽

10.3390/rs13071372 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1372

Author(s):

Jinhuan Xu ◽

Liang Xiao ◽

Jingxiang Yang

Keyword(s):

Hyperspectral Image ◽

Subspace Clustering ◽

Feature Space ◽

Low Rank ◽

Great Success ◽

Clustering Methods ◽

Hypergraph Learning ◽

Optimal Dynamic ◽

Low Rank Representation ◽

Original Feature

Low-rank representation with hypergraph regularization has achieved great success in hyperspectral imagery, which can explore global structure, and further incorporate local information. Existing hypergraph learning methods only construct the hypergraph by a fixed similarity matrix or are adaptively optimal in original feature space; they do not update the hypergraph in subspace-dimensionality. In addition, the clustering performance obtained by the existing k-means-based clustering methods is unstable as the k-means method is sensitive to the initialization of the cluster centers. In order to address these issues, we propose a novel unified low-rank subspace clustering method with dynamic hypergraph for hyperspectral images (HSIs). In our method, the hypergraph is adaptively learned from the low-rank subspace feature, which can capture a more complex manifold structure effectively. In addition, we introduce a rotation matrix to simultaneously learn continuous and discrete clustering labels without any relaxing information loss. The unified model jointly learns the hypergraph and the discrete clustering labels, in which the subspace feature is adaptively learned by considering the optimal dynamic hypergraph with the self-taught property. The experimental results on real HSIs show that the proposed methods can achieve better performance compared to eight state-of-the-art clustering methods.

Download Full-text