Tensor-Based Robust Principal Component Analysis With Locality Preserving Graph and Frontal Slice Sparsity for Hyperspectral Image Classification

Wang, Yingxu; Li, Tianjun; Chen, Long; Yu, Yufeng; Zhao, Yin-Ping; Zhou, Jin

doi:10.1109/tgrs.2021.3093582

Cited by 15 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the proposed LLRA-SLPG method with stateof-the-art HSI classification methods, including seven LRAbased methods for HSIs, i.e., RPCA [51], LLRSSTV [52], S 3 LRR [28], SS-LRR [30], LSSTRPCA [35], LPGTRPCA [53], OLRT [54]. We adopt the suggested settings in the original papers for all those baseline methods.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Local Low-Rank Approximation With Superpixel-Guided Locality Preserving Graph for Hyperspectral Image Classification

Yang

Zhang

Jia

et al. 2022

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

View full text Add to dashboard Cite

Given the detrimental effect of spectral variations in a hyperspectral image (HSI), this paper investigates to recover its discriminative representation to improve the classification performance. We propose a new method, namely local low-rank approximation with superpixel-guided locality preserving graph (LLRA-SLPG), which can reduce the spectral variations and preserve the local manifold structure of an HSI. Specifically, the LLRA-SLPG method first clusters pixels of an HSI into several groups (i.e., superpixels). By taking advantage of the local manifold structure, a Laplacian graph is constructed from the superpixels to ensure that a typical pixel should be similar to its neighbors within the same superpixel. The LLRA-SLPG model can increase the compactness of pixels belonging to the same class by reducing spectral variations while promoting local consistency via the Laplacian graph. The objective function of the LLRA-SLPG model can be solved efficiently in an iterative manner. Experimental results on four benchmark datasets validate the superiority of the LLRA-SLPG model over state-of-the-art methods, particularly in cases where only extremely few training pixels are available.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Local Low-Rank Approximation With Superpixel-Guided Locality Preserving Graph for Hyperspectral Image Classification

Yang

Zhang

Jia

et al. 2022

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

View full text Add to dashboard Cite

show abstract

“…Some researchers try to apply the T-SVD-based TRPCA algorithms appropriately to hyperspectral datasets. They mainly choose different kinds of slices [26], change the types of norms [27], add parameters to original objective functions, or employ additional pre-processing or post-processing steps [28]. Nevertheless, these updated TRPCA low-rank extracting techniques destroy the underlying spectral contextual information of HSIs, which may directly result in unsatisfactory classification performance as the homogeneity and heterogeneity information are insufficiently exploited.…”

Section: Introductionmentioning

confidence: 99%

An Efficient and Adaptive Reconstructive Homogeneous Block-Based Local Tensor Robust PCA for Feature Extraction of Hyperspectral Images

Qian,

Wang,

Hong

et al. 2024

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

View full text Add to dashboard Cite

show abstract

“…However, the problems of low spatial resolution, high spectral dimensionality and lack of labelled samples in HSI pose great challenges to the classification task [10][11][12]. In the early days, researchers proposed a series of feature extraction methods such as principal component analysis [13,14], independent component analysis [15][16][17], and linear discriminant analysis [17,18], and combined them with machine learning classifiers such as support vector machines [19,20], random forests [21,22], and Gaussian mixture model [23,24] to classify the HSI. These methods can effectively alleviate the Hughes phenomenon [25] that classification accuracy decreases with increasing spectral dimension, but because only spectral features are considered and based on manual design, the classification accuracy and applicability are not ideal.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Classification Based on 3D-2D Hybrid Convolution and Graph Attention Mechanism

Zhang

Huanhuan

et al. 2023

Preprint

View full text Add to dashboard Cite

Convolutional neural networks and graph convolutional neural networks are two classical deep learning models that have been widely used in hyperspectral image classification tasks with remarkable achievements. However, hyperspectral image classification models based on graph convolutional neural networks using only shallow spectral or spatial features are insufficient to provide reliable similarity measures for constructing graph structures, limiting their classification performance. To address this problem, we propose a hyperspectral image classification model combining 3D-2D hybrid convolution and a graph attention mechanism. First, a 3D-2D hybrid convolutional network is constructed and used to rapidly extract deep features that express spatial and spectral associations. Then, the graph is built based on deep spatial-spectral features to enhance the feature representation of the graph. Finally, a network of graph attention mechanisms is adopted to learn long-range spatial connections and to classify them using the extracted spatial features. The experimental results on two datasets, Indian Pine and the University of Pavia, show that the proposed method can achieve higher classification accuracy compared with other advanced methods.

show abstract

Tensor-Based Robust Principal Component Analysis With Locality Preserving Graph and Frontal Slice Sparsity for Hyperspectral Image Classification

Cited by 15 publications

References 56 publications

Local Low-Rank Approximation With Superpixel-Guided Locality Preserving Graph for Hyperspectral Image Classification

Local Low-Rank Approximation With Superpixel-Guided Locality Preserving Graph for Hyperspectral Image Classification

An Efficient and Adaptive Reconstructive Homogeneous Block-Based Local Tensor Robust PCA for Feature Extraction of Hyperspectral Images

Hyperspectral Image Classification Based on 3D-2D Hybrid Convolution and Graph Attention Mechanism

Contact Info

Product

Resources

About