Hyperspectral Imaging For Detection Research Articles

Greedy Ensemble Hyperspectral Anomaly Detection

Hyperspectral images include information from a wide range of spectral bands deemed valuable for computer vision applications in various domains such as agriculture, surveillance, and reconnaissance. Anomaly detection in hyperspectral images has proven to be a crucial component of change and abnormality identification, enabling improved decision-making across various applications. These abnormalities/anomalies can be detected using background estimation techniques that do not require the prior knowledge of outliers. However, each hyperspectral anomaly detection (HS-AD) algorithm models the background differently. These different assumptions may fail to consider all the background constraints in various scenarios. We have developed a new approach called Greedy Ensemble Anomaly Detection (GE-AD) to address this shortcoming. It includes a greedy search algorithm to systematically determine the suitable base models from HS-AD algorithms and hyperspectral unmixing for the first stage of a stacking ensemble and employs a supervised classifier in the second stage of a stacking ensemble. It helps researchers with limited knowledge of the suitability of the HS-AD algorithms for the application scenarios to select the best methods automatically. Our evaluation shows that the proposed method achieves a higher average F1-macro score with statistical significance compared to the other individual methods used in the ensemble. This is validated on multiple datasets, including the Airport–Beach–Urban (ABU) dataset, the San Diego dataset, the Salinas dataset, the Hydice Urban dataset, and the Arizona dataset. The evaluation using the airport scenes from the ABU dataset shows that GE-AD achieves a 14.97% higher average F1-macro score than our previous method (HUE-AD), at least 17.19% higher than the individual methods used in the ensemble, and at least 28.53% higher than the other state-of-the-art ensemble anomaly detection algorithms. As using the combination of greedy algorithm and stacking ensemble to automatically select suitable base models and associated weights have not been widely explored in hyperspectral anomaly detection, we believe that our work will expand the knowledge in this research area and contribute to the wider application of this approach.

Spectrum-Induced Transformer-Based Feature Learning for Multiple Change Detection in Hyperspectral Images

Spectrum-Induced Transformer-Based Feature Learning for Multiple Change Detection in Hyperspectral Images

Self-Paced Probabilistic Collaborative Representation for Anomaly Detection of Hyperspectral Images

Self-Paced Probabilistic Collaborative Representation for Anomaly Detection of Hyperspectral Images

Hyperspectral Anomaly Detection With Tensor Average Rank and Piecewise Smoothness Constraints.

Anomaly detection in hyperspectral images (HSIs) has attracted considerable interest in the remote-sensing domain, which aims to identify pixels with different spectral and spatial features from their surroundings. Most of the existing anomaly detection methods convert the 3-D data cube to a 2-D matrix composed of independent spectral vectors, which destroys the intrinsic spatial correlation between the pixels and their surrounding pixels, thus leading to considerable degradation in detection performance. In this article, we develop a tensor-based anomaly detection algorithm that can effectively preserve the spatial-spectral information of the original data. We first separate the 3-D HSI data into a background tensor and an anomaly tensor. Then the tensor nuclear norm based on the tensor singular value decomposition (SVD) is exploited to characterize the global low rank existing in both the spectral and spatial directions of the background tensor. In addition, the total variation (TV) regularization is incorporated due to the piecewise smoothness. For the anomaly component, the l2.1 norm is exploited to promote the group sparsity of anomalous pixels. In order to improve the ability of the algorithm to distinguish the anomaly from the background, we design a robust background dictionary. We first split the HSI data into local clusters by leveraging their spectral similarity and spatial distance. Then we develop a simple but effective way based on the SVD to select representative pixels as atoms. The constructed background dictionary can effectively represent the background materials and eliminate anomalies. Experimental results obtained using several real hyperspectral datasets demonstrate the superiority of the proposed method compared with some state-of-the-art anomaly detection algorithms.

A Preliminary Study on the Utilization of Hyperspectral Imaging for the On-Soil Recognition of Plastic Waste Resulting from Agricultural Activities

Plastic in agriculture is frequently used to protect crops and its use boosts output, enhances food quality, contributes to minimize water consumption, and reduces the environmental impacts of agricultural activities. On the other hand, end-of-life plastic management and disposal are the main issues related to their presence in this kind of environment, especially in respect of plastic degradation, if not properly handled (i.e., storage places directly in contact with the ground, exposure of stocks to meteoric agents for long periods, incorrect or incomplete removal). In this study, the possibility of using an in situ near infrared (NIR: 1000–1700 nm) hyperspectral imaging detection architecture for the recognition of various plastic wastes in agricultural soils in order to identify their presence and also assess their degradation from a recovery/recycling perspective was explored. In more detail, a Partial Least Squares—Discriminant Analysis (PLS-DA) classifier capable of identifying plastic waste from soil was developed, implemented, and set up. Results showed that hyperspectral imaging, in combination with chemometric approaches, allows the utilization of a rapid, non-destructive, and non-invasive analytical approach for characterizing the plastic waste produced in agriculture, as well as the potential assessment of their lifespan.

Dual-discriminator conditional generative adversarial network optimized with hybrid manta ray foraging optimization and volcano eruption algorithm for hyperspectral anomaly detection

A significant task on remote sensing field is anomaly detection in hyperspectral images (HSI). Many scientists have created several relevant techniques developing deep network-based ways for hyperspectral anomaly detection (HAD) in the recent years. Dual-discriminator conditional generative adversarial network (DcGAN) optimized with hybrid Manta ray foraging optimization algorithm and Volcano eruption algorithm (Hyb-MRF-VEA) is proposed for anomaly identification in Hyperspectral images (DcGAN-HAD) in this manuscript. The three steps of the proposed methodology are data preparation, reconstruction, and detection. Background purification is a stage in the data preparation process that trains the deep network unsupervised. In the reconstruction step, DcGAN method is executed in spatial, spectral, combined spectral-spatial domains. The novelty of DcGAN method is to produce the hyper spectral images (HSIs) that are closer to real ones. Among original and image pixels the reconstruction error map (REM) is computed. The pixel weights are obtained with respect to REM at the detection step. Finally, to obtain the final detection map, the original with reconstructed image is subject to spatial and spectral joint anomaly detector. For scaling the optimal parameters and make sure exact detection, DcGAN approach not exposes any optimization techniques adoption. Therefore, in this work, a Hyb-MRF-VEA with optimize DcGAN weight parameters. The proposed DcGAN-HAD system is done in PyTorch and its efficacy is calculated with certain performances metrics, like, area under ROC curve (AUC) metric, precision, computation time, accuracy. For hyper spectral remote sensing scenes dataset of PAVIA CENTER ANDUNIVERSITY, the proposed DcGAN-HAD method attains 22.15%, 58.97% and 34.29% higher accuracy compared with the existing methods.

Background Reconstruction via 3D-Transformer Network for Hyperspectral Anomaly Detection

Recently, autoencoder (AE)-based anomaly detection approaches for hyperspectral images (HSIs) have been extensively proposed; however, the reconstruction accuracy is susceptible to the anomalies and noises. Moreover, these AE-based anomaly detectors simply compress each pixel into a hidden-layer with a lower dimension and then reconstruct it, which does not consider the spatial properties among pixels. To solve the above issues, this paper proposes a background reconstruction framework via a 3D-transformer (3DTR) network for anomaly detection in HSIs. The experimental results on both synthetic and real hyperspectral datasets demonstrate that the proposed 3DTR network is able to effectively detect most of the anomalies by comprehensively considering the spatial correlations among pixels and the spectral similarity among spectral bands of HSIs. In addition, the proposed method exhibits fewer false alarms than both traditional and state-of-the-art (including model-based and AE-based) anomaly detectors owing to the adopted pre-detection procedure and the proposed novel patch-generation method in this paper. Moreover, two ablation experiments adequately verified the effectiveness of each component in the proposed method.

Self-supervised learning with deep clustering for target detection in hyperspectral images with insufficient spectral variation prior

Target detection in hyperspectral images (HSIs) mainly relies on the spectral information of the target prior. However, prior spectra with precise variation information are often hard to obtain, and the “different objects with the same spectrum” phenomena in complex environments make it difficult to detect the variational targets. To mitigate this problem, self-supervised learning (SSL) is introduced to mine the spectral variation in the HSIs to supplement the priors. The SSL-based detector, termed SSDCTD, is optimized with unlabeled spectra using an unsupervised pretext task and restricted with prior spectra in an end-to-end way. A deep clustering-based pretext task is designed, which utilizes the discriminative features among different substances to cluster the spectra in HSIs into several classes. Besides, we simultaneously optimize the detector to classify the priors into the target cluster. The combination of exploiting variational features from HSIs and supervision of target priors helps the proposed detector to make a great balance between target detectability (TD) and background suppressibility (BS). Experiments on four real datasets validate the superior performance of the proposed detector over several state-of-the-art detectors in multiple criteria.

Adaptive convolution kernel network for change detection in hyperspectral images.

Feature extraction is a key step in hyperspectral image change detection. However, many targets with great various sizes, such as narrow paths, wide rivers, and large tracts of cultivated land, can appear in a satellite remote sensing image at the same time, which will increase the difficulty of feature extraction. In addition, the phenomenon that the number of changed pixels is much less than unchanged pixels will lead to class imbalance and affect the accuracy of change detection. To address the above issues, based on the U-Net model, we propose an adaptive convolution kernel structure to replace the original convolution operations and design a weight loss function in the training stage. The adaptive convolution kernel contains two various kernel sizes and can automatically generate their corresponding weight feature map during training. Each output pixel obtains the corresponding convolution kernel combination according to the weight. This structure of automatically selecting the size of the convolution kernel can effectively adapt to different sizes of targets and extract multi-scale spatial features. The modified cross-entropy loss function solves the problem of class imbalance by increasing the weight of changed pixels. Study results on four datasets indicate that the proposed method performs better than most existing methods.

Spatial Anomaly Detection in Hyperspectral Imaging Using Optical Neural Networks

Hyperspectral imaging is a widely used technology, yet hard to implement in real-time anomaly detection due to its extensive data flow volume. An auto-encoder structured hybrid optical-electrical neural network method is proposed in this work that realizes feature exaction and anomaly detection during the hyperspectral data acquisition process to address such issues. In the proposed method, a digital micromirror device functions as the core optical processor to extract low-level features from the hyperspectral data flow. Weight binarization and a conditional sub-network are utilized to suit optical computation. Pretraining by artificial data is implemented to ease the training data burden. Case studies on defect detection and foreign object detection have demonstrated that the proposed method can significantly reduce the sampling time by orders of magnitude without loss of detection accuracy.

From Trained to Untrained: A Novel Change Detection Framework Using Randomly Initialized Models With Spatial–Channel Augmentation for Hyperspectral Images

Deep learning approaches have been extensively applied to change detection in hyperspectral images (HSIs). However, the majority of them encounter scarcity of training samples or rely on complex structures and learning strategies. Although untrained change detection models have been proved to be effective in relief above problems, they were constructed using regular convolutions and treated spatial locations and channels equally, which are insufficient to extract discriminative features and lead to limited accuracy. Given this, a novel untrained framework using randomly initialized models with spatial-channel augmentation (RICD) is proposed for HSI change detection in this paper. It consists of two major modules: 1) an enhanced feature extraction network using successive dilation-deformable feature extraction blocks, which can extract multiscale spatial-spectral features over unfixed sampling locations. It enlarges the field of view of convolutions and takes arbitrary neighborhood into consideration, which helps to increase the discriminativeness of the extracted features; 2) a change sensitive feature augmentation and comparison module integrating feature selection and spatial-channel augmentation strategies, which can exploit spatial context and channel importance. It magnifies difference between changed pixels and unchanged ones and emphasizes contribution of significant channels of the selected change sensitive features. Despite that convolution operations are included in RICD, all the weights are untrained and fixed once they are randomly initialized, indicating that the RICD can work in an unsupervised manner. Its performance is tested over three widely used hyperspectral datasets. Quantitative and qualitative comparisons with several state-of-the-art unsupervised methods reveal the effectiveness of the RICD method.

Corrections to “Anomaly Detection in Hyperspectral Images via Regularization by Denoising”

Corrections to “Anomaly Detection in Hyperspectral Images via Regularization by Denoising”

A new spectral and spatial framework for detecting buildings with special roofing in hyperspectral images

One of the analyses in hyperspectral images is target detection. With recent developments and the creation of high spatial resolution images, the need to use both spectral and spatial information in the target detection has increased. Recently, an effective approach for spectral and spatial classification has been proposed using minimum spanning forest (MSF) algorithm. It was attempted to improve this approach for target detection in hyperspectral images. In the proposed method, the spectral image was primarily segmented using the watershed algorithm. Afterwards, for the objects resulting from segmentation, five spatial properties of area, environment, strength, meaning intensity, and entropy were extracted. Finally, the detection operation was performed utilizing the marker-based MSF algorithm. The above-mentioned techniques were applied to three hyperspectral images, first Toulouse, second Toulouse and Quebec. The results of quantitative and qualitative evaluations showed that the proposed method improved the kappa coefficient by 40, 34 and 23% in comparison with the spectral angle measurement (SAM) algorithm in the first Toulouse, second Toulouse and Quebec images, respectively.

FUSING MULTIPLE UNTRAINED NETWORKS FOR HYPERSPECTRAL CHANGE DETECTION

Abstract. Change detection in hyperspectral images is challenging due to the presence of a large number of spectral bands. Due to the differences in band composition, a deep model trained on one hyperspectral sensor cannot be reused on another hyperspectral sensor. This challenge can be tackled by using untrained models as feature extractor for change detection in hyperspectral images. However, results produced by such a strategy may show variance if the untrained model is slightly perturbed. Different change detection maps are produced from different versions of the untrained model. We propose a decision fusion based strategy that can combine such different results and produce a final change detection map that retains the change information from all change maps. This approach improves the change detection performance and also improves reliability of the result. Experimental results on two publicly available hyperspectral datasets show the effectiveness of the proposed approach.

Unsupervised Change Detection in Hyperspectral Images using Principal Components Space Data Clustering

Change detection of hyperspectral images is a very important subject in the field of remote sensing application. Due to the large number of bands and the high correlation between adjacent bands in the hyperspectral image cube, information redundancy is a big problem, which increases the computational complexity and brings negative factor to detection performance. To address this problem, the principal component analysis (PCA) has been widely used for dimension reduction. It has the capability of projecting the original multi-dimensional hyperspectral data into new eigenvector space which allows it to extract light but representative information. The difference image of the PCA components is obtained by subtracting the two dimensionality-reduced images, on which the change detection is considered as a binary classification problem. The first several principal components of each pixel are taken as a feature vector for data classification using k-means clustering with k=2, where the two classes are changed pixels and unchanged pixels, respectively. The centroids of two clusters are determined by iteratively finding the minimum Euclidean distance between pixel’s eigenvectors. Experiments on two publicly available datasets have been carried out and evaluated by overall accuracy. The results have validated the efficacy and efficiency of the proposed approach.

Self-supervised learning-based oil spill detection of hyperspectral images

Self-supervised learning-based oil spill detection of hyperspectral images

Siamese Network Ensembles for Hyperspectral Target Detection with Pseudo Data Generation

Target detection in hyperspectral images (HSIs) aims to distinguish target pixels from the background using knowledge gleaned from prior spectra. Most traditional methods are based on certain assumptions and utilize handcrafted classifiers. These simple models and assumptions’ failure restrict the detection performance under complicated background interference. Recently, based on the convolutional networks, many supervised deep learning detectors have outperformed the traditional methods. However, these methods suffer from unstable detection, heavy computation burden, and optimization difficulty. This paper proposes a Siamese fully connected based target detector (SFCTD) that comprises nonlinear feature extraction modules (NFEMs) and cosine distance classifiers. Two NFEMs, which extract discriminative spectral features of input spectra-pairs, are based on fully connected layers for efficient computing and share the parameters to ease the optimization. To solve the few samples problem, we propose a pseudo data generation method based on the linear mixed model and the assumption that background pixels are dominant in HSIs. For mitigating the impact of stochastic suboptimal initialization, we parallelly optimize several Siamese detectors with small computation burdens and aggregate them as ensembles in the inference time. The network ensembles outperform every detector in terms of stability and achieve an outstanding balance between background suppression and detection rate. Experiments on multiple data sets demonstrate that the proposed detector is superior to the state-of-the-art detectors.

Laplacian matrix graph for anomaly target detection in hyperspectral images

To improve the accuracy of abnormal target detection in hyperspectral images, an abnormal target detection method based on Laplacian matrix graph (LGD) is proposed. The method makes full use of the spatial and spectral information of hyperspectral abnormal targets by constructing the full-connection graph and the nearest neighbour matrix obtained by the Gaussian kernel function. In the graph, the total variation of the graph signal calculated by the Laplacian matrix is taken as the evaluation function to judge the abnormal target, so as to realize the detection of abnormal pixels. It avoids the matrix inversion calculation that must be carried out in the conventional detection algorithms and the complexity is reduced. Compared with other detection algorithms on three different data sets, the experiment results show that the proposed algorithm presents obvious advantages in detection accuracy and excellent utility in practice.

Ensemble-Based Information Retrieval With Mass Estimation for Hyperspectral Target Detection

Given the prior information of the target, hyperspectral target detection focuses on exploiting spectral differences to separate objects of interest from the background, which can be treated as information retrieval (IR) task in machine learning (ML). Most traditional detection methods work in the original feature space and rely heavily on specific assumptions, which cannot guarantee effective extraction of features for the target and background in hyperspectral images (HSIs). Mass estimation (ME) is a base modeling mechanism that has been proven to effectively solve problems in IR and is not restricted by specific assumptions. In this article, we propose a novel target detection method through ensemble-based IR with ME (EIRME). By directly deriving the ordering from a sample set to rank data points, ME provides a simple and straightforward ranking measure to ensure that points similar to the given target are far away from dissimilar points. For the estimation of mass distribution, the proposed method utilizes a tree-structured mapping to generate a feature space, in which the separability of the target and background is further improved. In particular, to break through the technical difficulty that the direct migration of IR methods with mass measure cannot specifically meet the high-precision requirements of target detection in HSIs, we develop a specialized measurement, topological mass, which innovatively combines the mass measure with tree topology to quantify the spectral difference for detection output. Moreover, the IR with ME based on parallel measurements through ensemble trees provides a robust solution with better generalization capacity and higher precision for hyperspectral target detection, facilitating practical applications. Experimental results on benchmark HSI datasets prove that the specialized measurement that we developed successfully overcomes the drawbacks of the direct migration of IR methods with ME and exhibits unique advantages. In addition, comparisons with the most classic and advanced detection algorithms demonstrate the superiority of the proposed method.

Kernel-Based Decomposition Model With Total Variation and Sparsity Regularizations via Union Dictionary for Nonlinear Hyperspectral Anomaly Detection

Many linear approaches have been extensively proposed for the anomaly detection problem in hyperspectral images (HSIs), while nonlinear approaches have been rarely studied although most practical cases are nonlinear. Moreover, these existing nonlinear methods simply nonlinearly map each pixel into a high-dimensional space, which does not describe complex light scattering effects between endmembers. To address the above issues, this paper proposes an endmember-kernel-based decomposition model with total variation and sparsity regularizations via union dictionary for the nonlinear anomaly detection in HSIs. The proposed decomposition model utilizes endmember-kernel theory to handle nonlinear interactions between atoms in the dictionary, allowing for effective characterization of complex light scattering effects. By using this endmember-kernel-based decomposition model, a hyperspectral imagery can be decomposed into three components: anomaly, background, and noise. To separate these components effectively, the total variation (TV) and sparsity regularizations are incorporated into the decomposition model to characterize the spatial properties of the background and the anomaly, respectively. Besides, we present a novel construction framework of union dictionary that combines superpixel segmentation and clustering methods sequentially to achieve more accurate dictionary representation capabilities. Finally, the anomalous level of a tested pixel is calculated by the abundances associated with the anomaly dictionary. The experimental results on both synthetic and real hyperspectral data sets demonstrate that the proposed method outperforms several linear and nonlinear state-of-the-art anomaly detectors.