Infrared small-target detection (ISTD) in a single frame is an essential, yet challenging task due to its small size of targets, weak energy, and clutter background. Current methods either design complex network architectures to facilitate multilevel information interaction (e.g., DNA-Net and UIU-Net) or introduce structural texture priors to enhance feature discrimination (e.g., SRNet and CSRNet). However, both methods fail to explicitly distinguish or suppress the interference of complex background from infrared small targets, which makes them easy to “get lost” in clutter background with insufficient attention to the targets. In this work, we innovatively propose a novel background-masking approach (denoted as BGM) for ISTD. The proposed BGM aims to force the network to focus exclusively on the target by masking out irrelevant background information, thereby enhancing the network’s ability to detect weak and small infrared targets. Specifically, we present a new ISTD method that leverages a proxy training task with masking, enabling the network to simultaneously predict on both the original input and the masked data, where the background is randomly masked/forgotten. This strategy allows for a better concentration of the model on the shapeless targets rather than the cluttered background. The method is flexible with a simple U-shaped network without complicated manipulation and also computationally efficient without increasing the overall computational burden during inference. Extensive experiments demonstrate that our proposed BGM effectively enhances the detection performance of infrared small targets and achieves 70.8% mean intersection over union (mIoU) on IRSTD-1K. The source code would be available athttps://github.com/ZhihaoMa123/BGM

Low-altitude unmanned aerial vehicle (UAV) remote sensing facilitates the frequent detection of power lines and liberates manual inspection. In the process of UAV power line inspection, power line detection in UAV aerial images plays an important role. But false alarms and miss alarms often occur during the detection process. Aiming at this problem, a power line detection method based on Maxtree is proposed. This method transforms the UAV aerial images into a graph structure, i.e., Maxtree, and detects the power lines under graph signal processing frame. Two-stage filtering is designed to preserve power line components. The preprocessing stage filters out most of the background part according to the color value, and the other stage performs filtering on the Maxtree created with connectivity and gray value. For each node, three attribute components, i.e., gray value, linearity, and length, are assigned to facilitate power line detection. Experiments show that the method can detect power lines accurately and effectively.

The detection of floating small targets is a challenging problem for marine surveillance radar. To effectively detect the floating small target in a complex marine environment, this letter proposes an innovative multi-featured detection method by leveraging the graph signal processing (GSP) theory. With GSP, we propose two kinds of graph representations of standardized Doppler power spectrum (SDPS) to capture the correlation of the radar data in the Doppler domain. Then, by exploiting the graph representations, three quantitative graph features, graph Laplacian regularizer, trace of Laplacian matrix, and variance of self-loop weight, are developed to distinguish target returns from sea clutter. Finally, a detector based on the graph features is constructed by the fast convex hull learning algorithm. Experiments conducted on the measured radar datasets and comparisons with existing methods confirm the effectiveness of the proposed method.

Hyperspectral image (HSI) is often disturbed by various kinds of noise, which brings great challenges to subsequent applications. Many of the existing restoration algorithms do not scale well for HSI with large size. This article proposes a novel mixed-noise removal method for HSI with large size, by leveraging the superpixel segmentation-based technology and distributed algorithm based on graph signal processing (GSP). First, the underlying structure of the HSI is modeled by a two-layer architecture graph. The upper layer, called skeleton graph, is a rough graph constructed using the modified$k$-nearest-neighborhood algorithm and its nodes correspond to a series of superpixels formed by HSI segmentation. The skeleton graph can efficiently characterize the intercorrelations between superpixels, while preserving the boundary information and reducing the computational complexity. The lower layer, called detailed graph consisting of a series of local graphs which are constructed to model the similarities between pixels. Second, based on the two-layer graph architecture, the HSI restoration problem is formulated as a series of optimization problems each of which resides on a subgraph. In each optimization problem, a graph Laplacian regularization (GLR) is defined and incorporated into a low-rank (LR)-based model. Third, a novel distributed algorithm is tailored for the restoration problem, using the information interaction between the nodes of skeleton graph and subgraphs. Numerical experiments conducted on both synthetic and real-world datasets demonstrate the effectiveness of the proposed restoration algorithm compared with existing methods.

Hyperspectral image (HSI) is often corrupted by various kinds of noises. This letter proposes an innovative HSI denoising approach by leveraging the graph signal processing (GSP) theory and the low-rank (LR) matrix recovery model. With GSP, the piecewise smoothness (PWS) property of the HSI can be efficiently characterized, leading to a new regularization for HSI denoising, termed the adaptive weight graph total variation (AWGTV) regularization. Then, the denoising problem is formulated into a constrained optimization problem that incorporates the AWGTV and the LR property of the HSI. An augmented Lagrange multiplier method is adopted to solve the problem. Numerical experiments conducted on synthetic and real-world datasets and comparisons with existing methods demonstrate the effectiveness of the proposed denoising algorithm.

Graph filter banks play a crucial role in the vertex and spectral representation of graph signals. The notion of two-channel nonsubsampled graph filter banks (NSGFBs) on an undirected graph was introduced recently. The absence of downsampling/upsampling operators allows greater flexibility in the design of NSGFBs that achieve perfect reconstruction. However the design of NSGFBs that take the spectral response into account has not been adequately addressed yet. Based on the polynomial/rational lifting scheme, this letter presents a simple method to design NSGFBs with good spectral response and perfect reconstruction. Experimental results will demonstrate the effectiveness of the proposed method in tailoring the spectral responses of the lifted NSGFBs. Application of the NSGFB to denoising will also be considered.

This study presents a new property of the filter bank‐based multicarrier (FBMC) system. Also, an efficient iterative algorithm for designing the system with a large number of subcarriers and a prototype filter with a very long length are proposed. For the system, the compact from conditions are derived for both the intersymbol interference free and the interchannel interference (ICI) free. Based on these new conditions, the design of the prototype filter is formulated as an unconstrained optimisation problem where the objective function is the weighted sum of the total distortion of the system and the stopband energy. By deriving the gradient vector of the objective function, an efficient iterative algorithm is proposed for finding the solution of the optimisation problem. In addition, an efficient matrix inversion approach is presented to greatly reduce the computational complexity of the iterative algorithm. As a result, it is feasible to design the FBMC system with thousands of subcarriers. The convergence of the iterative algorithm is proved. Computer numerical simulation results with the comparisons to the existing methods are presented. It is shown that the proposed design algorithm is more effective and efficient than the existing methods.

In this study, the lifting scheme is first employed to design two‐channel biorthogonal graph filter bank. The biorthogonal condition is parameterised by imposing a single‐level lifting structure on the analysis and synthesis graph kernels. Based on the parametric structure, the two kernels are separately optimised by constrained quadratic programming. The obtained two‐channel biorthogonal graph filter banks are of structurally perfect reconstruction. Numerical results and comparison are included to show the proposed algorithm can lead to biorthogonal graph filter banks with improved performance.

This study presents several new properties of the discrete Fourier transform (DFT) modulated filter banks and efficient algorithm for designing the filter banks with very large‐scale (with a very large number of subbands and very long filters). For DFT modulated filter bank, the authors derive the symmetric property of the overall transfer function and aliasing transfer functions which can be efficiently calculated by using the orthogonal property of the DFT matrix. By invoking the M th band condition and new property, an efficient algorithm is proposed to design DFT modulated filter banks. The convergence of the algorithm is also proved. Several numerical examples and comparison with the conventional methods are included to show the effectiveness of the proposed algorithm.

This study presents a novel property of the two‐dimensional DFT‐modulated filter bank and an efficient algorithm for designing the filter bank with large scale (with a large number of subbands and filters of large spatial support). It is firstly shown that the overall transfer function and aliasing transfer functions can be simply represented with the multiplication of the prototype filters and their modulated filters; a new property used to remarkably reduce the calculation of these functions. On the other hand, the design problem of the filter bank is formulated into an unconstrained optimisation problem. Based on the gradient vector, the conjugate gradient method is utilised to solve the design problem. The convergence of the proposed algorithm is analysed. Numerical examples and comparisons with other methods are included to show the performance of the algorithm.