Search Results (25)

In high-resolution remote sensing imagery, farmland areas commonly exhibit blurred boundaries, discontinuous internal structures, and high similarity to non-farmland objects such as roads, bare soil, and low vegetation. Meanwhile, because pixel-level annotation is costly and training samples are difficult to obtain, only limited training data are often available in practical applications, making methods that rely on large-scale samples and complex model structures difficult to generalize effectively. To address these two issues, this paper proposes A3UNet, a multi-level attention-enhanced lightweight segmentation network for farmland identification from high-resolution remote sensing imagery. Based on a three-level encoder–decoder structure, the network introduces Point-Local Fusion Attention (PLFA), Medium-Range Attention (MRA), and Tri-Global Attention (TGA) into the skip connections, bottleneck layer, and intermediate decoder layer, respectively, thereby enhancing farmland feature representation from three levels: local boundaries, medium-range connected structures, and global semantic constraints. Few-sample experiments on two public datasets, GID and LoveDA, show that A3UNet achieves IoU values of 83.22% and 75.87%, respectively, with only 2.51 MB of parameters and 2.92 G FLOPs. Compared with the second-best methods on the corresponding datasets, the IoU is improved by 4.78 and 5.68 percentage points, respectively. These results indicate that the proposed method can achieve favorable identification accuracy and result stability while maintaining low model complexity, providing a lightweight solution with stronger practical application potential for farmland identification from high-resolution remote sensing imagery. Full article

Global gridded population datasets are widely used in urban analysis, risk assessment, and sustainability monitoring, including the calculation of indicators for the Sustainable Development Goals (SDGs). Despite their broad use, their behaviour at local scales in shrinking cities remains insufficiently understood. This study evaluates three global population datasets—WorldPop, GHS-POP, and GPWv4—in seven Croatian city cores using official census data as reference. Croatia represents a relevant case due to long-term population decline combined with relatively stable built-up extents. Population estimates were compared at the city-core level for the period 2001–2021, and spatial differences between datasets were examined using pixel-level residuals, built-up intensity metrics, and land-cover stratification. The results show that WorldPop and GHS-POP achieve similar accuracy in city-total estimates, with relative errors generally ranging between about 2% and 10%, but differ systematically in their spatial allocation of population. GHS-POP concentrates population within built-up areas, while WorldPop redistributes a substantial share into non-built-up land-cover classes, exceeding GHS-POP by approximately 290,000 inhabitants outside built-up areas, whereas GHS-POP concentrates over one million additional inhabitants within built-up zones. GPWv4 often shows the smallest city-level errors but produces spatially uniform population surfaces that limit its suitability for intra-urban analysis. The findings highlight that model choice can strongly influence spatial indicators used in SDG-related and sustainability assessments, highlighting the need for context-specific evaluation of global population datasets in shrinking urban environments. Full article

In recent years, image denoising has seen a shift from traditional non-local self-similarity methods like BM3D to deep-learning based approaches that use learnable convolutions and attention mechanisms. While pixel-level attention is effective at capturing long-range relationships similar to non-local self-similarity based methods, it incurs extremely high computational costs that scale quadratically with image resolution. As an alternative, channel-wise attention is resolution-independent and computationally efficient but may miss crucial spatial details. In this paper, an adjustable attention mechanism is introduced that bridges the gap between pixel and channel attentions. In the proposed model, average pooling and variable-size convolutions are added before attention calculation to adjust spatial resolution and, thus, allow dynamical adjustment of computational complexity. This adjustable attention is applied in a transformer-based U-Net architecture and achieves performance comparable to state-of-the-art methods in both real and Gaussian blind denoising tasks. To be more concrete, the proposed method achieves a Peak Signal-to-Noise Ratio of 39.65 dB and a Structural Similarity Index Measure of 0.913 on the Smartphone Image Denoising Dataset. Therefore, the proposed method demonstrates a balance between efficiency and denoising quality. Full article

Vision Transformers (ViTs), owing to their strong capability in modeling global contextual dependencies, have been widely adopted in hyperspectral image unmixing (HU). However, standard ViTs process images by partitioning them into non-overlapping patches, which disrupts spatial continuity at the pixel level and neglects the fine-grained structural relationships among pixels within local regions. Consequently, effectively capturing the detailed spatial–spectral features required for accurate unmixing remains challenging. Furthermore, the high computational complexity of global self-attention and its sensitivity to noise limit the applicability of conventional Transformers to HU. To address these issues, we propose a spatial–spectral similarity guided Transformer-in-Transformer (SSTNT) framework. The proposed network adopts a modified TNT architecture, in which the inner Transformer employs a linear self-attention (LSA) mechanism to efficiently exploit pixel-level local features within sliding windows, while the outer Transformer preserves global attention to aggregate contextual information, thereby forming a cooperative local–global optimization scheme. Furthermore, a lightweight spatial–spectral similarity module is introduced to enhance the modeling of neighborhood structures. Finally, spectral reconstruction is achieved through a trainable endmember decoder and a normalized abundance estimation module. Extensive experiments conducted on both synthetic and real hyperspectral datasets demonstrate the effectiveness and robustness of the proposed method. Full article

This study proposes a clinically driven hybrid segmentation framework for dense breast tissue analysis in mammographic images, addressing persistent challenges associated with intensity inhomogeneity, low-contrast, and complex tumor morphology. The framework integrates Multiplicative Intrinsic Component Optimization (MICO_2D) for bias field correction, followed by a distance-regularized multiphase Vese–Chan level-set model for coarse global tumor segmentation. To achieve precise boundary delineation, a localized refinement stage is employed using Localized Active Contours (LAC) with Local Image Fitting (LIF) energy, supported by Gaussian regularization to ensure smooth and coherent boundaries in regions with ambiguous tissue transitions. Building upon the refined semantic tumor mask, the framework further incorporates a panoptic-style tumor instance segmentation stage, enabling the decomposition of connected tumor regions into distinct anatomical instances, which were evaluated on both MIAS and INBreast mammography datasets to demonstrate generalizability. This extension facilitates detailed structural analysis of tumor multiplicity and spatial organization, enhancing interpretability beyond conventional pixel wise segmentation. Experiments conducted on Cranio-Caudal (CC) and Medio-Lateral Oblique (MLO) mammographic views demonstrate competitive performance relative to baseline U-Net and advanced deep learning fusion architectures, including multi-scale and multi-view networks, while offering improved interpretability and robustness. Quantitative evaluation using overlap-related metrics shows strong spatial agreement between predicted and reference segmentations, with per-image Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) distributions reported to ensure reproducibility. Descriptive per-image analysis, supported by bootstrap-based confidence intervals and paired comparisons, indicates consistent performance improvements across images. Robustness analysis under realistic perturbations, including noise, contrast degradation, blur, and rotation, demonstrates stable performance across varying imaging conditions. Furthermore, feature space visualizations using t-SNE and UMAP reveal clear separability between cancerous and non-cancerous tissue regions, highlighting the discriminative capability of the proposed framework. Overall, the results demonstrate the effectiveness, robustness, and clinical motivation of this hybrid panoptic framework for comprehensive dense breast tumor analysis in mammography, while emphasizing reproducibility and conservative statistical assessment. Full article

Unmanned aerial vehicles (UAVs) and birds are typical low-altitude small targets in optical remote sensing, often occupying only a few pixels and exhibiting highly similar appearances, which limits the effectiveness of appearance-based discrimination at long distances and low resolutions. To overcome this, we propose a non-appearance-based classification framework using kinematic and time–frequency features. At the trajectory level, kinematic features—including the coefficient of variation of velocity and acceleration, the Spatiotemporal Box-counting Fractal Dimension (SBFD), and the Local Higuchi Fractal Dimension (LHFD)—quantify multi-scale trajectory complexity. At the scale-variation level, time–frequency features, specifically the Time-Frequency Aware Singular Value Entropy (TF-SVE) derived from bounding-box area sequences, capture non-stationary oscillations from bird wing flapping, reflecting behavioral differences from rigid UAV motion. Experiments on a complex real-world dataset show that stacking these features achieves 99.47% classification accuracy, demonstrating a robust, resolution-invariant, and practically effective approach for non-appearance-based recognition of low-altitude targets. Full article

Scene depth information is a key component of any robotic mobile application. Range sensors, such as LiDAR, sonar, or radar, capture depth data of a scene. However, the data captured by these sensors frequently presents missing regions or information with a low confidence level. These missing regions in the depth data could be large areas without information, making it difficult to make decisions, for instance, for an autonomous vehicle. Recovering depth data has become a primary activity for computer vision applications. This work proposes and evaluates an interpolation model to infer dense depth maps from a Lab color space reference picture and an incomplete-depth image embedded in a completion pipeline. The complete proposal pipeline comprises convolutional layers and a convex combination of the infinity Laplacian and non-local means model. The proposed model infers dense depth maps by considering depth data and utilizing clues from a color picture of the scene, along with a metric for computing differences between two pixels. The work contributes (i) the convex combination of the two models to interpolate the data, and (ii) the proposal of a class of function suitable for balancing between different models. The obtained results show that the model outperforms similar models in the KITTI dataset and outperforms our previous implementation in the NYU_v2 dataset, dropping the MSE by 34.86%, 3.35%, and 34.42% for 4×, 8×, 16× upsampling tasks, respectively. Full article

Subspace clustering has become widely adopted for the unsupervised analysis of hyperspectral images (HSIs). Recent model-aware deep subspace clustering methods often use a two-stage framework, involving the calculation of a self-representation matrix with complexity of $\mathcal{O}\left(n^2\right)$, followed by spectral clustering. However, these methods are computationally intensive, generally incorporating only local or non-local structure constraints, and their structural constraints fall short of effectively supervising the entire clustering process. We propose a scalable, context-preserving deep clustering method based on basis representation, which jointly captures local and non-local structures for efficient HSI clustering. To preserve local structure—i.e., spatial continuity within subspaces—we introduce a spatial smoothness constraint that aligns clustering predictions with their spatially filtered versions. For non-local structure—i.e., spectral continuity—we employ a mini-cluster-based scheme that refines predictions at the group level, encouraging spectrally similar pixels to belong to the same subspace. These two constraints are jointly optimized to reinforce each other. Specifically, our model is designed as a one-stage approach, in which the structural constraints are applied to the entire clustering process. The time and space complexity of our method are $\mathcal{O}\left(n\right)$, making it applicable to large-scale HSI data. Experiments on real-world datasets show that our method outperforms state-of-the-art techniques. Full article

Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have been widely applied to hyperspectral image classification tasks, but both exhibit certain limitations. To address these issues, this paper proposes a multi-scale feature fusion architecture (MCGNet). Symmetry serves as the core design principle of MCGNet, where its parallel CNN-GCN branches and multi-scale fusion mechanism strike a balance between local spectral-spatial features and global graph structural dependencies, effectively reducing redundancy and enhancing generalization capabilities. The architecture comprises four modules: the Spectral Noise Suppression (SNS) module enhances the signal-to-noise ratio of spectral features; the Local Spectral Extraction (LSE) module employs deep separable convolutions to extract local spectral-spatial features; Superpixel-level Graph Convolution (SGC), performing graph convolution on superpixel graphs to precisely capture dependencies between object regions; Pixel-level Graph Convolution (PGC), constructed via adaptive sparse pixel graphs based on spectral and spatial similarity to accurately capture irregular boundaries and fine-grained non-local relationships between pixels. These modules form a symmetric, hierarchical feature learning pipeline integrated within a unified framework. Experiments on three public datasets—Indian Pine, Pavia University, and Salinas—demonstrate that MCGNet outperforms baseline methods in overall accuracy, average precision, and Kappa coefficient. This symmetric design not only enhances classification performance but also endows the model with strong theoretical interpretability and cross-dataset robustness, highlighting the significance of symmetry principles in hyperspectral image analysis. Full article

In this study, we propose a novel pixel-level non-local similarity (PNS)-based reconstruction method for millimeter-wave interferometric synthetic aperture radiometer (InSAR) imaging. Unlike traditional compressed sensing (CS) methods, which rely on predefined sparse transforms and often introduce artifacts, our approach leverages structural redundancies in InSAR images through an enhanced sparse representation model with dynamically filtered coefficients. This design simultaneously preserves fine details and suppresses noise interference. Furthermore, an iterative refinement mechanism incorporates raw sampled data fidelity constraints, enhancing reconstruction accuracy. Simulation and physical experiments demonstrate that the proposed InSAR-PNS method significantly outperforms conventional techniques: it achieves a 1.93 dB average peak signal-to-noise ratio (PSNR) improvement over CS-based reconstruction while operating at reduced sampling ratios compared to Nyquist-rate fast fourier transform (FFT) methods. The framework provides a practical and efficient solution for high-fidelity millimeter-wave InSAR imaging under sub-Nyquist sampling conditions. Full article

Inpainting noisy remote-sensing images can reduce the cost of acquiring remote-sensing images (RSIs). Since RSIs contain complex land structure features and concentrated obscured areas, existing inpainting methods often produce color inconsistency and structural smoothing when applied to RSIs with a high missing ratio. To address these problems, inspired by tensor recovery, a lightweight image Inpainting Generative Adversarial Network (GAN) method combining low-rankness and local-smoothness (IGLL) is proposed. IGLL utilizes the low-rankness and local-smoothness characteristics of RSIs to guide the deep-learning inpainting. Based on the strong low rankness characteristic of the RSIs, IGLL fully utilizes the background information for foreground inpainting and constrains the consistency of the key ranks. Based on the low smoothness characteristic of the RSIs, learnable edges and structure priors are designed to enhance the non-smoothness of the results. Specifically, the generator of IGLL consists of a pixel-level reconstruction net (PIRN) and a perception-level reconstruction net (PERN). In PIRN, the proposed global attention module (GAM) establishes long-range pixel dependencies. GAM performs precise normalization and avoids overfitting. In PERN, the proposed flexible feature similarity module (FFSM) computes the similarity between background and foreground features and selects a reasonable feature for recovery. Compared with existing works, FFSM improves the fineness of feature matching. To avoid the problem of local-smoothness in the results, both the generator and discriminator utilize the structure priors and learnable edges to regularize large concentrated missing regions. Additionally, IGLL incorporates mathematical constraints into deep-learning models. A singular value decomposition (SVD) loss item is proposed to model the low-rankness characteristic, and it constrains feature consistency. Extensive experiments demonstrate that the proposed IGLL performs favorably against state-of-the-art methods in terms of the reconstruction quality and computation costs, especially on RSIs with high mask ratios. Moreover, our ablation studies reveal the effectiveness of GAM, FFSM, and SVD loss. Source code is publicly available on GitHub. Full article

Event-based clustering provides a low-power embedded solution for low-level feature extraction in a scene. The algorithm utilizes the non-uniform sampling capability of event-based image sensors to measure local intensity variations within a scene. Consequently, the clustering algorithm forms similar event groups while simultaneously estimating their attributes. This work proposes taking advantage of additional event information in order to provide new attributes for further processing. We elaborate on the estimation of the object velocity using the mean motion of the cluster. Next, we are examining a novel form of events, which includes intensity measurement of the color at the concerned pixel. These events may be processed to estimate the rough color of a cluster, or the color distribution in a cluster. Lastly, this paper presents some applications that utilize these features. The resulting algorithms are applied and exercised thanks to a custom event-based simulator, which generates videos of outdoor scenes. The velocity estimation methods provide satisfactory results with a trade-off between accuracy and convergence speed. Regarding color estimation, the luminance estimation is challenging in the test cases, while the chrominance is precisely estimated. The estimated quantities are adequate for accurately classifying objects into predefined categories. Full article

This paper presents a parallel implementation of a non-local transform-domain filter (BM4D). The effectiveness of the parallel implementation is demonstrated by denoising image series from computed tomography (CT) and magnetic resonance imaging (MRI). The basic idea of the filter is based on grouping and filtering similar data within the image. Due to the high level of similarity and data redundancy, the filter can provide even better denoising quality than current extensively used approaches based on deep learning (DL). In BM4D, cubes of voxels named patches are the essential image elements for filtering. Using voxels instead of pixels means that the area for searching similar patches is large. Because of this and the application of multi-dimensional transformations, the computation time of the filter is exceptionally long. The original implementation of BM4D is only single-threaded. We provide a parallel version of the filter that supports multi-core and many-core processors and scales on such versatile hardware resources, typical for high-performance computing clusters, even if they are concurrently used for the task. Our algorithm uses hybrid parallelisation that combines open multi-processing (OpenMP) and message passing interface (MPI) technologies and provides up to 283× speedup, which is a 99.65% reduction in processing time compared to the sequential version of the algorithm. In denoising quality, the method performs considerably better than recent DL methods on the data type that these methods have yet to be trained on. Full article

Image segmentation methods have received widespread attention in face image recognition, which can divide each pixel in the image into different regions and effectively distinguish the face region from the background for further recognition. Threshold segmentation, a common image segmentation method, suffers from the problem that the computational complexity shows exponential growth with the increase in the segmentation threshold level. Therefore, in order to improve the segmentation quality and obtain the segmentation thresholds more efficiently, a multi-threshold image segmentation framework based on a meta-heuristic optimization technique combined with Kapur’s entropy is proposed in this study. A meta-heuristic optimization method based on an improved grey wolf optimizer variant is proposed to optimize the 2D Kapur’s entropy of the greyscale and nonlocal mean 2D histograms generated by image computation. In order to verify the advancement of the method, experiments compared with the state-of-the-art method on IEEE CEC2020 and face image segmentation public dataset were conducted in this paper. The proposed method has achieved better results than other methods in various tests at 18 thresholds with an average feature similarity of 0.8792, an average structural similarity of 0.8532, and an average peak signal-to-noise ratio of 24.9 dB. It can be used as an effective tool for face segmentation. Full article

Structures in their service life are often damaged as a result of aging or extreme events such as earthquakes or storms. It is essential to detect damage in a timely fashion to ensure the safe operation of the structure. If left unchecked, subsurface damage (SSD) can cause significant internal damage and may result in premature structural failure. In this study, a Convolutional Neural Network (CNN) has been developed for SSD detection using surface strain measurements. The adopted network architecture is capable of pixel-level image segmentation, that is, it classifies each location of strain measurement as damaged or undamaged. The CNN which is fed full-field strain measurements as an input image of size 256 × 256 projects the SSD onto an output image of the same size. The data for network training is generated by numerical simulation of aluminum bars with different damage scenarios, including single damage and double damage cases at a random location, direction, length, and thickness. The trained network achieves an Intersection over Union (IoU) score of 0.790 for the validation set and 0.794 for the testing set. To check the applicability of the trained network on materials other than aluminum, testing is performed on a numerically generated steel dataset. The IoU score is 0.793, the same as the aluminum dataset, affirming the network’s capability to apply to materials exhibiting a similar stress–strain relationship. To check the generalization potential of the network, it is tested on triple damage cases; the IoU score is found to be 0.764, suggesting that the network works well for unseen damage patterns as well. The network was also found to provide accurate predictions for real experimental data obtained from Strain Sensing Smart Skin (S⁴). This proves the efficacy of the network to work in real-life scenarios utilizing the full potential of the novel full-field strain sensing methods such as S⁴. The performance of the proposed network affirms that it can be used as a non-destructive testing method for subsurface crack detection and localization. Full article