Optimized Dilated Convolutional Neural Network with Quantum Self-Attention Based on Hyper Spectral Remote Sensing Image Classification

Hyperspectral remote sensing image (HRSI) can provide additional spectral information of objects and have been widely used in many fields. However, due to the complex environment of the HRSI gathering area, collecting the labeled samples of HRSI is time-consuming and labor-intensive. The scarcity of labeled samples is one of the major difficulties for HRSI analysis and processing. In this letter, a spatial–spectral prototypical network (SSPN) for HRSI is proposed for solving the problem of lack of labeled samples. The contribution of this letter is threefold. First, we design a novel local pattern coding algorithm to combine the spatial and spectral information of HRSI pixels based on spatial neighborhood correlation. Then, a spatial–spectral feature extraction algorithm based on 1-D convolutional neural network (1-D-CNN) is suggested to learn the spatial–spectral metric space where HRSI pixels can be correctly classified with only a few labeled samples. Finally, a novel prototype representation for HRSI in spatial–spectral metric space is proposed to better classify the mixed pixels existing in HRSI. The experimental results on three popular HRSI data sets demonstrate that the proposed SSPN is significantly better than the traditional algorithms.

Abnormal target detection in hyperspectral remote sensing image is one of the hotspots in image research. The image noise generated in the detection process will lead to the decline of the quality of hyperspectral remote sensing image. In view of this, this paper proposes an abnormal target detection method of hyperspectral remote sensing image based on the convolution neural network. Firstly, the deep residual learning network model has been used to remove the noise in hyperspectral remote sensing image. Secondly, the spatial and spectral features of hyperspectral remote sensing images were used to optimize the clustering dictionary, and then the image segmentation containing target information is completed. Finally, the image was input into the deep convolution neural network with a dual classifier, and the network detects the abnormal target in the image. The test results of this algorithm show that the structural similarity of the denoised image is higher than 0.86, which shows that this method has good noise reduction performance, image details will not damage, segmentation effect is good, and it can obtain high-definition target image information and accurately detect abnormal targets in the image.

Hyperspectral remote sensing image (HSI) consists of hundreds of bands that contain rich space, radiation and spectral information. The high-dimensional data can also lead to the curse of dimensionality problem making it difficult to be used effectively. In this paper, we proposed a manifold learning algorithm to reduce the dimensionality for HSI data. For high dimensional datasets with continuous variables, it is often the case that the data points are arranged along with low dimensional structures, named manifolds, in the high dimensional space. Manifold learning aims to identifying those special low dimensional structures for subsequent usage such as classification or regression. However, many manifold learning algorithms perform an eigenvector analysis on a data similarity matrix whose size is N×N, where N is the number of data points. The memory complexity of the analysis is at least O(N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) that is not feasible for a regular computer to compute or storage for very large datasets. To solve this problem, we used statistical sampling methods to sample a subset of data points as landmarks. A skeleton of the manifold was then identified based on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding (LLE). We tested our algorithm on AVIRIS Salinas-A data set. The experimental results showed that the HSI dataset could be reduced to a lower-dimensional space for land use classification with good performance, and the main structure was preserved well.

To effectively utilize the rich spectral information of hyperspectral remote sensing images (HRSIs), the fractional Fourier transform (FRFT) feature of HRSIs is proposed to reflect the time-domain and frequency-domain characteristics of a spectral pixel simultaneously, and an FRFT order selection criterion is also proposed based on maximizing separability. Firstly, FRFT is applied to the spectral pixels, and the amplitude spectrum is taken as the FRFT feature of HRSIs. The FRFT feature is mixed with the pixel spectral to form the presented spectral and fractional Fourier transform mixed feature (SF2MF), which contains time–frequency mixing information and spectral information of pixels. K-nearest neighbor, logistic regression, and random forest classifiers are used to verify the superiority of the proposed feature. A 1-dimensional convolutional neural network (1D-CNN) and a two-branch CNN network (Two-CNNSF2MF-Spa) are designed to extract the depth SF2MF feature and the SF2MF-spatial joint feature, respectively. Moreover, to compensate for the defect that CNN cannot effectively capture the long-range features of spectral pixels, a long short-term memory (LSTM) network is introduced to be combined with CNN to form a two-branch network C-CLSTMSF2MF for extracting deeper and more efficient fusion features. A 3D-CNNSF2MF model is designed, which firstly performs the principal component analysis on the spa-SF2MF cube containing spatial information and then feeds it into the 3-dimensional convolutional neural network 3D-CNNSF2MF to extract the SF2MF-spatial joint feature effectively. The experimental results of three real HRSIs show that the presented mixed feature SF2MF can effectively improve classification accuracy.

The classification of hyperspectral remote sensing images (HSI) is an important task in the processing and application of hyperspectral images. Convolutional neural network (CNN) has significant advantages in the extraction and fusion of hyperspectral image spectrum and spatial features, so it has become a common method in the field of HSI classification. However, the spectral domain feature redundancy of hyperspectral images is very high, and the spatial domain feature structure is complex, which makes CNN more time-consuming and higher memory requirements in the feature extraction process. Based on this problem, lightweight networks with fewer parameters have gradually become the main application method in the field of HSI classification. In order to reduce the computational complexity of deep feature extraction and take into account the shallow features, a high-order nonlinear Ghost module is proposed on the basis of the original Ghost linear transformation module. Furthermore, in view of the independent characteristics of each dimension of HSI, a Trip-GhostNet is proposed, which simultaneously extracts and fuses features from three dimensions in a lightweight manner. According to the distribution characteristics of HSI, the influence of attention embedding methods in the high-order Ghost module of each branch on the feature extraction is compared and analyzed. The results show that the proposed model can reduce model calculations and improve classification accuracy, and is suitable for HSI classification problems.

ABSTRACTThis study introduces the attention mechanism in hyperspectral remote sensing image (HSI) classification which can strengthen the information provided by important features, and weaken the non-essential information. We introduced the Squeeze-and-Excitation (SE) block embedded in three-dimensional densely connected convolutional network (3D-DenseNet) to form 3D-SE-DenseNet for HSI classifications. This model can learn a powerful network with low training costs and fast convergence speed, and avoids overfitting on small sample datasets. Two different 3D-SE-DenseNet models of 3D-SE-DenseNet and 3D-SE-DenseNet-BC were set up. Results from experiments show that the 3D-SE-DenseNet performs well on the Indian Pines, Pavia University, Botswana, and Kennedy Space Centre datasets.

Graph neural network has excellent performance in obtaining the similarity relationship of samples, so it has been widely used in computer vision. But hyperspectral remote sensing image (HSI) has some problems such as data redundancy, noise, lack of labeled samples, and insufficient utilization of spatial information. These problems affect the accuracy of HSI classification using graph neural networks. To solve the above problems, this paper proposes graph-based semi-supervised learning with weighted features for HSI classification. The method proposed in this paper first uses the stacked autoencoder network to extract features, which is used to remove the redundancy of HSI data. Then, the similarity attenuation coefficient is introduced to improve the original feature weighting scheme. In this way, the contribution difference of adjacent pixels to the center pixel is reflected. Finally, to obtain more generalized spectral features, a shallow feature extraction mechanism is added to the stacked autoencoder network. And features that have good generalization can solve the problem of the lack of labeled samples. The experiment on three different types of datasets demonstrates that the proposed method in this paper can get better classification performance in the case of the scarcity of labeled samples than other classification methods.

Hyperspectral remote sensing (HRS) image classification is time-consuming and complex due to its wide spectral range and large number of samples. Factors such as heterogeneous behaviour, unbalanced class distributions, complex boundaries, multiple spectral bands, inconsistent samples, significant spatial variability, and interclass similarities further challenge image classification. The design of a robust classification model that addresses these challenges demands efficient pre-processing of input information, e.g., dimensionality reduction and representative feature extraction, with the ability to handle information uncertainty and to reduce computational complexity. In line with these objectives, we have proposed a classification model called FRELM-SAE, which utilises fuzzy granulation of input features, a rule-based extreme learning machine (ELM), and a stacked autoencoder (SAE). Fuzzy granulation and rule-based ELM address the generalisation aspects and the complexity of the decision-making process. The SAE reduces the noise from the input feature space and performs representative feature extraction. Various experiments demonstrate the proposed model’s performance in classifying two HRS images. The experimental results show its supremacy over related work across performance metrics, including overall accuracy, precision, recall, etc.

Due to the high dimensionality and high data redundancy of hyperspectral remote sensing images, it is difficult to maintain the nonlinear structural relationship in the dimensionality reduction representation of hyperspectral data. In this paper, a feature representation method based on high order contractive auto-encoder with nuclear norm constraint (CAE-HNC) is proposed. By introducing Jacobian matrix in the CAE of the nuclear norm constraint, the nuclear norm has better sparsity than the Frobenius norm and can better describe the local low dimension of the data manifold. At the same time, a second-order penalty term is added, which is the Frobenius norm of the Hessian matrix expressed in the hidden layer of the input, encouraging a smoother low-dimensional manifold geometry of the data. The experiment of hyperspectral remote sensing image shows that CAE-HNC proposed in this paper is a compact and robust feature representation method, which provides effective help for the ground object classification and target recognition of hyperspectral remote sensing image.

Reflectance inversion is a critical challenge in quantitative hyperspectral remote sensing, especially in rugged terrain. The under-/over-correction of reflectance caused by such terrain and its impacts on subsequent information extraction have not been well quantified or effectively eliminated. To improve surface spectral reflectance inversion under varying illumination, atmospheric, and terrain conditions, an integrated correction method for geometric, atmospheric, and terrain effects (ICGAT) is proposed. The method incorporates a coupled radiative transfer model that accounts for direct solar irradiance, diffuse sky irradiance, surface-atmosphere coupling irradiance, and irradiance from neighboring slope along the sun-terrain-target path. The geometric positioning and irradiance components are first computed, and followed by an iterative retrieval of reflectance, geometric resampling is subsequently applied to the reflectance, an uncertainty quantification is finally conducted in the process. Tests show that ICGAT significantly improves spectral consistency between neighboring shaded and sunny slopes, reducing the influence of terrain relief on reflectance, as well as retrieve high-accuracy surface reflectance in flat areas. Meanwhile, the uncertainty propagation analysis could reveal not only the fidelity of the retrieved reflectance but also the major sources of uncertainty.

Eggs are important nutritional foods in people's daily life. They are rich in protein and vitamins, as well as a variety of minerals like iron, calcium and phosphorus. Therefore, monitoring egg quality is always a focus problem that people are concerned about. This article breaks through traditional ideas and methods, proposes using hyperspectral remote sensing images to obtain the spectral characteristics of boiled yolk, and establishes the analysis model of egg quality. Through a large number of experiments on different types of eggs, the experimental results are effective, and this shows that the method proposed in this paper is feasible. It provides new ideas and methods for the examination of egg quality and the establishment of traceability system.

Hyperspectral remote sensing images (HSIs) provide invaluable information for environmental and agricultural monitoring, yet they are often degraded by atmospheric haze, which distorts spatial and spectral content and hinders downstream analysis. Progress in hyperspectral dehazing has been limited by the absence of paired real-haze benchmarks; most prior studies rely on synthetic haze or unpaired data, restricting fair evaluation and generalization. We present HyperHazeOff, the first comprehensive benchmark for hyperspectral dehazing that unifies data, tasks, and evaluation protocols. It comprises (i) RRealHyperPDID, 110 scenes with paired real-haze and haze-free HSIs (plus RGB images), and (ii) RSyntHyperPDID, 2616 paired samples generated using a physically grounded haze formation model. The benchmark also provides agricultural field delineation and land classification annotations for downstream task quality assessment, standardized train/validation/test splits, preprocessing pipelines, baseline implementations, pretrained weights, and evaluation tools. Across six state-of-the-art methods (three RGB-based and three HSI-specific), we find that hyperspectral models trained on the widely used HyperDehazing dataset fail to generalize to real haze, while training on RSyntHyperPDID enables significant real-haze restoration by AACNet. HyperHazeOff establishes reproducible baselines and is openly available to advance research in hyperspectral dehazing.

The extraction of concise and discriminative features from hyperspectral remote sensing images (HSIs) holds great significance for land cover classification tasks. Nevertheless, the intricate spatial-spectral tensor structure and inaccurate class labels undermine the performance of existing vector-based or Tucker tensor-based feature dimensionality reduction (DR) approaches. To tackle this problem, we propose an Adaptive Tensor-Ring Manifold Maintaining Embedding (ATRMME) approach for HSI feature DR in the presence of noisy labels. Firstly, a tensor-ring subspace representation theory is established to characterize the low-dimensional hyperspectral tensor subspace. To mine concise features from complex spatial-spectral data, differing from existing Tucker-based DR methods that involve exorbitant parameter overheads, a nuclear norm-constrained Tensor-Ring (TR) feature representation term is designed. This term enables the compression of key features within the low-dimensional subspace with a linear parameter cost. For the adaptive perception and capture of the manifold structure under noisy labels, an adaptive adjacency matrix is constructed, and the adjacency relationships are reorganized based on the TR feature distribution. To guarantee the effective execution of model training, an alternating optimization algorithm is developed for parameter estimation. Experimental results on multiple hyperspectral datasets verify that the ATRMME approach exhibits strong robustness against noisy labels, outperforms conventional vector-based and Tucker tensor-based methods, and has lower parameter requirements.

Research on spatial information is a hot topic in hyperspectral remote-sensing image (HSI) exploitation. This paper defines a spatial correlation filter to study the spatial variation characteristics and intensity of regionalized variables. Unlike existing spatial information expression methods based on theoretical model, the novel filter takes multi-scale and multi-directional spatial structure features into account and visualizes them, which is model-free and more comprehensive. Further, SCFB model constructed by the filter banks is proposed for pixel-wise classification of HSI and performs well when replacing the classifier component with multiple machine-learning algorithms. Accurate classification on two classic hyperspectral datasets with approximately 3% training samples and on one large dataset with 0.544% training samples indicate that the model is promising in small samples learning. In particular, supervised linear discriminant analysis (LDA) used in the feature subspace optimization part of the model significantly outperforms the other two spectral strategies. Most notably, the model is not only superior to the traditional machine-learning methods considering spectral information only, but also has advantages in accuracy, the number of learnable kernel parameters and time-consuming compared with equal-layer convolution neural network.

This paper explores the problem of recovering the discriminative representation of a hyperspectral remote sensing image (HRSI), which suffers from spectral variations, to boost its classification accuracy. To tackle this challenge, we propose a new method, namely local-global balanced low-rank approximation (GLB-LRA), which can increase the similarity between pixels belonging to an identical category while promoting the discriminability between pixels of different categories. Specifically, by taking advantage of the particular structural spatial information of HRSIs, we exploit the low-rankness of an HRSI robustly in both spatial and spectral domains from the perspective of local and global balance. We mathematically formulate GLB-LRA as an explicit optimization problem and propose an iterative algorithm to solve it efficiently. Experimental results over three commonly-used benchmark datasets demonstrate the significant superiority of our method over state-of-the-art methods.