Dimensionality Reduction of Hyperspectral Imagery Based on Spatial–Spectral Manifold Learning

Hong, Huixiao; Shi, Guangyao; He, Haibo; Duan, Yule; Luo, Fulin

doi:10.1109/tcyb.2019.2905793

Cited by 142 publications

(64 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…1) The method uses SVM to classify raw spectral features (SP-SVM). The method called spatial-spectral manifold reconstruction preserving embedding (SSMRPE) for HIS classification [32]. The evaluation indicators used in this article include overall classification accuracy (OA), average classification accuracy (AA) and Kappa coefficient (KC).…”

Section: B Comparison Methods and Evaluation Indicatorsmentioning

confidence: 99%

See 1 more Smart Citation

Spatial-Spectral Joint Classification of Hyperspectral Image With Locality and Edge Preserving

Zhang

Liu

Huanhuan

2020

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

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification is an important part of its processing and application. Aiming at the problems of high data dimensionality and high spatial neighborhood correlation in HSI classification, we propose a spatial-spectral joint classification method of HSI with locality and edge preserving in this article. First, the input HSI is normalized, and the feature is extracted by principal component analysis. The first principal component image is taken as the guidance image. Second, guided filtering is used to extract the spatial features of each band separately. Then, the extracted spatial features are superimposed, and low-dimensional embedding is completed through local Fisher discriminant analysis. Finally, the obtained low-dimensional embedded features are input into a random forest classifier to get classification results. The experimental results of two HSI show that the proposed method achieves higher classification accuracy than other related methods. In the case of randomly selecting 10% and 1% samples from each class of ground object as training samples, the overall classification accuracy is improved to 99.57% and 97.79%, respectively. This method effectively uses the spatial and local information of the image in low dimensional embedding, and preserves the boundaries of the ground objects, thus improving the classification effect.

show abstract

Section: B Comparison Methods and Evaluation Indicatorsmentioning

confidence: 99%

“…Finally, the learned features were fed to SVM for classification. Huang et al [32] first employed a weighted mean filter to filter the image. Then, a spatial-spectral combined distance was used to fuse the spatial and spectral information to select the neighbors of each pixel.…”

Section: Introductionmentioning

confidence: 99%

Spatial-Spectral Joint Classification of Hyperspectral Image With Locality and Edge Preserving

Zhang

Liu

Huanhuan

2020

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

View full text Add to dashboard Cite

show abstract

“…Basically, there are two kinds of dimensionality reduction methods for HSI: feature extraction and feature selection. With the feature space transform, feature extraction can project the original data into a lower dimensional space, using approaches such as the principal component analysis (PCA) [15], [16], independent component analysis (ICA) [17], wavelet transform [18], the manifold learning [19], and the maximum noise fraction (MNF) [20], etc. The resulted data can be assumed to contain most of the spectral and spatial information from the original HSI data.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Distance-Based Band Hierarchy (ADBH) for Effective Hyperspectral Band Selection

Sun

Ren

Zhao

et al. 2022

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Band selection has become a significant issue for the efficiency of hyperspectral image (HSI) processing. Although many unsupervised band selection (UBS) approaches have been developed in the last decades, a flexible and robust method is still lacking. The lack of proper understanding of the HSI data structure has resulted to the inconsistency in the outcome of UBS. Besides, most of UBS methods are either relying on complicated measurements or rather noise sensitive, which hinder the efficiency of the determined band subset. In this paper, an adaptive distance based band hierarchy (ADBH) clustering framework is proposed for unsupervised band selection in HSI, which can help to avoid the noisy bands whilst reflecting the hierarchical data structure of HSI. With a tree hierarchy-based framework, we can acquire any number of band subset. By introducing a novel adaptive distance into the hierarchy, the similarity between bands and band groups can be computed straightforward whilst reducing the effect of noisy bands. Experiments on four datasets acquired from two HSI systems have fully validated the superiority of the proposed framework.

show abstract

“…Wang et al [19] proposed selecting representative features hierarchically by the means of random projection in an end-to-end neural network, which has shown the effectiveness in the large-scale data. Very recently, Huang et al [20] followed the trail of drawbacks of spatial-spectral techniques, and fixed them by designing a new spatial-spectral-combined distance to select spatialspectral neighbors of each HS pixel more effectively. In the combined distance, the pixel-to-pixel distance measurement between two spectral signatures is converted to the weighted summation distance between spatially adjacent spaces of the two target pixels.…”

Section: Introductionmentioning

confidence: 99%

Joint and Progressive Subspace Analysis (JPSA) With Spatial–Spectral Manifold Alignment for Semisupervised Hyperspectral Dimensionality Reduction

Hong

Yokoya

Chanussot

et al. 2021

IEEE Trans. Cybern.

View full text Add to dashboard Cite

This is the pre-acceptance version, to read the final version please go to IEEE Transactions on Cybernetics on IEEE Xplore. Conventional nonlinear subspace learning techniques (e.g., manifold learning) usually introduce some drawbacks in explainability (explicit mapping) and cost-effectiveness (linearization), generalization capability (out-of-sample), and representability (spatial-spectral discrimination). To overcome these shortcomings, a novel linearized subspace analysis technique with spatial-spectral manifold alignment is developed for a semi-supervised hyperspectral dimensionality reduction (HDR), called joint and progressive subspace analysis (JPSA). The JPSA learns a high-level, semantically meaningful, joint spatialspectral feature representation from hyperspectral data by 1) jointly learning latent subspaces and a linear classifier to find an effective projection direction favorable for classification; 2) progressively searching several intermediate states of subspaces to approach an optimal mapping from the original space to a This paper is an extended version in algorithm of [1] published in ECCV2018.

show abstract

Dimensionality Reduction of Hyperspectral Imagery Based on Spatial–Spectral Manifold Learning

Cited by 142 publications

References 41 publications

Spatial-Spectral Joint Classification of Hyperspectral Image With Locality and Edge Preserving

Spatial-Spectral Joint Classification of Hyperspectral Image With Locality and Edge Preserving

Adaptive Distance-Based Band Hierarchy (ADBH) for Effective Hyperspectral Band Selection

Joint and Progressive Subspace Analysis (JPSA) With Spatial–Spectral Manifold Alignment for Semisupervised Hyperspectral Dimensionality Reduction

Contact Info

Product

Resources

About