Hyperspectral Image Classification via Low-Rank and Sparse Representation With Spectral Consistency Constraint

Pan, Lei; Li, Heng-Chao; Meng, Hua; Li, Wei; Du, Qian; Emery, William J.

doi:10.1109/lgrs.2017.2753401

Cited by 22 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our method also achieves excellent performance in this setting: it improves significantly over the considered baselines, according to a binomial test for comparing classifiers [45]; see Table 9. Table 10 reports the results of our method and published results of the following state-of-the-art methods based on different approaches: discriminative low-rank Gabor filtering [12], multiple kernel learning [30], kernel sparse representation [34] and probabilistic class structure regularized sparse representation graph [31,29]. Unfortunately, due to the diversity of choices regarding the number of training pixels, it is not possible to completely fill Table 10.…”

Section: Methodsmentioning

confidence: 99%

“…Extensive experiments indicate the effectiveness of the proposed method, which achieves comparable or better accuracy performance than existing methods, such as deep neural networks [28], multiple kernel learning [29], probabilistic class structure regularized sparse representation graph [30,31] and low-rank Gabor filtering [12] (see the results in Table 10).…”

Section: Introductionmentioning

confidence: 90%

See 1 more Smart Citation

Spectral-Spatial Classification of Hyperspectral Images: Three Tricks and a New Learning Setting

et al. 2018

View full text Add to dashboard Cite

Spectral-spatial classification of hyperspectral images has been the subject of many studies in recent years. When there are only a few labeled pixels for training and a skewed class label distribution, this task becomes very challenging because of the increased risk of overfitting when training a classifier. In this paper, we show that in this setting, a convolutional neural network with a single hidden layer can achieve state-of-the-art performance when three tricks are used: a spectrallocality-aware regularization term and smoothing-and label-based data augmentation. The shallow network architecture prevents overfitting in the presence of many features and few training samples. The locality-aware regularization forces neighboring wavelengths to have similar contributions to the features generated during training. The new data augmentation procedure favors the selection of pixels in smaller classes, which is beneficial for skewed class label distributions. The accuracy of the proposed method is assessed on five publicly available hyperspectral images, where it achieves state-of-the-art results. As other spectral-spatial classification methods, we use the entire image (labeled and unlabeled pixels) to infer the class of its unlabeled pixels. To investigate the positive bias induced by the use of the entire image, we propose a new learning setting where unlabeled pixels are not used for building the classifier. Results show the beneficial effect of the proposed tricks also in this setting and substantiate the advantages of using labeled and unlabeled pixels from the image for hyperspectral image classification.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 90%

Spectral-Spatial Classification of Hyperspectral Images: Three Tricks and a New Learning Setting

et al. 2018

View full text Add to dashboard Cite

show abstract

“…2 depicts the SAD and RMSE results with standard deviation. Obviously, the unmixing performance is stable when µ is in the range [1,100]. Then, the value of µ is fixed to 10 in the following experiments.…”

Section: A Experiments On Synthetic Datamentioning

confidence: 99%

“…H YPERSPECTRAL imagery (HSI) contains a range of spectra from ultraviolet to infrared bands, providing affluent information to detect and identify ground objects. Therefore, HSI advances active research in various fields: classification [1], object detection [2], and data fusion [3], etc. Due to the limited spatial resolution of spectrometer, diverse materials present in the scene, and multiple scattering, the spectrum of an observed pixel is generally a combination of these spectra of several materials, resulting in mixed pixel.…”

Section: Introductionmentioning

confidence: 99%

Sparsity-Constrained Coupled Nonnegative Matrix–Tensor Factorization for Hyperspectral Unmixing

Liu

Feng

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Hyperspectral unmixing refers to a source separation problem of decomposing a hyperspectral imagery (HSI) to estimate endmembers and their corresponding abundances. Recently, matrix-vector nonnegative tensor factorization (MV-NTF) was proposed for unmixing to avoid structure information loss, which is caused by the HSI cube unfolding in nonnegative matrix factorization (NMF)-based methods. However, MV-NTF ignores local spatial information due to directly dealing with data as a whole, meanwhile, the forceful rank constraint in low-rank tensor decomposition loses some detailed structures. Unlike MV-NTF works at the original data, the pixel-based NMF is more adaptive to learn local spatial variations. Hence, from the perspective of multi-view, it is significant to utilize the complementary advantages of MV-NTF and NMF to fully preserve the intrinsic structure information and exploit more detailed spatial information. In this paper, we propose a sparsityconstrained coupled nonnegative matrix-tensor factorization (SC-NMTF) model for unmixing, wherein MV-NTF and NMF are subtly coupled by sharing endmembers and abundances. Since the representations for abundances in MV-NTF and NMF are distinct, abundance sharing is achieved indirectly by introducing an auxiliary constraint. Furthermore, the L 1/2 regularizer is adopted to promote the sparsity of abundances. A series of experiments on synthetic and real hyperspectral data demonstrate the effectiveness of the proposed SCNMTF method.

show abstract

“…LRSD based methods express an input matrix as the sum of a low rank and a sparse matrix. It is widely used in image and video processing topics [14] such as denoising [15], classification [16], restoration [17], scene change detection and foreground/background separation [18]. In GPR, the target part can be considered as sparse compared to the whole GPR image and the clutter part can be expressed by a low rank matrix as demonstrated in [7]- [11].…”

Section: Introductionmentioning

confidence: 99%

GPR Clutter Reduction by Robust Orthonormal Subspace Learning

Kumlu

Erer

2020

IEEE Access

View full text Add to dashboard Cite

The clutter severely decreases the target visibility, thus the detection rates in ground penetrating radar (GPR) systems. Recently proposed robust principal component analysis (RPCA) based clutter removal method decomposes the GPR image into its low rank and sparse parts corresponding to clutter and target components. Motivated by its encouraging results, many lower complexity low rank and sparse decomposition (LRSD) methods such as go decomposition (GoDec) or robust non-negative matrix factorization (RNMF) have been applied to GPR. This paper proposes a new clutter reduction method using robust orthonormal subspace learning (ROSL). The raw GPR image is decomposed into its clutter and target parts via ROSL. The proposed method is faster than the popular RPCA. Although it has similar complexity, and similar performance with GoDec and RNMF for fine tuned parameters of these methods, the proposed method does not require any presetting of the algorithm parameters. Its performance remains independent for a broad range parameter value. Results demonstrate that the proposed method achieves 14 − 48% higher performance in terms of PSNR values than the state-of-the-art LRSD methods for an arbitrary parameter choice.INDEX TERMS Clutter reduction, low rank and sparse matrix decomposition, robust subspace learning, GPR.

show abstract

Hyperspectral Image Classification via Low-Rank and Sparse Representation With Spectral Consistency Constraint

Cited by 22 publications

References 15 publications

Spectral-Spatial Classification of Hyperspectral Images: Three Tricks and a New Learning Setting

Spectral-Spatial Classification of Hyperspectral Images: Three Tricks and a New Learning Setting

Sparsity-Constrained Coupled Nonnegative Matrix–Tensor Factorization for Hyperspectral Unmixing

GPR Clutter Reduction by Robust Orthonormal Subspace Learning

Contact Info

Product

Resources

About