SuperPCA: A Superpixelwise PCA Approach for Unsupervised Feature Extraction of Hyperspectral Imagery

Jiang, Junjun; Ma, Jiayi; Chen, Chen; Wang, Zhongyuan; Cai, Zhihua; Wang, Lizhe

doi:10.1109/tgrs.2018.2828029

Cited by 250 publications

(161 citation statements)

References 63 publications

(94 reference statements)

Supporting

Mentioning

161

Contrasting

Order By: Relevance

“…As a crucial task, the classification of HSI pixels attracts great attention for a long time [1][2][3]. Many early methods are based on classical machine learning algorithms and their variations, for instance, principal component analysis (PCA) [4,5], independent component analysis (ICA) [6], linear discriminant analysis (LDA) [7,8], support vector machine (SVM) [9], and sparse representation [10,11].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Classification With Deep Metric Learning and Conditional Random Field

Liang

Zhao

Guo

et al. 2020

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

To improve the classification performance in the context of hyperspectral image processing, many works have been developed based on two common strategies, namely the spatial-spectral information integration and the utilization of neural networks. However, both strategies typically require more training data than the classical algorithms, aggregating the shortage of labeled samples. In this letter, we propose a novel framework that organically combines the spectrum-based deep metric learning model and the conditional random field algorithm. The deep metric learning model is supervised by the center loss to produce spectrum-based features that gather more tightly in Euclidean space within classes. The conditional random field with Gaussian edge potentials, which is firstly proposed for image segmentation tasks, is introduced to give the pixel-wise classification over the hyperspectral image by utilizing both the geographical distances between pixels and the Euclidean distances between the features produced by the deep metric learning model. The proposed framework is trained by spectral pixels at the deep metric learning stage and utilizes the half handcrafted spatial features at the conditional random field stage. This settlement alleviates the shortage of training data to some extent. Experiments on two real hyperspectral images demonstrate the advantages of the proposed method in terms of both classification accuracy and computation cost.

show abstract

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Classification With Deep Metric Learning and Conditional Random Field

Liang

Zhao

Guo

et al. 2020

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

show abstract

“…Obtain U (1),t by (9); 7 Obtain U (2),t by (10); 8 Obtain U (3),t by (11); 9 Obtain G t by (7), t = t + 1; 10 end…”

Section: A the Mapping Layermentioning

confidence: 99%

“…The validation results show that the best hyperparameters of our mapping layers are different for three datasets. According to the results in Table II, Table III and Table IV, we specify (R 1 , R 2 , R 3 ) as (7,7,40), (7,7,20) and (7,7,40) for IP, UP and Salinas, respectively. The results also reveal that our mapping layers are able to extract better spectral-spatial features of small sizes, which further reduce computational cost and achieve better classification results.…”

Section: B the Validation Of Hyperparametersmentioning

confidence: 99%

“…Thus, the feature extraction methods are designed to find a best method to map the original high-dimensional feature into a low-dimensional subspace while keeping the most useful dimensions for classification. The most representative methods are principal component analysis (PCA) [7] and its variants [8]- [10]. The linear discriminant analysis is also a widely used feature extraction method which searches the optimal projection subspace by maximizing between-class scatter matrix and minimizing within-class scatter matrix [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Convolutional Neural Network With Mapping Layers for Hyperspectral Image Classification

Pan

Yang

et al. 2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

In this paper, we propose a convolutional neural network with mapping layers (MCNN) for hyperspectral image (HSI) classification. The proposed mapping layers map the input patch into a low dimensional subspace by multilinear algebra. We use our mapping layers to reduce the spectral and spatial redundancy and maintain most energy of the input. The feature extracted by our mapping layers can also reduce the number of following convolutional layers for feature extraction. Our MCNN architecture avoids the declining accuracy with increasing layers phenomenon of deep learning models for HSI classification and also saves the training time for its effective mapping layers. Furthermore, we impose the 3-D convolutional kernel on convolutional layer to extract the spectral-spatial features for HSI. We tested our MCNN on three datasets of Indian Pines, University of Pavia and Salinas, and we achieved the classification accuracy of 98.3%, 99.5% and 99.3%, respectively. Experimental results demonstrate that the proposed MCNN can significantly improve the classification accuracy and save much time consumption.

show abstract

“…Due to the high spectral resolution, it is inevitable to bring about the problem of "mixed pixels", and different materials usually occupy a single hyperspectral pixel [4][5][6]. The existence of mixed pixels have a large impact on many applications, such as object detection [7], subpixel mapping [8], classification [9][10][11][12], and matching [13][14][15]. Thus, hyperspectral unmixing has been exploited to decompose mixed pixels into a group of pure materials (called endmembers) and their corresponding proportions (called abundances) [16,17].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Unmixing with Bandwise Generalized Bilinear Model

Liu

Cheng

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Generalized bilinear model (GBM) has received extensive attention in the field of hyperspectral nonlinear unmixing. Traditional GBM unmixing methods are usually assumed to be degraded only by additive white Gaussian noise (AWGN), and the intensity of AWGN in each band of hyperspectral image (HSI) is assumed to be the same. However, the real HSIs are usually degraded by mixture of various kinds of noise, which include Gaussian noise, impulse noise, dead pixels or lines, stripes, and so on. Besides, the intensity of AWGN is usually different for each band of HSI. To address the above mentioned issues, we propose a novel nonlinear unmixing method based on the bandwise generalized bilinear model (NU-BGBM), which can be adapted to the presence of complex mixed noise in real HSI. Besides, the alternative direction method of multipliers (ADMM) is adopted to solve the proposed NU-BGBM. Finally, extensive experiments are conducted to demonstrate the effectiveness of the proposed NU-BGBM compared with some other state-of-the-art unmixing methods.Keywords: additive white Gaussian noise (AWGN); hyperspectral images (HSIs); mixed noise; bandwise generalized bilinear model (BGBM); alternative direction method of multipliers (ADMM) some flexible models based on signal processing, such as post-nonlinear model [22], neural network model [23] and kernel model [24]. The second category includes some physical based models, such as intimate mixture model [25], bilinear mixture model (BMM) [26][27][28][29][30][31][32][33] and multilinear mixing model [34][35][36]. Among them, the BMM only takes the second-order scattering into consideration, while the higher-order interactions of light are ignored [18]. The reason is that the interactions of orders larger than two, not only have minor contribution for improving the unmixing accuracy than that of second-order scattering, but also bring in tremendous computational costs [21]. Several representative models known as the family of BMM have been proposed. The Nascimento model (NM) [26] is an extended LMM with additional virtual endmembers, the Fan's model (FM) is the truncated Taylor expansion of nonlinear mixing function [27], and the GBM [28] can be seen as the generalization of LMM and FM, which can efficiently deal with the assumptions in BMM. Different methods have been proposed for GBM unmixing of HSI, Halimi et al. developed a Bayesian algorithm to estimate the abundance and noise variance of the GBM [28]. Besides, they also proposed a pixel-wise unmixing method based on the gradient descent algorithm (GDA) [29]. Moreover, Yokoya et al. proposed the semi-nonnegative matrix factorization (semi-NMF) as a new optimization method for GBM based HSI unmixing [30]. Furthermore, Li et al. developed the bound projected optimal gradient method (BPOGM) for GBM unmixng, and it can achieve the optimal convergence rate of O( 1 k 2 ), where k denotes the number of iteration in BPOGM [31].Most unmixing methods based on the GBM are implicitly developed for Gaussian noise, and the underlying assumptio...

show abstract

SuperPCA: A Superpixelwise PCA Approach for Unsupervised Feature Extraction of Hyperspectral Imagery

Cited by 250 publications

References 63 publications

Hyperspectral Image Classification With Deep Metric Learning and Conditional Random Field

Hyperspectral Image Classification With Deep Metric Learning and Conditional Random Field

A Convolutional Neural Network With Mapping Layers for Hyperspectral Image Classification

Hyperspectral Unmixing with Bandwise Generalized Bilinear Model

Contact Info

Product

Resources

About