To address core challenges in synthetic aperture radar (SAR) image target detection, including complex background interference, weak small-target features, and multiscale target coexistence, this study proposes the Synthetic Aperture-optimized Real-Time Detection Transformer (SA-RTDETR) model. The framework incorporates three core modules to enhance detection efficacy. First, the Bidirectional Receptive Field Boosting module synergistically integrates local details with global contextual information and substantially improves discriminative feature extraction while preserving spatial resolution. Second, the Deformable Attention-based Intra-scale Feature Interaction module employs adaptive sampling of critical scattering regions to address localization difficulties of small targets in SAR imagery. Third, the Attention Upsampling module mitigates detail loss and aliasing artifacts inherent in traditional interpolation methods through feature compensation strategies. Experimental results on the SARDet-100K dataset demonstrate that SA-RTDETR achieves 90.1% mAP@50, 56.0% mAP@50-95, and 84.7% recall rate representing improvements of 2.7%, 2.6%, and 2.2% over the baseline model, respectively. The end-to-end architecture enables high-precision SAR image analysis and offers considerable potential for military reconnaissance and maritime surveillance applications. The SA-RTDETR model establishes a novel technical paradigm for reliable all-weather remote sensing target detection by harmonizing feature robustness, scale adaptability, and operational efficiency.

Short-term electric load forecasting is essential for efficient power system operation, but existing deep learning models struggle to capture the multi-scale features and cyclical fluctuations inherent in short-term load data. This paper introduces a novel deep learning model, Wavelet Transform Convolution-inverted ProbSparse Transformer (WTC-iPST), specifically designed for short-term load forecasting. Unlike existing deep learning models, WTC-iPST leverages Wavelet Transform Convolution (WTConv) for multi-scale feature extraction and integrates Wavelet Kolmogorov-Arnold Networks (Wav-KAN) to enhance the ProbSparse self-attention mechanism, significantly improving the model's ability to capture multi-scale features and cyclical fluctuations inherent in short-term load data. This design addresses the challenge of extracting multi-scale and cyclical features from short-term load data, which existing models struggle with, and strengthens the model's capacity to handle long series. Additionally, WTC-iPST incorporates quantile regression to quantify uncertainty and provide confidence intervals, further enhancing the prediction's reliability and accuracy. Experimental results on real-world datasets demonstrate that WTC-iPST outperforms state-of-the-art forecasting models, with significant improvements over the baseline iTransformer, achieving reductions of up to 16.84% in RMSE, 18.09% in MAPE, and 17.65% in RRMSE, as well as an increase of up to 2.96% in R². In terms of probabilistic prediction, WTC-iPST consistently maintains a narrow confidence interval with high interval coverage. Moreover, WTC-iPST shows strong performance across various prediction horizons and different distribution substations, highlighting its robustness and adaptability. These results confirm that WTC-iPST provides more accurate and reliable forecasts, making it a valuable tool for power system dispatch and operational planning.

In the current fully open and highly dynamic electronic countermeasures environment, acquiring sufficient jamming label priors is particularly challenging. Especially when the labeled samples are extremely limited, existing intelligent recognition models for radar active jamming struggle to effectively learn discriminative features, resulting in inaccurate and unstable recognition results. Therefore, this letter proposes a visual-text alignment network (VTANet) that introduces the text modality to reuse the label prior information, thereby leveraging labeling knowledge to enhance jamming recognition accuracy under few-shot conditions. During training, VTANet utilizes a text feature encoding module (TFEM) to encode text constructed based on label priors. Through a contrastive learning strategy, these obtained text features are then used to guide the visual feature encoding module (VFEM) to learn more discriminative visual time-frequency (TF) representations. Experimental results show that reusing label priors through the text modality significantly improves the intraclass compactness and interclass separability of visual TF features. With the jamming-to-noise ratio (JNR) of 5 dB and only two labeled samples per jamming type, VTANet achieves a recognition accuracy of over 90%, improving by more than 5% compared to existing methods, thus demonstrating its superiority.

Due to significant data distribution differences among polarimetric synthetic aperture radar (PolSAR) images and the expensive and time-consuming nature of data labeling, existing methods are challenged to classify newly acquired unlabeled data. To address these issues, this letter proposes an unsupervised domain adaptation (UDA) network that leverages an intermediate domain-assisted biclassifier. An adversarial UDA network incorporating a biclassifier is introduced as the fundamental structure. Then, by interacting with the semantic information of the features extracted from the source and target domains, the cross-domain feature enhancement module (CFEM) is integrated to improve intraclass cohesion and interclass separation. In addition, to achieve a more stable domain alignment process, an intermediate domain is created through the weighted fusion of features from both the source and target domains, serving as a conduit for cross-domain knowledge transfer. Experimental results conducted on three datasets captured with different systems or regions show that the proposed method achieves an average overall accuracy (OA) improvement of over 1.5% compared with other state-of-the-art methods.

Cross-domain classification of hyperspectral remote sensing images is one of the hotspots of research in recent years, and its main problem is insufficient training samples. To address this issue, few-shot learning (FSL) has emerged as a promising paradigm in cross-domain classification tasks. However, a notable limitation of most existing FSL methods is that they focus only on local information and less on the critical role of global information. Based on this, this paper proposes a new feature processing method with adaptive band selection, which takes into account the global nature of image features. Firstly, adaptive band analysis is performed in the target domain, and threshold analysis is used to determine the number of selected bands. Secondly, a band selection method is employed to select representative bands from the spectral bands of the high-dimensional data according to the determined band count. Finally, the weights of the selected bands are analyzed, fully considering the importance of pixel weight, and then the results are used as inputs for the classification model. The experimental results on various datasets show that this method can effectively improve the classification accuracy and generalization ability. Meanwhile, the results of the objective accuracy index of the proposed method in different databases improved by 3.9%, 4.7% and 5.4%.

This work proposes deploying stacked intelligent metasurface (SIM) on individual Internet of Things (IoT) devices to enhance the uplink transmission capability under a finite blocklength (FBL) regime. Aiming to maximize the achievable sum rate, a joint transmit power allocation, SIM phase shifts, and receiving beamforming design optimization problem is formulated. By decomposing the original problem into three sub-problems, reducing the intractable quadratic fraction of signal-to-interference-plus-noise ratio (SINR), the nonconvex channel dispersion function, and the constant modulus constraints to linear forms, we propose an iterative algorithm to obtain the solutions. Numerical results demonstrate that in a multi-user uplink FBL network, the incorporation of SIM yields approximately a 40% enhancement in the sum rate. The optimization of phase shifts leads to an improvement of nearly 70% in the sum rate compared to a random phase setting scheme, highlighting the crucial role of proper phase shift configuration in realizing the significant performance gains offered by SIM. The performance of the proposed algorithm is validated to be close to the slack upper bound. Furthermore, with the same total number of metasurface elements, the multi-layer SIM performs better than the traditional single-layer RIS, which reveals the advantages of multi-layer structure.

Effective noise suppression is crucial for the subsequent interpretation tasks of SAR imagery. Traditional SAR image processing techniques often overlook the coherent nature of noise, leading to a loss of vital detail during filtering. With advancements in deep-learning, significant strides have been made in image processing. However, existing deep-learning methods do not fully leverage the imaging mechanisms of SAR, resulting in a lack of specificity and interpretability in the filtering process. To balance noise reduction with detail preservation and to address the “black box” issue in filtering, we propose an interpretable filtering method that employs a correlation-based upward search for density peaks. Initially, we develop an MeanShift-Markov Random Fields filter (MS-MRF) that integrates MeanShift with Markov Random Fields (MRF) in the joint spatial-spectral domain, ensuring both correlation and detail preservation; the derivation of the MS-MRF filter is rigorously grounded in mathematical theory. Subsequently, we integrate MS-MRF with convolutional operations in deep-learning to create a novel convolutional filter, Interpretable MS-MRF Convolution (IMMC), which enhances the model’s interpretability, noise reduction capabilities, and detail retention. Extensive experiments demonstrate that our method outperforms State of the art(SOTA) SAR denoising techniques, achieving an average SSIM of over 85.00% and an average PSNR exceeding 35.00dB across synthetic datasets with varying noise levels, showing significant improvements in noise suppression, detail preservation, and interpretability.

Detecting ships in synthetic aperture radar (SAR) imagery is a pivotal task for marine surveillance and security. Although many deep learning (DL) methods have been proposed for SAR ship detection, they still lack the ability to explore intrinsic scattering features, and their ship target detection capabilities necessitate further enhancements in complex labile environments, especially for small ships. For this reason, this letter proposes a dual branch scattering feature fusion network (SFFNet). First, scattering center feature maps are reconstructed, and then, we design a scattering feature attention fusion module (SFAFM) in view of reconstructed feature maps, which can enhance the prominent feature extraction ability of the network. Moreover, the backbone feature extraction architecture incorporates a dense depthwise block (DDWB) aimed at more effectively fostering information interactions for scattering features and improving the efficiency of the network. To validate the efficacy of the SFFNet, comprehensive experiments were conducted on two public datasets, namely, HRSID and LS-SSDD-v1.0, and experimental results indicated that the detection accuracy reached 98.3%, and the false detection rate decreased to 0.21%. The proposed method can achieve superior performance when benchmarked against other state-of-the-art detection methods.

This paper investigates physical layer secure communication in a wideband wireless system, where a base station (BS) equipped with an extremely large scale antenna array (ELAA) transmits confidential information to a legitimate receiver under the threat of a potential eavesdropper. Due to the high carrier frequency and large antenna aperture, both the receiver and eavesdropper lie in the near-field region of the BS. In order to mitigate the beam split effect and reduce the hardware cost, a true-time delayer-based hybrid beamfocusing architecture is designed. Then, a nonconvex sum secrecy capacity maximization problem (SSCM) is formulated for securing wideband communications. Based on alternating optimization, the SSCM is decomposed into three subproblems solved iteratively for designing the digital beamfocusing vectors, time delay matrices, and phase shift matrices on each subcarrier, respectively. Simulation results show that the proposed scheme yields significantly high secrecy capacity compared to benchmarks, which validates the effectiveness of our scheme in enhancing secure wideband communications and mitigating the beam split effects.

Precise crop classification plays a significant role in the agriculture field. An appropriate data source for precise crop classification is high spatial resolutions hyperspectral imagery (H2 imagery) acquired by unmanned aerial vehicle (UAV). However, for imagery with many different classes of crops, crop classification of UAV H2 imagery is a huge challenge. The significant spectral diversity, spatial heterogeneity and nonlinear data structure of UAV H2 imagery results in poor spectral discriminability. To improve the discriminability, a kernel tensor slice sparse coding-based classifier (KTSSCC) is proposed for precise crop classification of UAV H2 imagery in this research. The kernel tensor representation mechanism in KTSSCC can reduce the nonlinear separation while well preserving the spectral characteristics and spatial constraints of land-covers, and thus the discriminability is greatly improved. Furthermore, this paper puts forward the kernel tensor slice sparse orthogonal matching pursuit (KTSSOMP) algorithm to optimize kernel tensor slice sparse coding in the spectral space, which greatly reduces the computation cost. Moreover, there are very few parameters to be tuned in our proposed model. We assess the performance of KTSSCC on two real UAV hyperspectral imagery datasets, and find that, based on visual and quantitative results, it provides satisfactory crop classification results and outperforms the state-of-the-art approaches.

A compact coupled-fed dual-antenna building block has been constructed in this study. The building block is simple in structure and easy to process, and has a high degree of isolation. The dual-antenna building block is composed of a coupled-fed loop antenna and a coupled-fed slot antenna that completely overlap. Based on this dual-antenna module, an eight-element MIMO system is designed, and the fabricated eight-element MIMO array is measured. The measured isolation of the designed eight-element MIMO system is >18.5 dB without any decoupling element. In addition, the MIMO array has good measured efficiencies, with a measured efficiency variation range of 43%–54% in the entire working frequency band. The measured ECC of the MIMO system is <0.02. Therefore, the designed MIMO array has great potential in 5G metal-rimmed mobile phone applications.

Accurate recognition of the types of mainlobe active deception jamming is essential for radar systems to take anti-jamming countermeasures. A bunch of deep learning (DL)-based recognition methods that require largescale datasets for training have shown promising results. However, capturing a sufficient number of diverse deception jamming samples is particularly intricate in actual dynamic and complex battlefields, the yielding limited or unbalanced datasets presents a significant challenge in training and generalizing DL models. This letter proposes a deep generative model, called label-guided denoising diffusion probabilistic model (LG-DDPM), to address the issue of limited or class-imbalanced active deception jamming samples through data augmentation. By embedding label information into the diffusion process, the proposed model can generate and expand the active deception jamming samples specific to a pre-defined class even under low jamming-to-noise ratios (JNR) scenarios. The proposed method demonstrates superior performance in terms of both the fidelity and diversity of the generated jamming samples as well as the recognition accuracy of the DL recognizer when compared to state-of-the-art methods. Experimental results demonstrate the effectiveness and robustness of the proposed method.

In this letter, a kernel tensor sparse coding model (KTSCM) is proposed for precise crop classification of unmanned aerial vehicle (UAV) hyperspectral image (HSI). Benefited from the kernel tensor representation mechanism in KTSCM, which can not only improve the linear separation but also well preserving the spatial-spectral structures of land-covers, the discriminability of UAV HSI is greatly improved. The L1-norm based tensor sparsity makes the tensor operation in KTSCM can be equivalently converted to matrix operation, which greatly reduces the computation cost. Furthermore, the analytical solution to KTSCM allows it be well optimized with very few iterations. The performance of KTSCM is assessed on two real UAV HSIs. The experimental results indicate that KTSCM can provides rapid and accurate crop classification results with limited labeled pixels and outperforms the related counterparts.

Data security and resource allocation are two important terms associated with the Internet of Things (IoT). This recent technical evolution has made its mark in industrial applications making the network more flexible and computation friendly through connecting all the devices. As a subset of IoT, the framework of Industrial IoT (IIoT) is based on the huge number of nodes with the continuous process of multiple works at a time. Due to this, multiobjective network, interference in the path always becomes the reason for the loss of network resources as well as the security of data becomes vulnerable. In most of the previous works, dedicated channel states are considered for fixed resources which remains a major issue of IIoT network flexibility along with security. In this article, both the problems are incorporated by calculating the channel security and using convolutional neural network (CNN) optimal channel state extracted for different applications. This results as a fast system with proper utilization of resources and validated with mathematical analysis and simulations.

Due to the differentiation of polarimetric scattering mechanisms between ships and sea surface, designing the ship detection method in polarimetric synthetic aperture radar (PolSAR) is a potential promising technique and has been paid extensive attention. The complexity of sea clutter and weak scattering of small ships result in a great challenge for high-precision ship detection. In this letter, we investigate the scattering mechanisms of ships to improve the detection performance and propose a novel ship detection method based on the principal contribution of scattering mechanisms. First, the seven-component model-based decomposition (SCMD) is used to analyze the scattering mechanisms of ships. Second, the primary scattering contribution and local contrast (SCLC) mechanism are used to enhance ships, especially small ships. Finally, the threshold segmentation is used to realize the extraction of ships. Experimental results by real PolSAR data not only verify the rationality and effectiveness of the constructed detection metric but also show the clear superiority of the proposed detection method, which can encourage further application of polarimetric scattering mechanisms in ship detection.

Nonlocal low-rank (LR) hyperspectral image (HSI) denoising approaches have gained a lot of attention because of their capacity to fully take advantage of spectral correlation and nonlocal self-similarity (NLSS). Most of the existing LR-tensor-based approaches use tensor singular value decomposition (t-SVD). However, fixed discrete Fourier transform-based t-SVD may compromise the low rank structure. Additionally, these approaches restricts flexibility in dealing with HSI data because it treats the singular values of each frontal slice equally. To overcome these issues, we propose a method using weighted nuclear norms of transformed tensors (WNNTT) for nonlocal HSI denoising. Our approach exploits the low-rankness in both the spectral and NLSS dimensions. We also compare our proposed method with other t-SVD based LR-tensor regularization methods under the same framework. Our experiments show that our WNNTT approach outperforms several state-of-the-art nonlocal t-SVD based methods on open HSI data.

In the healthcare research community, Internet of Medical Things (IoMT) is transforming the healthcare system into the world of the future internet. In IoMT enabled Computer aided diagnosis (CAD) system, the Health-related information is stored via the internet, and supportive data is provided to the patients. The development of various smart devices is interconnected via the internet, which helps the patient to communicate with a medical expert using IoMT based remote healthcare system for various life threatening diseases, e.g., brain tumors. Often, the tumors are predecessors to cancers, and the survival rates are very low. So, early detection and classification of tumors can save a lot of lives. IoMT enabled CAD system plays a vital role in solving these problems. Deep learning, a new domain in Machine Learning, has attracted a lot of attention in the last few years. The concept of Convolutional Neural Networks (CNNs) has been widely used in this field. In this paper, we have classified brain tumors into three classes, namely glioma, meningioma and pituitary, using transfer learning model. The features of the brain MRI images are extracted using a pre-trained CNN, i.e. GoogLeNet. The features are then classified using classifiers such as softmax, Support Vector Machine (SVM), and K-Nearest Neighbor (K-NN). The proposed model is trained and tested on CE-MRI Figshare and Harvard medical repository datasets. The experimental results are superior to the other existing models. Performance measures such as accuracy, specificity, and F1 score are examined to evaluate the performances of the proposed model.

The future advancement of technology in Internet of Things (IoT) paradigm, Wireless Sensor Networks (WSNs) provide sensing services to connect all the devices. In the upper layer of OSI model designing an energy efficient routing protocol in WSN is a challenge, which can ease the work of Multi-access edge computing (MEC) in IoT applications. The advent of 6G is also playing key role for reliable communication between the sensing elements for IoT applications. These two phenomena are significantly influencing for the progress of next generation Intelligent Transportation System (ITS). Therefore, the proposed work presents a novel method of implementing Distributed Artificial Intelligence (DAI) with neural networks for energy efficient routing as well as a fast response for intra-cluster communication of the nodes to overcome the challenges for ITS. Although there exist several works on the inter-cluster energy-efficient network, our work proposes a new way of implementing the hybrid approach of DAI and Self Organizing Map (SOM). The proposed approach proves to be a better solution in terms of overall energy consumption by the network, along with the computational challenges. Further, the work presents mathematical analysis, simulation results and comparison with the conventional techniques for justification.

Abstract Radome being an RF window and support structure for an antenna system is a very critical element of terrestrial and airborne radar systems. This paper presents an efficient X‐band frequency select surface (FSS)‐antenna‐radome system for airborne and ground applications. In the first step, an optimum wall configuration with lowest insertion loss is found out of A‐sandwich, C‐sandwich and multilayers wall configurations. In the second step, two 5×5 arrays (FSS screens) are designed that cover the whole antenna face in the broadside direction for a controlled and secure communication system. A slotted array on a dielectric substrate gives a bandpass feature with antenna for radome operation. A dipole array on a dielectric substrate gives a broader bandwidth with antenna somewhat different from antenna alone. It makes the antenna to stop radiating for a specific band. So, it gives bandstop feature. This proposed FSS‐antenna‐radome system is demonstrated with an X‐band high directional horn antenna over the frequency range 9.4–16 GHz under a sandwich‐wall dielectric radome. The bandpass and bandstop features make this proposed FSS‐antenna‐radome a good candidate for ground and airborne applications for secure communications. In bandpass feature, antenna becomes inaccessible to other antennas/radars except a narrow band.

The birth of beyond 5G (B5G) and emerge of 6G have made personal and industrial operations more reliable, efficient, and profitable, accelerating the development of the next-generation Internet of Things (IoT). We know, one of the most important key performance indicators in 6G is smart network architecture, and in massive IoT applications, energy-efficient ubiquity networks rely mainly on the intelligence and automation for industrial applications. This article addresses the energy consumption problem with a massive IoT system model with dynamic network architecture or clustering using a multiagent system (MAS) for industrial 6G applications. The work uses distributed artificial intelligence (DAI) to cluster the sensor nodes in the system to find the main node and predict its location. The work initially uses the backpropagation neural network (BPNN) and convolutional neural network (CNN), which are, respectively, introduced for optimization. Furthermore, the work analyzes the correlation of mutual clusters to allocate resources to individual nodes in each cluster efficiently. The simulation results show that the proposed method reduces the waste of resources caused by redundant data, improves the energy efficiency of the whole network, along with information preservation.

Radomes are used for external protection of antennas not only for ground applications and air borne weather Radars but also for submarines to protect antennas underwater. For under water applications, Radomes must have high stiffness, better corrosion resistance, high strength to weight ratio and have to withstand high water pressure. In this paper, performance of a Submarine Radome is analyzed with various wall configurations and two different shapes using FEM based tool ANSYS and Siemens NX. A monopole VHF submarine antenna with AT-6000 specifications is simulated with different parameters under two different Radome structures to check the efficiency and performance under high pressure. This article presents a novel shape Radome structure that faces less stress and deformation with the increasing depth under water as compared to a typical barrel shape structure and can operate in high collapse depths under sea water.

Wireless sensor network enhances the classic features of wireless communication with cognitive capabilities for efficient spectrum usage. This work focuses on the dynamic correlation between the secondary users (SUs) based on their statistical behaviour while performing the cooperative communication in cognitive radio sensor network. The proposed approach addresses the problem of uneven and repetitive communication between the SUs in a cooperative communication scenario. The authors’ objective is to use a novel approach based on the Gaussian copula theory and advanced particle swarm optimisation algorithm to analyse the dependencies of time‐varying spectrum sensing behaviour of multiple SUs. Here, time delay in prediction reduces due to the analysis of the dynamic correlation between the time delay in spectrum sensing results for the same set of channels. The simulation results show the performance of the proposed approach outperforming the other well‐known techniques.

Under the umbrella of tensor algebra, this paper proposes a new sparse-coding-based classifier (SCC) for hyperspectral imagery classification (HIC). By utilizing the tensor forms of hyperspectral pixels, we advance a tensor sparse-coding model which preserves as many original spatial constraints of a pixel and its spatial neighbors as possible. Furthermore, to alleviate the classification uncertainty resulted from widely existing mixed pixels, this paper constructs a regularization term for maximizing the likelihood of sparse-coding tensor defined on the posterior class probability. By combining the tensor sparse coding with maximizing likelihood estimation, a hybrid probabilistic SCC with spatial neighbor tensor (HPSCC-SNT) is proposed, which makes the pixels be well represented by the training pixels belonging to the same class. The performance of HPSCC-SNT is evaluated on three real hyperspectral imagery data sets, and the results show that it can achieve accurate and robust HIC results, and outperforms the state-of-the-art methods.

A symmetric Doherty power amplifier (DPA) based on integrated enhancing reactance (IER) was proposed for large back‐off applications. The IER was generated using the peaking amplifier with the help of a desired impedance transformation in the low‐power region to enhance the back‐off efficiency of the carrier amplifier. To convert the impedances properly, both in the low‐power region and at saturation, a two‐impedance matching method was employed to design the output matching networks. For verification, a symmetric DPA with large back‐off power range over 2.2–2.5 GHz was designed and fabricated. Measurement results show that the designed DPA has the 9 dB back‐off efficiency of higher than 45%, while the saturated output power is higher than 44 dBm over the whole operation bandwidth. When driven by a 20 MHz LTE signal, the DPA can achieve good average efficiency of around 50% with adjacent channel leakage ratio of about –50 dBc after linearization over the frequency band of interest. The linearity improvement of the DPA for multistandard wireless communication system was also verified with a dual‐band modulated signal.

In this letter we explore the sparse sensing and learning mechanism of the human visual system, to propose a dual-sparse single-hidden-layer feedforward neural network (SLFNN) for the hyperspectral imagery classification. Firstly a large SLFNN is randomly initialized and trained by an extreme learning algorithm, and then the input and hidden neurons are simultaneously reduced by imposing a sparse constraint on the weights of the network. Then a saliency map is derived via the recent developed compressive sensing theory, and a joint sparse optimization approach is proposed to realize a one-step rapid selection of significant neurons. The reduction of input neurons can realize an automatic band-subset-selection of hyperspectral bands to remove the redundancy of hyperspectral vectors, and the reduction of hidden neurons can avoid the high computational cost at runtime and potential overfitting. Some experiments are taken on AVIRIS imagery data to investigate the performance of the proposed method, and the results show that it can achieve accurate and rapid classification.

In this letter, a relaxed clustering assumption and spatial Laplace-regularizer-based semisupervised hyperspectral image classifier is proposed. Considering the mixed pixels and noise intrinsic in hyperspectral image, we relax the clustering assumption employed in most of the available classifiers so that the similar hyperspectral vectors tend to share the “similar” labels instead of the “same” label, to formulate a modified spectral similarity regularizer. Moreover, the spatial homogeneity assumption is cast on hyperspectral pixels to construct a spatial regularizer, to overcome the salt-and-pepper misclassification of images. The effectiveness of our proposed method is evaluated via experiments on AVIRIS data, and the results show that it exhibits state-of-the-art performance, particularly when there are a small number of training samples.

In this letter, we propose a new spatio-spectral Laplacian support vector machine (SS-LapSVM) for semi-supervised hyperspectral image classification. The clustering assumption on spectral vectors is used to formulate a manifold regularizer, and neighborhood spatial constraints of hyperspectral images are designed to construct a spatial regularizer. Moreover, a non-iterative optimization procedure is presented to solve this dual-regularized SVM, which makes rapid classification possible. By combining spatial and spectral information together, SS-LapSVM can avoid the speckle-like misclassification of hyperspectral images in the original Lap-SVM. The performance of SS-LapSVM is evaluated on AVIRIS image data taken over Indiana's Indian Pine, and the results show that it can achieve accurate and rapid classification with a small number of labeled data, and outperform state-of-the-art semi-supervised approaches.

Exploring the geometric prior in the dimensionality reduction (DR) of hyperspectral image data (HID) is an important issue because it can overcome the possible overclassification of spectrally homogeneous areas in the HID classification. In this paper, the local geometric similarity of hyperspectral vectors is explored in both the manifold domain and image domain, and a semisupervised dual-geometric subspace projection (DGSP) approach is proposed for the DR of HID, by utilizing both labeled and unlabeled samples. First, the geometric information in the manifold domain is captured by a sparse coding-based geometric graph, and then, a local-consistency-constrained geometric matrix is defined to reveal the geometric structure in the image domain. Second, unlabeled samples are used to refine the geometric structure by defining a pairwise similarity matrix. Third, three scatter matrices are then derived from these similarity matrices to find the optimal subspace projection that captures the most important properties of the subspaces with respect to classification. Some experiments are taken on the airborne visible infrared imaging spectrometer (AVIRIS) HID to prove the efficiency of the proposed method.

Camera calibration is essential for many computer vision and image processing applications. However, this calibration process can be rather time consuming and may require a significant amount of human intervention. Calibration models traditionally employ a calibration grid whose four corner points must be marked by hand on a per-frame basis. The objective of this work is to develop a technique for processing these frames rapidly, with as little human intervention as possible. We propose an algorithm to extract the boundaries of the calibration grid automatically, based on a spectral analysis of HD (high-definition) video frames. The accuracy of the intrinsic parameters estimated using our automatic method is evaluated through comparison with those obtained using a method that requires hand labeling of the corner points.