Gaussian Process Graph-Based Discriminant Analysis for Hyperspectral Images Classification

Song, Xin; Jiang, Xinwei; Gao, Junbin; Cai, Zhihua

doi:10.3390/rs11192288

Cited by 6 publications

(5 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remote sensing utilizes modern carrying tools and sensors to acquire the electromagnetic wave characteristics of target objects from a distance. It involves the transmission, storage, correction, and interpretation of information to analyze changes in the shape, location, nature, and state of the target This redundancy not only affects the classification performance of algorithms but also leads to lower efficiency in algorithm execution [16,17].…”

Section: Characteristics and Challenges Of Hyperspectral Remote Sensi...mentioning

confidence: 99%

Dimensionality Reduction and Research of Hyperspectral Remote Sensing Images Based on Manifold Learning

Song,

Zhang,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

With the rapid advancements in remote sensing technology, the spectral information from hyperspectral remote sensing images has become increasingly rich, facilitating detailed spectral analysis of the Earth's surface objects. However, this abundance of spectral data poses significant challenges in data processing, such as the curse of dimensionality leading to the “Hughes” phenomenon, "strong correlation" due to high resolution, and "non-linear characteristics" caused by varied surface reflectance rates. Therefore, dimensionality reduction of hyperspectral data has become a crucial task. This paper, grounded in manifold theory and manifold learning techniques, and considering the non-linear structures and features in hyperspectral remote sensing data, elucidates the principles and processes of dimensionality reduction in hyperspectral remote sensing images using manifold learning, with a formalized expression of the process. This article introduces spectral information divergence (SID) into the nearest neighbor graph computation of manifold learning algorithms. The principles and computational processes of nearest neighbor graph algorithms based on Euclidean distance (ED), spectral angle mapping (SAM), and SID are studied, and a comparative analysis of the dimensionality reduction effects under these three metrics in hyperspectral data is conducted. Experiments on feature extraction under different metrics were performed using the publicly available Indian Pines hyperspectral dataset. The intrinsic features obtained post-dimensionality reduction were used as inputs for classification algorithms in ground objects classification experiments, with algorithm runtime, overall accuracy, and Kappa coefficient as evaluation metrics for dimensionality reduction quality. The results demonstrate that nearest neighbor graph computation based on SAM and SID outperforms traditional ED methods; SAM-based computation has the lowest time complexity, while SID-based manifold learning yields the highest accuracy in ground objects classification. Thus, manifold learning based on SAM and SID metrics proves to be an effective method for feature extraction in hyperspectral remote sensing data, underscoring the potential of manifold learning techniques in the dimensionality reduction of hyperspectral remote sensing images.

show abstract

Section: Characteristics and Challenges Of Hyperspectral Remote Sensi...mentioning

confidence: 99%

Dimensionality Reduction and Research of Hyperspectral Remote Sensing Images Based on Manifold Learning

Song,

Zhang,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…However, most of the research on GP methods is limited to tests and applications performed on objects with simple geometries. Consequently, whether these algorithms are capable of dealing with multiscale complex surfaces is not yet clear [36,54,[84][85][86]. Additionally, the implementation of GP algorithms simplifies the real modelling process into a set of GP equations [81].…”

Section: Advantages and Limitations Of User-dependent And -Independen...mentioning

confidence: 99%

Applications of data fusion in optical coordinate metrology: a review

Zhang

Catalucci

Thompson

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Data fusion enables the characterisation of an object using multiple datasets collected by various sensors. To improve optical coordinate measurement using data fusion, researchers have proposed numerous algorithmic solutions and methods. The most popular examples are the Gaussian process (GP) and weighted least-squares (WLS) algorithms, which depend on user-defined mathematical models describing the geometric characteristics of the measured object. Existing research on GP and WLS algorithms indicates that GP algorithms have been widely applied in both academia and industry, despite their use being limited to applications on relatively simple geometries. Research on WLS algorithms is less common than research on GP algorithms, as the mathematical tools used in the WLS cases are too simple to be applied with complex geometries. Machine learning is a new technology that is increasingly being applied to data fusion applications. Research on this technology is relatively scarce, but recent work has highlighted the potential of machine learning methods with significant results. Unlike GP and WLS algorithms, machine learning algorithms can autonomously learn the geometrical features of an object. To understand existing research in-depth and explore a path for future work, a new taxonomy of data fusion algorithms is proposed, covering the mathematical background and existing research surrounding each algorithm type. To conclude, the advantages and limitations of the existing methods are reviewed, highlighting the issues related to data quality and the types of test artefacts.

show abstract

“…Factors like solar elevation and cloud cover also have a uniform effect on all bands of the hyperspectral imagery, further enhancing inter-band correlation. The strong correlation among bands leads to low algorithmic efficiency [14][15][16].…”

Section: Introduction 1characteristics and Challenges Of Hyperspectra...mentioning

confidence: 99%

A Study on Dimensionality Reduction and Parameters for Hyperspectral Imagery Based on Manifold Learning

Song,

Zhang,

Yang

et al. 2024

Sensors

View full text Add to dashboard Cite

With the rapid advancement of remote-sensing technology, the spectral information obtained from hyperspectral remote-sensing imagery has become increasingly rich, facilitating detailed spectral analysis of Earth’s surface objects. However, the abundance of spectral information presents certain challenges for data processing, such as the “curse of dimensionality” leading to the “Hughes phenomenon”, “strong correlation” due to high resolution, and “nonlinear characteristics” caused by varying surface reflectances. Consequently, dimensionality reduction of hyperspectral data emerges as a critical task. This paper begins by elucidating the principles and processes of hyperspectral image dimensionality reduction based on manifold theory and learning methods, in light of the nonlinear structures and features present in hyperspectral remote-sensing data, and formulates a dimensionality reduction process based on manifold learning. Subsequently, this study explores the capabilities of feature extraction and low-dimensional embedding for hyperspectral imagery using manifold learning approaches, including principal components analysis (PCA), multidimensional scaling (MDS), and linear discriminant analysis (LDA) for linear methods; and isometric mapping (Isomap), locally linear embedding (LLE), Laplacian eigenmaps (LE), Hessian locally linear embedding (HLLE), local tangent space alignment (LTSA), and maximum variance unfolding (MVU) for nonlinear methods, based on the Indian Pines hyperspectral dataset and Pavia University dataset. Furthermore, the paper investigates the optimal neighborhood computation time and overall algorithm runtime for feature extraction in hyperspectral imagery, varying by the choice of neighborhood k and intrinsic dimensionality d values across different manifold learning methods. Based on the outcomes of feature extraction, the study examines the classification experiments of various manifold learning methods, comparing and analyzing the variations in classification accuracy and Kappa coefficient with different selections of neighborhood k and intrinsic dimensionality d values. Building on this, the impact of selecting different bandwidths t for the Gaussian kernel in the LE method and different Lagrange multipliers λ for the MVU method on classification accuracy, given varying choices of neighborhood k and intrinsic dimensionality d, is explored. Through these experiments, the paper investigates the capability and effectiveness of different manifold learning methods in feature extraction and dimensionality reduction within hyperspectral imagery, as influenced by the selection of neighborhood k and intrinsic dimensionality d values, identifying the optimal neighborhood k and intrinsic dimensionality d value for each method. A comparison of classification accuracies reveals that the LTSA method yields superior classification results compared to other manifold learning approaches. The study demonstrates the advantages of manifold learning methods in processing hyperspectral image data, providing an experimental reference for subsequent research on hyperspectral image dimensionality reduction using manifold learning methods.

show abstract

Gaussian Process Graph-Based Discriminant Analysis for Hyperspectral Images Classification

Cited by 6 publications

References 52 publications

Dimensionality Reduction and Research of Hyperspectral Remote Sensing Images Based on Manifold Learning

Dimensionality Reduction and Research of Hyperspectral Remote Sensing Images Based on Manifold Learning

Applications of data fusion in optical coordinate metrology: a review

A Study on Dimensionality Reduction and Parameters for Hyperspectral Imagery Based on Manifold Learning

Contact Info

Product

Resources

About