Precise object classification based on Hyperspectral imagery with limited training data presents a challenging task. We propose a tensor-based dictionary self-taught learning (TDSL) classification method to provide some insight into these challenges. The idea of TDSL is to utilize a small amount of unlabeled data to improve the supervised classification. The TDSL trains tensor feature extractors from unlabeled data, extracts joint spectral-spatial tensor features and performs classification on the labeled data set. These two data sets can be gathered over different scenes even by different sensors. Therefore, TDSL can complete cross-scene and cross-sensor classification tasks. For training tensor feature extractors on unlabeled data, we propose a sparse tensor-based dictionary learning algorithm for three-dimensional samples. In the algorithm, we initialize dictionaries using Tucker decomposition and update these dictionaries based on the K higher-order singular value decomposition. These dictionaries are feature extractors, which are used to extract sparse joint spectral-spatial tensor features on the labeled data set. To provide classification results, the support vector machine as the classifier is applied to the tensor features. The TDSL with the majority vote (TDSLMV) can reduce the misclassified pixels in homogenous regions and at the edges of different homogenous regions, which further refines the classification. The proposed methods are evaluated on Indian Pines, Pavia University, and Houston2013 datasets. The classification results show that TDSLMV achieves as high as 99.13%, 99.28%, and 99.76% accuracies, respectively. Compared with several state-of-the-art methods, the classification accuracies of the proposed methods are improved by at least 2.5%.

/pdf/tensor-dictionary-self-taught-learning-classification-method-2mytinol.pdf

Tensor Dictionary Self-Taught Learning Classification Method for Hyperspectral Image

Due to a lack of labeled samples, deep learning methods generally tend to have poor classification performance in practical applications. Few-shot learning (FSL), as an emerging learning paradigm, has been widely utilized in hyperspectral image (HSI) classification with limited labeled samples. However, the existing FSL methods generally ignore the domain shift problem in cross-domain scenes and rarely explore the associations between samples in the source and target domain. To tackle the above issues, a graph-based domain adaptation FSL (GDAFSL) method is proposed for HSI classification with limited training samples, which utilizes the graph method to guide the domain adaptation learning process in a uniformed framework. First, a novel deep residual hybrid attention network (DRHAN) is designed to extract discriminative embedded features efficiently for few-shot HSI classification. Then, a graph-based domain adaptation network (GDAN), which combines graph construction with domain adversarial strategy, is proposed to fully explore the domain correlation between source and target embedded features. By utilizing the fully explored domain correlations to guide the domain adaptation process, a domain invariant feature metric space is learned for few-shot HSI classification. Comprehensive experimental results conducted on three public HSI datasets demonstrate that GDAFSL is superior to the state-of-the-art with a small sample size.

/pdf/graph-based-domain-adaptation-few-shot-learning-for-2t2oslil.pdf

Graph-Based Domain Adaptation Few-Shot Learning for Hyperspectral Image Classification

Haze and mist caused by air quality, weather, and other factors can reduce the clarity and contrast of images captured by cameras, which limits the applications of automatic driving, satellite remote sensing, traffic monitoring, etc. Therefore, the study of image dehazing is of great significance. Most existing unsupervised image-dehazing algorithms rely on a priori knowledge and simplified atmospheric scattering models, but the physical causes of haze in the real world are complex, resulting in inaccurate atmospheric scattering models that affect the dehazing effect. Unsupervised generative adversarial networks can be used for image-dehazing algorithm research; however, due to the information inequality between haze and haze-free images, the existing bi-directional mapping domain translation model often used in unsupervised generative adversarial networks is not suitable for image-dehazing tasks, and it also does not make good use of extracted features, which results in distortion, loss of image details, and poor retention of image features in the haze-free images. To address these problems, this paper proposes an end-to-end one-sided unsupervised image-dehazing network based on a generative adversarial network that directly learns the mapping between haze and haze-free images. The proposed feature-fusion module and multi-scale skip connection based on residual network consider the loss of feature information caused by convolution operation and the fusion of different scale features, and achieve adaptive fusion between low-level features and high-level features, to better preserve the features of the original image. Meanwhile, multiple loss functions are used to train the network, where the adversarial loss ensures that the network generates more realistic images and the contrastive loss ensures a meaningful one-sided mapping from the haze image to the haze-free image, resulting in haze-free images with good quantitative metrics and visual effects. The experiments demonstrate that, compared with existing dehazing algorithms, our method achieved better quantitative metrics and better visual effects on both synthetic haze image datasets and real-world haze image datasets.

/pdf/one-sided-unsupervised-image-dehazing-network-based-on-3jroan1r.pdf

One-Sided Unsupervised Image Dehazing Network Based on Feature Fusion and Multi-Scale Skip Connection

Ground subsidence is the main cause of vegetation degradation in mining areas. It is of great significance to study the effects of ground subsidence on vegetation. At present, few studies have analyzed the effects of ground subsidence on vegetation from different scales. However, the conclusions on different scales may differ. In this experiment, chlorophyll content was used as an indicator of vegetation degradation. We conducted a long-term field survey in the Lijiahao coalfield in China. Based on field survey data and remote sensing images, we analyzed the effects of ground subsidence on chlorophyll content from two scales (leaf scale and canopy scale) and summarized the similarities and differences. We found that, regardless of leaf scale or canopy scale, the effects of subsidence on chlorophyll content have the following three characteristics: (1) mining had the least effect on chlorophyll content in the neutral area, followed by the compression area, and the greatest effect on chlorophyll content in the extension area; (2) subsidence had a slight effect on chlorophyll content of Caragana korshins, but a serious effect on chlorophyll content of Stipa baicalensis; (3) chlorophyll content was not immediately affected when the ground sank. It was the cumulative subsidence that affects chlorophyll content. The difference between leaf scale and canopy scale was that the chlorophyll content at canopy scale is more affected by mining. This means that when assessing vegetation degradation, the results obtained by remote sensing were more severe than those measured in the field. We believe that this is because the canopy chlorophyll content obtained by remote sensing is also affected by the plant canopy structure. We recommend that mining and ecological restoration should be carried out concurrently, and that ground fissures should be taken as the focus of ecological restoration. In addition, Caragana korshins ought to be widely planted. Most importantly, managers should assess the effects of ground subsidence on vegetation on different scales. However, managers need to be aware of differences at different scales.

/pdf/effects-of-ground-subsidence-on-vegetation-chlorophyll-2dscr6cd.pdf

Effects of Ground Subsidence on Vegetation Chlorophyll Content in Semi-Arid Mining Area: From Leaf Scale to Canopy Scale

Recently, deep learning methods, particularly the convolutional neural networks, have been extensively employed for extracting spectral–spatial features in hyperspectral image (HSI) classification tasks, yielding promising results. Conventional methods often use small image patches as input and combine spectral and spatial features with fixed strategies. However, the equal treatment of all pixels within heterogeneous patches can negatively impact feature extraction performance. In this article, we propose a semisupervised dual-branch spectral–spatial adversarial representation learning (SSARL) method for HSI classification. SSARL adaptively assigns attention weights to different pixels and adds a spectral constraint to spatial features. Our approach consists of three main components: 1) a dual-branch framework designed to independently extract spectral and spatial information from pixel and patch samples; 2) a class consistency loss that adaptively combines spectral and spatial classification results, mitigating the adverse effects of heterogeneous patches and enabling appropriate feature selection for various situations; and 3) the deep learning model on the labeled sample size by adding the adversarial representation module and conditional entropy to two branches, reducing the deep learning model's reliance on labeled sample size. Experimental results demonstrate that SSARL outperforms competitive methods on small-sized (0.3%–5%) labeled samples and exhibits superior performance for boundary test pixels.

https://ieeexplore.ieee.org/ielx7/4609443/4609444/10168240.pdf

Dual-Branch Spectral–Spatial Adversarial Representation Learning for Hyperspectral Image Classification With Few Labeled Samples

Hyperspectral image (HSI) classification has attracted widespread concern in recent years. However, due to the complexity of the HSI gathering environment, it is difficult to obtain a great number of HSI labeled samples. Therefore, how to effectively extract the spatial–spectral feature with small-scale training samples is the crucial point of HSI classification. In this paper, a novel fusion framework for small-sample HSI classification is proposed to fully combine the advantages of multidimensional CNN and handcrafted features. Firstly, a 3D fuzzy histogram of oriented gradients (3D-FHOG) descriptor is proposed to fully extract the handcrafted spatial–spectral feature of HSI pixels, which is suggested to be more robust by overcoming the local spatial–spectral feature uncertainty. Secondly, a multidimensional Siamese network (MDSN), which is updated by minimizing both contrastive loss and classification loss, is designed to effectively exploit the CNN-based spatial–spectral features from multiple dimensions. Finally, the proposed MDSN combined with 3D-FHOG is utilized for small-sample HSI classification to verify the effectiveness of our proposed fusion framework. The experimental results on three public data sets indicate that the proposed MDSN combined with 3D-FHOG is significantly better than the representative handcrafted feature-based and CNN-based methods, which in turn demonstrates the superiority of the proposed fusion framework.

https://www.mdpi.com/2072-4292/14/15/3796/pdf?version=1660031901

Fusion of Multidimensional CNN and Handcrafted Features for Small-Sample Hyperspectral Image Classification

Due to the complex environment of hyperspectral image (HSI) gathering area, it is difficult to obtain a large number of labeled samples for HSI. Therefore, how to effectively achieve the HSI few-shot classification is a hot spot of current research. Prototypical network (PN) is one of the most classical few-shot learning algorithms, which has been widely employed for few-shot image classification and few-shot object detection. However, existing PN-based algorithms for HSI only utilize the single-scale spatial–spectral feature extracted from the last layer, ignoring the semantic information with different scales contained in the other layers. To solve this problem, a novel multiscale spatial–spectral PN (MSSPN) is proposed in this letter. The contribution of this letter is threefold. First, a multiscale spatial–spectral feature extraction algorithm based on ladder structure is proposed to effectively achieve the integration of spatial–spectral features with different scales. Second, with the theory of ladder-structure-based extraction algorithm, we design a multiscale spatial–spectral prototype representation, which is suggested to be more robust and effective in the multiscale spatial–spectral metric space. Finally, our proposed MSSPN has the advantage of expandability, and can be easily applied for the other PN-based few-shot learning methods. The experimental results on HSI few-shot classification indicate that our proposed MSSPN algorithm can achieve higher accuracy than the representative HSI classifiers and the existing PN-based algorithms.

A Multiscale Spatial–Spectral Prototypical Network for Hyperspectral Image Few-Shot Classification

/pdf/estimation-of-mangrove-canopy-chlorophyll-content-using-3er4wike.pdf

Estimation of mangrove canopy chlorophyll content using hyperspectral image and stacking ensemble regression algorithm

The main idea of few-shot learning is to learn a generalized model which can realize the transfer of knowledge from the source domain to the target domain with a small number of labeled samples. However, existing few-shot learning algorithms for hyperspectral image (HSI) simply and directly extract the spatial-spectral features from the three-dimensional local neighborhood of HSI pixels. In other words, it lacks an effective mathematical models for analyzing and preprocessing the local spatial and spectral information of HSI pixels. Therefore, a HSI few-shot classification algorithm based on analogous tensor decomposition (HSIFC-ATD) is proposed in this paper. By applying the analogous tensor decomposition to the 3-D local spatial-spectral tensor of HSI pixels, redundant information contained in the 3-D local spatial-spectral tensor is effectively removed, which improves the efficiency of subsequent HSI few-shot classification. The experimental results show that the proposed HSIFC-ATD algorithm achieves excellent classification performance on HSI few-shot classification.

Li Zhang

Papers

Fusion of Multidimensional CNN and Handcrafted Features for Small-Sample Hyperspectral Image Classification

A Multiscale Spatial–Spectral Prototypical Network for Hyperspectral Image Few-Shot Classification

Estimation of mangrove canopy chlorophyll content using hyperspectral image and stacking ensemble regression algorithm

Hyperspectral Image Few-shot Classification Based on Analogous Tensor Decomposition