Single-image super-resolution (SISR) techniques attempt to reconstruct the finer resolution version of a given image from its coarser version. In the SISR of hyperspectral data sets, the simultaneous consideration of spectral bands is crucial for ensuring the spectral fidelity. However, the high spectral resolution of these data sets affects the performance of conventional approaches. This research proposes the design of 3-D convolutional neural network (CNN)-based SISR architectures that can map the spatial-spectral characteristics of hypercubes to a finer spatial resolution. The proposed approaches facilitate the simultaneous optimization of sparse codes and dictionaries with regard to the super-resolution objective. Our main hypothesis is that the consideration of spectral aspects is essential for the spatial enhancement of hyperspectral images. Also, we propose that the regularized deconvolution of a coarser-scale hypercube, using learned 3-D filters, yields the required high-resolution version. Based on these hypotheses, a convolution-deconvolution framework is proposed to super-resolve the hypercubes in parallel with the reconstruction of a set of regularizing features. Novel sparse code optimization sub-networks proposed in this article give better performance than the existing strategies. The endmember similarities and hyperspectral image prior are considered while designing the proposed loss functions. In order to improve the generalizability, a collaborative spectral unmixing strategy is employed to refine the spectral base of the super-resolved result. The spatial-spectral accuracy of the super-resolved hypercubes, in terms of the validity of regularizing features and endmembers, is explored to devise an optimal ensemble strategy. The experiments, over different data sets, confirm better accuracy of the proposed frameworks compared to the prominent approaches.

Most existing hyperspectral anomaly detection algorithms primarily rely on spatial information to identify anomalous targets. However, they often overlook the spatial–spectral gradient information inherent in hyperspectral images, which can lead to decreased detection accuracy. To address this limitation, we propose a novel hyperspectral anomaly detection algorithm that incorporates both local sub-block contrast and spatial–spectral gradient features. In this approach, a grid block window is utilized to capture local spatial information. To effectively detect low-contrast targets, we introduce a novel local sub-block ratio-multiply contrast method that enhances anomalous regions while suppressing the background. Additionally, to mitigate the challenges posed by complex backgrounds, a feature extraction technique based on spatial–spectral gradients is proposed. To account for the spectral reflectance differences between anomalous targets and the background, we further introduce a local sub-block ratio-difference contrast method to compute preliminary detection scores. The final anomaly detection results are obtained by merging these two detection scores. The key advantage of the proposed method lies in its ability to exploit local gradient characteristics within hyperspectral images, thereby resolving the issue of edge features being misidentified as anomalies. This method also effectively reduces the impact of noise on detection accuracy. Experimental validation based on four real-world datasets demonstrates that the proposed method outperforms seven state-of-the-art techniques, showing superior performance in both qualitative and quantitative evaluations.

Existing hyperspectral anomaly detection methods leverage the spectral and spatial information in the hyperspectral image (HSI) to detect the anomalies. However, the performance of these methods is limited due to the spectral variability of the materials. To address this issue, a hyperspectral anomaly detection method, based on empirical mode decomposition (EMD) and local weighted contrast (HELWC), is proposed. Firstly, a novel spectral decomposition method based on EMD is adopted to reduce the spectral noise, and estimate the spectral reference of the material. Secondly, spectral Jensen–Shannon(JS) divergence is utilized to describe the distances between different spectra. Subsequently, a local weighted contrast estimation method is proposed to calculate the contrast score. Finally, the contrast score is multiplied with the test pixel to obtain the final detection result. Experiments are conducted on four real-world datasets using multiple metrics for comparing the proposed and the benchmark approaches. The results demonstrate that the proposed method effectively reduces spectral noise and suppresses background. The average AUC _(D,F) of the proposed method on the four datasets is 0.9965, which is 0.0014 higher than the second ranked baseline method. Overall, the proposed algorithm outperforms the nine state-of-the-art methods in both subjective and objective evaluations.

In this paper, a Capsulenet-based framework is proposed for extracting spectral and spatial features for improving hyperspectral image classification. Unlike conventional strategies, the proposed framework simultaneously optimizes both feature extraction and classification. The spectral features/patterns derived at different levels of hierarchies are remodeled as spectral-feature capsules. Consequently, unlike conventional convolutional neural network-based approaches, the relative locations as well as other properties such as depth, width, and position of the spectral patterns are taken into consideration. In addition to learning spectral features/patterns, a convolutional long short-term memory (conv-LSTM) is employed for sequentially integrating the spatial features learned from each band. The integrated spatial-feature representation, thus obtained from the final hidden state of conv-LSTM, forms spatial-feature capsules. The capsule-level integration of spatial and spectral features/patterns yields better convergence and accuracy as compared to both ensemble-based and kernel-level integrations. Along with the margin loss, a spectral-angle-based reconstruction loss is also minimized to regularize the learning of network weights. Experiments over different standard datasets indicate that the proposed approach performs better than other prominent hyperspectral classifiers. Furthermore, in comparison with the recent deep learning models, our approach is found to be less sensitive to the network parameters and achieves better accuracy even with lesser network depth.