Search Results (6,497)

Automated damage inspection of railway viaducts requires pixel-level identification of structural components and surface damage such as cracking and rebar exposure. A common assumption in bridge inspection is that damage segmentation improves when component information is provided alongside the image. This study tests that assumption on the Tokaido synthetic viaduct dataset using controlled comparisons between segmentation models with and without component information. Both damage and structural component segmentation are evaluated across multiple architectures, and the trained component model is assessed on real viaduct photographs against a baseline model requiring no task-specific training. Under the original random split, explicit component conditioning does not produce a measurable improvement in damage segmentation: all tested strategies remain within 0.008 mean Intersection-over-Union (mIoU) of a baseline without component input, and this null result persists even when component predictions are reliable. Under a leakage-controlled scene-disjoint split, however, the same component-aware variants show a small positive trend (up to $+0.019$ mIoU over three seeds), so the effect of component conditioning depends on the evaluation protocol. The best unconditioned model reaches 0.569 mIoU for damage segmentation; for real-photo component segmentation, the trained model reaches 0.424 mIoU compared with 0.250 mIoU for the training-free baseline. These results show that multitask benefits reported in bridge inspection do not automatically translate into gains from explicit use of component information on synthetic viaduct data, where damage occurs almost exclusively on columns yet is too sparse for structural element identity to yield more than a marginal localisation gain. The multi-architecture benchmark and the measured real-photo structural transfer gap provide reference baselines for subsequent work on component-aware and transfer-robust inspection. Full article

Spaceborne Synthetic Aperture Radar (SAR) provides all-weather, day and night and wide-area imaging capability, and plays a critical role in maritime surveillance. While substantial progress has been achieved in SAR ship detection, SAR ship classification remains relatively underexplored, mainly due to the scarcity of reliable category labels. Automatic Identification System (AIS) provides vessel identity, type, and dynamic trajectory information, and thus offers vessel type information that is difficult to obtain directly from SAR imagery. This paper proposes a fine-grained nine-category SAR ship classification method based on AIS association, which reorganizes the original AIS vessel types into nine fine-grained categories of SAR ship, transfers AIS vessel type information to SAR detection through a global optimal matching strategy, and supports SAR-only vessel category recognition. By retaining only high-confidence SAR and AIS matched pairs and cropping the corresponding SAR ship chips, an SAR ship classification dataset containing 4472 ship chips across the nine categories is constructed. In Monte Carlo experiments based on real AIS records, the proposed association strategy achieves more reliable high-confidence label generation than the compared association methods under close ship ambiguity, spatial perturbation, distractor AIS candidates, and AIS static size errors. In the benchmark experiment on the constructed classification dataset, ConvNeXt-Tiny achieves the best performance among the compared mainstream classifiers. These results demonstrate that AIS association can provide reliable category supervision for SAR ship classification, and the trained classifier can perform ship classification using SAR imagery alone. Full article

Cloud contamination obscures ground objects, interferes with surface reflectance, and disrupts spatial continuity. In thick-cloud regions, surface structures and spectral information are often extensively missing. CNN-based cloud removal methods can recover local textures, but they are less effective at modeling global structures and color consistency over large cloud-covered areas. Transformer-based methods capture long-range dependencies; however, standard self-attention introduces high computational and memory costs for high-resolution remote sensing images. Efficient attention reduces this cost but may weaken edge and texture discriminability. SAR imagery can penetrate clouds and provide surface structural information, yet repeated SAR injections may propagate speckle noise, cross-modal misalignment, and imaging discrepancies through deep restoration layers. To address these issues, this paper proposes DST-SARNet, a dual-stage SAR structural guidance network for optical remote sensing image cloud removal. In this framework, dual-stage refers to two explicit SAR-guidance positions: early structural skeleton guidance at the input side and late high-frequency modulation near the output. The Texture-Aware Asymmetric Retrieval module is placed between these two stages as a bottleneck memory retrieval operation rather than as a third dense SAR injection stage. With this design, SAR provides structural skeletons, readable texture memory, and terminal detail compensation, while the optical branch remains responsible for color, semantics, and spectral appearance recovery. Experiments on the SMILE-CR and SEN12MS-CR datasets show that DST-SARNet effectively restores cloud-contaminated imagery with a compact model scale, demonstrating its potential for efficient SAR-assisted optical cloud removal. Full article

This paper proposes a novel approach for multiple-view $L_2$ triangulation, a key problem in computer vision which consists of estimating a scene point from its estimated image projections on two or more cameras and from the estimated projection matrices of the cameras by minimizing the reprojection error in the $L_2$ norm. In the proposed approach, the estimated image projections are allowed to be uncertain in admissible regions described by polynomial inequalities and equalities, and an estimate of the scene point is obtained by solving a linear matrix inequality (LMI) problem built with matrix decompositions, polynomial multipliers, and the Gram matrix method. It is proven that the optimal estimate can always be achieved by using multipliers with sufficiently large degree. Moreover, a simple test is provided in order to establish the optimality of the obtained estimate. As shown by some examples with real and synthetic data, the proposed approach presents key advantages with respect to several existing methods of a different nature, which may fail to find the optimal estimate, may not allow one to establish the optimality of the found estimate, or may require a larger computational burden. Full article

Global Navigation Satellite System Reflectometry Interferometric Synthetic Aperture Radar (GNSS-R InSAR) offers all-weather, all-day observation capabilities and high temporal resolution, enabling elevation deformation monitoring with a single satellite. However, in hazardous regions, such as tailings dam slopes, measuring the deformation of a greater number of target points is essential for a more accurate assessment of geological hazard risks. Since navigation satellite signals are not originally designed for imaging purposes, their inherent narrow bandwidths result in low spatial resolution and limited target recognition capabilities, rendering them inadequate for such scenarios. To address these limitations, this paper investigates a GNSS-R InSAR deformation measurement architecture utilizing dual-frequency BeiDou-3 (BDS-3) signal fusion. Specifically, a coherent spectrum fusion method is introduced to effectively expand the signal bandwidth, thereby significantly enhancing range resolution and target identification capabilities. Building upon this, deformation measurements are conducted to achieve more refined and detailed monitoring. Full article

Industrial defect generation has long been challenged by the scarcity of real anomaly samples and the imbalance of defect categories, particularly in complex industrial scenarios involving transparent containers. Taking vials as an example, glass reflection, specular highlights, and fine-grained defects make continuous defect acquisition difficult, thereby making the realism and controllability of augmented samples critical to downstream detection performance. Although existing diffusion-based generation methods can improve synthetic image quality, they often require additional training or lightweight fine-tuning, which limits their efficiency in sample-limited industrial scenarios. To address this issue, this paper builds upon the TF-IDG framework and proposes a training-free industrial defect generation method based on multi-domain consistency and geometric-semantic constraints. To alleviate the unnatural texture details, boundary transitions, and background blending commonly observed in generated defects, a multi-domain consistency constraint is introduced to enhance generation realism from both frequency-domain structures and cross-domain contextual representations, thereby improving anomaly texture expression and overall visual coherence. To further mitigate unstable defect contours, spatial deviation, and structural mismatch with target objects, a geometric-semantic constraint is designed to regulate the generation process through elastic shape constraints and semantic region-anchored attention, enhancing the rationality of defect morphology evolution and spatial localization. Experimental results on both the MVTec AD dataset and a self-built vial defect dataset demonstrate that the proposed method outperforms comparative approaches. Specifically, when YOLOv11 is used as the downstream detector, the mAP@50 on the MVTec AD dataset and the self-built vial defect dataset is improved from 88.5% and 98.0% for the TF-IDG baseline to 89.6% and 98.8%, respectively. Full article

Multi-source remote sensing is transforming landslide susceptibility assessment from static terrain-based zonation toward observation-driven spatiotemporal inference and dynamic map updating. Satellite precipitation products, interferometric synthetic aperture radar (InSAR) deformation time series, optical image sequences, land-cover products, and multi-temporal terrain observations provide complementary evidence of hydrometeorological forcing, slope kinematics, land-system regulation, and geomorphic reorganization. However, these observation streams differ substantially in spatial support, temporal resolution, physical meaning, and uncertainty structure and therefore cannot be reliably integrated as generic predictors without process-aware interpretation. This review synthesizes recent progress in remote sensing-enabled dynamic landslide susceptibility assessment by linking four key components: dynamic factor construction from Earth observation data, spatiotemporal representation and learning, susceptibility map updating, and validation under temporal and spatial independence. The reviewed literature is organized around four process roles: rainfall- and soil moisture-related forcing, kinematic state and response captured by InSAR, land-system and ecological regulation derived from optical time series, and geomorphic memory represented by multi-temporal digital elevation models (DEMs). We further examine how these signals are encoded and integrated through temporal models, graph-based representations, attention mechanisms, and hybrid frameworks, with particular emphasis on consistency among process role, data structure, mapping unit, inference target, and validation design. Current progress remains constrained by temporally coarse landslide inventories, cross-scale incompatibility among remote sensing products, uneven and insufficiently process-aware multimodal fusion, and limited physical interpretability. Future advances require event-resolved inventories, uncertainty-aware multimodal fusion, process-consistent spatiotemporal learning, and validation designs that explicitly test whether susceptibility maps can be updated in a scientifically defensible manner as new Earth observation data become available. Full article

Vision-based fire detection models are often limited by the insufficient diversity of annotated fire and smoke images, particularly in terms of fire location, flame scale, smoke density, ignition cause, and indoor scene context. This study investigates whether generative AI-based synthetic images can expand fire-image diversity and improve object detection-based fire detection performance. Real fire images were combined with conventional augmented images and synthetic images generated using ChatGPT-4.o and ChatGPT-5.5. The generated images were constructed using multivariable prompts considering fire location, scale, and cause, and unsuitable samples were screened using a pretrained fire detection model. YOLOv8n, YOLOv11n, and RT-DETR were trained under 48 dataset–detector conditions and evaluated using fixed validation and test datasets. The results showed that generated-image-based training generally maintained or improved detection performance compared with the original and conventional augmentation conditions. In particular, selected ChatGPT-4.o-based YOLOv11 conditions showed statistically supported improvements over matched augmentation conditions, with increases of +0.052 in Precision, +0.031 in Recall, +0.065 in mAP@0.5, and +0.038 in mAP@0.5:0.95. LPIPS and t-SNE analyses indicated that the generated images formed structured perceptual and feature-space distributions relative to real fire images. Scenario-based inference using location-specific video frames also showed stable model responses in several complex indoor fire environments. These findings suggest that validated generative AI-based images can supplement the limited visual diversity of real fire datasets and improve the robustness of vision-based fire detection models. Full article

Translating Synthetic aperture radar (SAR) images into optical images is intrinsically ill-posed because microwave backscatter and optical reflectance describe different physical properties of the observed scene. Although frequency-domain modeling has been introduced into diffusion-based translation, existing methods mainly rely on independent weighting of individual Fourier coefficients and provide limited modeling of interactions among neighboring frequencies and feature channels. To address this limitation, we propose dualCDM, a conditional diffusion model that jointly exploits spatial- and frequency-domain representations. In the diffusion backbone, a spatial-frequency hybrid residual block (SFHRB) combines a spatial convolution branch with complex-valued convolution in the Fourier domain. The complex convolution aggregates neighboring Fourier coefficients across all input feature channels, enabling local cross-frequency and cross-channel modeling, while its response is modulated by the diffusion timestep. In the SAR conditional encoder, an adaptive frequency-domain feature recalibration block (AFFRB) predicts input-dependent real-valued gains from magnitude and trigonometric phase representations of intermediate GRD features. These gains adaptively recalibrate the complex frequency responses without introducing an additional phase shift, while the residual connection preserves the original conditional information. A dual-domain objective further constrains both the predicted diffusion noise and the one-step optical reconstruction in the spatial and frequency domains. We also construct the S1S2 dataset using 16-bit Sentinel-2 reflectance data, retaining the original 0–10,000 value range and including the near-infrared band. Experiments on SEN1-2 and S1S2 show that dualCDM improves radiometric accuracy, spectral consistency, and structural preservation over six representative methods. Paired statistical tests further confirm significant improvements over the strongest competing method across all six evaluation metrics on both datasets. Full article

Accurate grade detection in graphite ore, which is a strategic and critical mineral resource, plays an important role in improving beneficiation efficiency and overall resource utilization. However, the scarcity of high-grade samples limits the performance of deep learning models in grade identification tasks. This limitation makes it difficult for models to learn stable and representative features. This paper proposes an enhanced CycleGAN-based image augmentation framework designed for graphite ore imagery. The method works within an unpaired image translation architecture. It introduces a distributed reflectance consistency loss. This loss encodes the graphite ore’s typical low reflectance and high optical contrast as explicit statistical constraints. The design enforces consistency in both the intensity distribution and the textural structure of the generated images. The model further integrates a convolutional block attention module into the generator. This module helps refine feature representation under a physics-inspired heuristic. The study constructs augmented training sets using the proposed method. It then evaluates these datasets with a downstream grade classification model. Experimental results show clear improvements. The method reduces Fréchet Inception Distance by 21.9% and Kernel Inception Distance by 39.4%. It also improves peak signal-to-noise ratio by 3.3% and structural similarity index measure by 2.6% compared with the baseline CycleGAN. The classification accuracy in the grade identification task increases by about 2.3 percentage points. These results show that the proposed method improves both the perceptual quality and the statistical consistency of synthetic graphite ore images. It also helps reduce the performance drop caused by limited training data in few-shot learning conditions. Full article

Deploying visual anomaly detection in industrial production requires retraining models for each product domain, leading to substantial costs in data collection, computational resources, and energy consumption that scale poorly across diverse manufacturing environments. This paper proposes PFAD, a parameter-efficient framework for cross-domain anomaly detection without retraining, enabling the direct deployment of a source model trained on a benchmark dataset to unseen industrial settings in a zero-shot manner. PFAD leverages a frozen vision transformer backbone and introduces Soft Anomaly-Aware Feature Selection (Soft AFS), which assigns continuous weights to feature channels based on anomaly discriminability, preserving information while enhancing cross-domain generalization without relying on synthetic anomalies or target-domain data. Extensive experiments on both public benchmarks and real-world industrial datasets demonstrate that PFAD achieves strong cross-domain performance, including an image-level AUROC of 0.945 for semiconductor PCB inspection using only a public dataset for training. Furthermore, PFAD supports an optional one-shot inference extension, where a single normal reference image improves detection performance in scenarios with large domain gaps (up to $+10.4$ pp), most effectively when zero-shot transfer leaves meaningful headroom. These results demonstrate that PFAD provides a practical and scalable solution for industrial anomaly detection by eliminating repeated retraining cycles and reducing associated computational and energy overhead, while maintaining high performance across heterogeneous domains. Full article

Detecting rotated parabolic shapes in digital images remains a significant challenge in computer vision, especially in embedded environments constrained by computational and memory resources. This study introduces a novel field-programmable gate array (FPGA)-based genetic algorithm (GA) architecture specifically tailored for rotated parabola detection, implemented as an intellectual property (IP) core on a PYNQ-Z1 system-on-chip (SoC) platform. The architecture encodes four parabola parameters into fixed-length chromosomes, assesses their geometric consistency with a 640 × 480 binary edge image using a hardware fitness function, and executes the entire evolutionary process in programmable logic. Image pre-processing is executed on an external CPU, using Canny edge detection for synthetic images and Holistically Nested Edge Detection (HED). For real images, post-processing and result visualization are conducted on the ARM processor using the PYNQ framework. Experimental results on synthetic images demonstrate mean accuracies of 98.47% and 95.23%, with detection success rates of up to 96%. For real images, since manually annotated ground truth is not available, results are presented as qualitative observations of convergence consistency across 100 independent runs. These findings demonstrate the feasibility of detecting rotated parabolas on resource-constrained embedded platforms and indicate promising applications in domains where parabolic patterns are prevalent, such as structural inspection, biomedical imaging, and perception modules for autonomous vehicles and driver-assistance systems. Full article

We propose a secure biometric data protection (SBDP) system, which uses artificial intelligence (AI) and encryption methods to prevent forgery and keep the biometric data private and intact. The proposed SBDP approach integrates deep learning-based feature extraction with robust encryption and authentication mechanisms in a single pipeline. We use the optimized convolutional neural network (OCNN) to obtain unique features from multimodal biometric inputs like fingerprints, facial photos, and retinal scans. This works well because it learns how to represent data efficiently. To reduce the risks of raw biometric exposure, we adopt a generative adversarial network (GAN) to generate synthetic biometric representations that maintain essential characteristics while reducing sensitivity to data leakage. The biometric features and images are encrypted using the ElGamal cryptosystem to provide security assurance, while the digital signature scheme based on the SHA-256 hash function is used to provide data integrity and authenticity. Experimental results show good performance of all components of the framework. The optimized CNN obtains a classification accuracy of more than 99.8%, while the GAN shows stable training behavior with the discriminator and generator losses converging to around 0.3 and 4.0, respectively. The cryptographic module guarantees encryption dependability and signature verification efficacy across all evaluated scenarios. The integrated system provides effective protection of biometric data from unauthorized access, tampering and identity forgery. The SBDP framework is a promising solution for defense, healthcare and digital identity management, ensuring secure transmission and storage of biometric data. Full article

Knowledge distillation is a cornerstone of image anomaly detection for amplifying subtle defects via teacher–student discrepancy, yet existing methods rely on feature alignment loss that causes reconstruction error confusion and degrades accuracy. To address this critical limitation, this study proposes an abnormal discrepancy-guided knowledge distillation method (DiffKD) that differentially guides student feature reconstruction through channel-level discrepancy masks, leveraging normal features as supervisory signals and abnormal discrepancy features as constraints to enhance anomaly detection performance. The approach integrates a knowledge distillation network for feature reconstruction with a segmentation network for anomaly localization, while utilizing prior anomaly samples and synthetic anomaly samples to provide real-time training data of anomalous samples. Extensive evaluations on the SUT-Crack and MVTec AD benchmarks validate the effectiveness and generalizability of our approach. On MVTec AD, it achieves 80.7% average precision (AP) and 81.9% instance-level average precision (IAP), showing competitive performance against the representative methods evaluated under the same protocol. These results not only demonstrate significant improvements in IAD accuracy but also highlight its promise for enabling real-time, automated anomaly detection in practical applications. Full article

Deep learning-based malware classification using image representations has emerged as a highly effective paradigm for threat detection. However, training robust neural networks is frequently bottlenecked by data scarcity and severe class imbalances in real-world repositories. This study investigates the viability of using an autoregressive PixelCNN framework to synthesize high-fidelity, class-specific malware images to augment limited training distributions. Utilizing the benchmark Malimg dataset, we systematically evaluate a Convolutional Neural Network (CNN) classifier across varying ratios of synthetic-to-authentic data under strict data scarcity constraints (ranging from 10 to 80 authentic samples per family). Our experimental results reveal that while PixelCNN successfully replicates intricate, byte-level micro-textures, classifiers trained exclusively on synthetic data experience catastrophic performance degradation, yielding an accuracy of just 3%. Crucially, however, the introduction of a minimal authentic data anchor (15% to 20%) restores functional decision boundaries, immediately elevating classification accuracy up to 72%. Furthermore, performance saturates rapidly once the training matrix reaches a 50/50 synthetic-to-authentic split, achieving up to 82% classification accuracy, rendering it highly competitive with the 89% accuracy upper bound of a fully authentic baseline. These findings demonstrate an exceptional degree of data efficiency, proving that generative autoregressive augmentation can halve the authentic data collection burden in cybersecurity workflows provided a minor, real-world baseline anchor is preserved. Full article