Search Results (1,182)

Accurate anomalous localization is a core challenge in industrial visual quality inspection. Current diffusion-based methods typically rely on single-scale reconstruction at a fixed resolution, often exhibiting limited performance on subtle or low-contrast anomalies due to the lack of hierarchical feature collaboration. We propose AdaNMD, a nested adaptive multi-resolution diffusion model that jointly optimizes accuracy and efficiency. AdaNMD constructs a three-branch nested decoding architecture. It utilizes Adaptive Group Normalization (AdaGN) to embed diffusion time steps and a top-down feature fusion module to generate semantically rich pyramid representations. Crucially, a resolution decision module dynamically evaluates image complexity, activating only the most suitable branch during inference to reduce redundant computation. To bridge the capability gap between branches, we introduce a cross-scale self-distillation mechanism where the high-resolution branch acts as a teacher for lighter branches. A unified multi-task loss function further guides the model toward robust inference policies. Experiments on the VisA and MVTec AD benchmarks demonstrate that AdaNMD achieves Area Under the Per-Region Overlap Curve (AUPRO) scores of 95.0% and 94.4%, respectively. Furthermore, compared to a baseline always using the high-resolution branch, our method improves inference speed by approximately 21%, confirming the architecture’s advantage in achieving high-precision anomaly localization and efficient inference simultaneously. Full article

Glioblastoma and diffuse gliomas pose major therapeutic challenges due to marked intratumoral heterogeneity, limited tissue accessibility, and the blood–brain barrier. Tissue-based next-generation sequencing (NGS) remains essential for WHO CNS5 molecular classification, yet it is invasive and poorly suited to serial monitoring. Two complementary non- or minimally invasive approaches have advanced rapidly: radiogenomics, which correlates multiparametric MRI features with genomic alterations, and cerebrospinal fluid (CSF) liquid biopsy sequencing, which detects circulating tumor DNA with high tissue concordance. This review examines the independent progress and synergistic integration of radiogenomics and CSF-NGS. Imaging signatures can non-invasively predict key drivers (IDH1/2, EGFR, TERT, PTEN, TP53) and molecular subtypes, while CSF-ctDNA sequencing enables real-time assessment of clonal evolution, therapy resistance (including post-temozolomide hypermutation), and residual disease. We discuss technical considerations, performance metrics, multimodal artificial-intelligence fusion, and emerging clinical applications for diagnosis, prognosis, treatment selection, and longitudinal surveillance. Critical challenges, standardization, prospective validation, and workflow integration are highlighted. By combining the spatial phenotypic information of radiogenomics with the temporal genomic resolution of CSF sequencing, this multimodal strategy offers a promising path toward precision neuro-oncology and reduced reliance on repeated invasive sampling. Full article

To solve the problem where the low contrast and extremely small target size in the three-sky-screen target-integrated linear array CCD sensor measurement system under low-illumination conditions make it difficult to accurately identify projectile targets, this paper proposes a method of Frequency-Enhanced and Multi-scale Feature Fusion YOLOv11 (FEMFF-YOLOv11). It introduces a frequency-domain enhancement module in the backbone to improve feature discriminability, and deformable offset convolution is incorporated to handle geometric deformations. It also adds a multi-scale attention aggregation module in the neck to strengthen weak target features and suppress false targets such as near-lens flying objects. The detection head is optimized by replacing the low-resolution P5 layer with a high-resolution P2 layer for better projectile target localization. Experiments are conducted on a self-built linear array CCD projectile dataset. The results demonstrate that compared with YOLOv11 and other mainstream algorithms, our method achieves 87.35% precision and 85.13% recall under 300 lx low-illumination conditions. It also maintains 85.91% precision and 82.56% recall even at 50 lx, significantly outperforming all competitors. Full article

Accurate and rapid detection of citrus leaf diseases is important for early diagnosis, precision orchard management, and the reduction of economic losses in citrus production. Automatic detection remains difficult because early lesions are often small and irregular. Several disease categories also share similar visual appearances, and localization is easily affected by veins, shadows, and cluttered backgrounds. To address these task-specific challenges, we propose HGSM-YOLO, where HGSM denotes the coordinated use of heterogeneous convolution, a GSConv-based slim neck, and multi-scale dilated local attention. The framework is built on YOLO11n because its 2.59 M-parameter and 6.4 GFLOP design provides a stringent compact baseline for edge-oriented improvement. The method follows a hierarchical design: C3k2-HetConv preserves lesion edges and local morphology in the backbone; the GSConv-based slim neck reduces part of the feature fusion cost; and an MSDA module in the high-resolution P3 branch enhances the context of small lesions. Following model selection on the validation split, the final locked models were evaluated once on the held-out test split, with HGSM-YOLO reaching 77.5% precision, 66.8% recall, 71.7% F1-score, 70.8% mAP@0.5, and 44.2% mAP@0.5:0.95, compared with 68.5%, 61.5%, 64.8%, 66.0%, and 40.2% for YOLO11n. A stratified outer five-fold cross-validation further yields 71.0% ± 1.4% mAP@0.5 and 44.4% ± 1.1% mAP@0.5:0.95 for HGSM-YOLO, versus 65.9% ± 1.1% and 40.2% ± 0.9% for YOLO11n. On the independent 1871-image citrus-leaf-disease-2 dataset, retraining under the same protocol gives 94.4% mAP@0.5 for HGSM-YOLO versus 92.2% for YOLO11n and 93.1% for the public Roboflow YOLOv11 reference model. The complete HGSM-YOLO architecture uses 7.2 GFLOPs, 2.82 M parameters, and runs at 90.9 FPS on the RTX 4090, compared with 6.4 GFLOPs, 2.59 M parameters, and 110.1 FPS for the baseline. Thus, the contribution provides a recall- and localization-oriented accuracy–efficiency trade-off rather than universal superiority in every individual metric. Full article

Regenerative aluminum melting serves as a core process in recycled aluminum production. In the regenerative aluminum melting process, the furnace temperature is a key variable which affects product performance and energy costs. The extreme in-furnace temperature necessitates sensors equipped with protective jackets, which increases measurement costs and severely compromises real-time monitoring capability. Accordingly, accurate furnace temperature prediction is highly valuable for regenerative aluminum melting. In regenerative aluminum melting furnaces, periodic burner nozzle commutation and frequent material charging and discharging lead to complex and time-varying operating conditions, posing considerable challenges to high-precision furnace temperature prediction. To address these issues, a condition-adaptive multi-scale convolution-enhanced Transformer (CA-MC-Transformer) model is proposed for furnace temperature prediction. Firstly, an agglomerative hierarchical clustering algorithm based on the weighted dynamic time warping (WDTW) distance is designed to perform unsupervised clustering on historical process data, thereby extracting physically interpretable prior labels for macroscopic operating conditions. Secondly, multi-scale dilated causal convolutions are utilized to capture local dynamic features at diverse temporal resolutions. A soft attention mechanism is further introduced to dynamically assign fusion weights to condition embeddings and local features, enabling condition-adaptive feature reconstruction. Finally, the fused adaptive features are fed into an encoder-only Transformer network to capture the global long-range temporal dependencies and achieve accurate furnace temperature prediction. Comparative experiments conducted on real operational datasets from an aluminum plant verify that the proposed method effectively eliminates the inherent tracking lag of conventional deep learning models, and substantially improves prediction accuracy and anti-noise robustness under complex and variable operating conditions. Full article

Small object detection in UAV remote sensing imagery plays a crucial role in applications such as infrastructure inspection, disaster assessment, and precision agriculture, where targets of interest frequently occupy fewer than $32\times 32$ pixels under large ground sampling distance variation and complex cluttered backgrounds. Existing methods still face three main challenges in UAV small-object detection: fine-grained detail loss caused by repeated downsampling, feature inconsistency during cross-scale fusion, and unstable boundary regression in densely distributed aerial scenes. To address these issues, this paper proposes HSAR-DETR, a detection framework that jointly improves hierarchical feature representation, cross-scale refinement, and geometry-aware localization. Specifically, a Hierarchical Enhancement Network (HENet) is introduced to preserve shallow spatial details while strengthening deep semantic-context representation. A Dual-Stream Feature Refinement module (DSFR) is designed at the P4-to-P3 fusion stage, combining spatial-domain structural modeling with frequency-domain phase refinement to improve cross-scale feature consistency. A Coordinate-Guided Adaptive Convolution module (CGAC) is further deployed before the detection head, converting coordinate-guided offset magnitudes into modulation weights for adaptive feature recalibration and improved localization stability. In addition, a conventional high-resolution P2 detection branch is incorporated to enhance small-object representation. Experimental results on the VisDrone, RSOD, and TinyPerson datasets demonstrate improved detection performance. On the VisDrone validation set, HSAR-DETR achieves 50.8% $mA{P}_{50}$ and 31.4% $mA{P}_{50:95}$, outperforming the RT-DETR baseline by 4.2 and 3.0 percentage points, respectively. Full article

In protected agriculture such as greenhouses, pest and disease monitoring via UAVs and fixed cameras suffers from extremely small object proportions owing to shooting altitude constraints, posing considerable detection challenges. Moreover, fine-grained annotation of numerous small-scale images incurs prohibitive costs. Targeting this bottleneck, this paper proposes a cross-scale unified semantic space learning framework and introduces an end-to-end DS-DETR detector based on DETR. Unlike existing methods relying on domain adaptation, multi-scale fusion, or super-resolution reconstruction, this work explicitly models instance-level cross-scale semantic correlation, transferring fine-grained semantics from large-scale close-up images to small-scale scene feature space. A Single-Point Dual-Shooting (SPDS) strategy is adopted to collect high-fidelity paired images via ordinary smartphones at low cost. A dual-stream encoder with cross-view attention and an instance-level contrastive loss align features of identical instances in a unified semantic space. A self-built CropScale-Det dataset covering three crop diseases is constructed in greenhouse scenarios. Experimental results show that DS-DETR achieves 42.5 ± 1.2% mAP@50 under limited annotations, outperforming YOLOv8-n by 11.2%, with small-target average precision reaching 26.8 ± 1.1%. Ablation experiments and feature visualization validate the effectiveness of the designed mechanism. This approach considerably reduces reliance on large-scale densely annotated data, establishing a data-efficient proof-of-concept for small-scale pest detection in protected agriculture. Full article

Object detection in remote sensing imagery remains challenging due to vast scale variations, complex backgrounds, and the prevalence of small, densely packed targets. Existing CNN-based detectors are limited by restricted receptive fields, while Transformer-based methods incur prohibitive computational overhead for high-resolution inputs. In this paper, we propose SFSMamba-DETR, a detection framework that integrates state space models with Dual-Scale Window Attention for efficient and accurate remote sensing object detection. Specifically, we design a Selective Feature Scanning (SFS) module that uses the Mamba-based 2D Selective Scan mechanism to model long-range spatial dependencies with linear computational complexity. To capture both fine-grained local patterns and broader contextual cues simultaneously, we introduce a Dual-Scale Window Attention (DSWA) mechanism that operates at two complementary window scales with multi-kernel convolution bridging. These modules are orchestrated within a Cross-scale Feature Aggregation Module (CFAM) that performs hierarchical multi-scale fusion in a hybrid encoder. Extensive experiments on three primary benchmarks (MAR20, UCAS-AOD, and the Jilin-1 Satellite Aircraft Detection Dataset), together with supplementary results on DOTA and DIOR, demonstrate that SFSMamba-DETR achieves strong detection accuracy while maintaining competitive inference speed. Full article

Low-altitude UAV aerial imagery often has complex backgrounds with densely distributed small objects, posing challenges to accurate small-object detection. To address these problems, we propose a spatial–frequency response aware synergistic network for small-object detection in low-altitude UAV aerial imagery. A Frequency-Response-Aware Enhancement Module (FRAEM) is designed to effectively extract discriminative features. The module employs a deterministic stage-aware filtering strategy: Scharr-based edge-sensitive filtering is used in the shallow stage, whereas Gaussian smoothing is used in deeper stages, enabling complementary enhancement of hierarchical representations. A Detail Feature Fusion module (DFFusion) is then developed to improve the efficiency of multi-scale feature fusion. The existing Content-Aware Reassembly of Features (CARAFE) operator is employed for content-aware upsampling and feature alignment, after which DFFusion uses learnable scalar weighting to integrate high-resolution detail information with low-resolution contextual information. A Lightweight Adaptive Decoupled Head (LADH) is also designed to reduce complexity. LADH asymmetrically allocates computational capacity across the prediction tasks: the confidence branch retains stronger spatial processing, whereas the classification and regression branches use lightweight projections; depthwise separable convolution serves as an efficiency-oriented implementation choice. Experiments on the VisDrone2019 and DOTA-v2.0 datasets demonstrate that the proposed method can achieve balance between detection performance and model complexity over mainstream detection methods. Ablation experiments also prove the effectiveness of the proposed components. Full article

High-resolution remote sensing semantic segmentation remains challenging because repeated downsampling progressively weakens the fine-grained spatial information of small objects, while direct fusion of heterogeneous multi-scale features may introduce semantic discrepancies and redundant background responses. To address these issues, this study proposes SEMU-Net, a structure-enhanced multi-branch U-shaped network. First, an independent multi-scale complementary branch is constructed outside the main encoder pathway to provide auxiliary hierarchical representations and compensate for information degradation during progressive semantic abstraction. Second, a scale-consistent feature embedding module is introduced to project and normalize side-branch features before residual injection, thereby improving the compatibility of cross-path feature representations. Third, a discriminative channel modulation module is incorporated into the decoder to adaptively strengthen task-relevant channel responses and suppress redundant background activations. Experiments were conducted on the ISPRS Vaihingen dataset and a self-annotated high-resolution remote sensing dataset. On the Vaihingen dataset, SEMU-Net achieved a mIoU of 72.21% and an Average F1 score of 83.64%, outperforming the strongest competing method by 0.59 and 0.44 percentage points, respectively. The IoU of the Car class increased by 3.50 percentage points. On the self-annotated dataset, the IoU of the narrow Road class improved by 4.12 percentage points. These results demonstrate that SEMU-Net improves overall segmentation accuracy and enhances the recognition of small objects, with the observed improvements being consistent with the design objectives of multi-scale information compensation, cross-path feature adaptation, and channel recalibration. Full article

Remote sensing image super-resolution aims to reconstruct high-resolution images from low-resolution observations and is important for image interpretation. Existing fixed-scale methods achieve good performance at predefined integer scales, but their dedicated upsampling modules limit their application to arbitrary-scale scenarios such as interactive GIS and multi-source image fusion. Continuous implicit methods provide scale flexibility but often exhibit spectral bias, resulting in over-smoothed textures and blurred object boundaries. To overcome these limitations, we propose an Arbitrary-scale Equivariant Resolution Operator (AERO) for remote sensing image super-resolution. AERO consists of three components. The Omnidirectional Feature Extractor enhances feature representation under orientation variations. The Wavelet–Arnold Residual Group models low- and high-frequency information in the wavelet domain to preserve textures and geographic boundaries. The Local Implicit Terrain Operator employs relative sub-pixel coordinates for continuous arbitrary-scale reconstruction. Experiments on AID, NWPU-RESISC45, UCMerced, and WHU-RS19 demonstrate that AERO achieves the best performance in the ×4 fixed-scale task. On WHU-RS19, AERO reaches a PSNR of 31.02 dB, exceeding FMSR by 0.64 dB. In rotational robustness experiments, the maximum PSNR fluctuation is reduced from 0.0181 dB to 0.0010 dB. The results show that AERO provides a practical approach for arbitrary-scale remote sensing image super-resolution. Full article

Low-light conditions degrade remote sensing imagery by reducing contrast, distorting color, and obscuring fine terrain structures and small objects critical for Earth observation. Accurate illumination adjustment under spatially varying scene content remains challenging for existing enhancement methods, and many prior-guided approaches operate exclusively in either the spatial domain or the frequency domain. In this work, we propose a Dual-Domain Illumination Prior (DDIP), a trainable dual-domain illumination-prior module that is jointly optimized with each host backbone and exploits frequency-domain and spatial-domain illumination statistics. DDIP comprises three components: a Frequency-Domain Illumination Distribution Prior (FIDP) that performs per-color-channel amplitude calibration in Fourier space to improve global brightness; a Spatial-Domain Illumination Distribution Prior (SIDP), adapted from IDP-Net, that performs multi-scale sub-region statistical correction for local illumination adjustment; and a Selective Core Feature Fusion (SCFF) module that adaptively combines the frequency-domain output, the spatial-domain output, and the original input through an attention-based gating mechanism with dual pooling. DDIP is integrated with each host backbone while leaving its main restoration blocks unchanged. In the controlled reconstruction comparisons on iSAID-dark and the evaluated general low-light benchmarks, equipping the tested backbone networks with DDIP improves PSNR and SSIM over their corresponding baselines. Complementary LPIPS and CIELAB lightness measurements characterize perceptual similarity and lightness behavior, while a fixed-detector object-detection evaluation on the tested high-resolution iSAID-dark scenes examines the effect of the enhancement pipelines under the reported synthetic low-light conditions. The ablation studies further examine the contribution of the module components within the reported experimental settings. Full article

Medical image resolution plays a crucial role in early disease detection and fine-structure observation. Super-resolution reconstruction technology can restore low-resolution images to high-resolution versions, thereby assisting physicians in making accurate diagnoses. To address challenges in medical image super-resolution reconstruction, including insufficient global information acquisition, excessive network complexity, and suboptimal loss function adaptation for medical imaging data, this paper proposes an image super-resolution reconstruction algorithm named IDCASR-MMF based on improved dilated convolution and multi-module fusion. First, multi-dilation-rate dilated convolution is introduced to expand the receptive field and integrated with a spatial attention mechanism to dynamically calibrate high-frequency features after feature extraction. Subsequently, the Squeeze-and-Excitation module is fused with dilated convolution as a channel attention mechanism to streamline the network architecture. Finally, a weighted fusion strategy combining adversarial loss and MSE loss is adopted, where the dynamic adjustment of weighting coefficients balances pixel-level structural accuracy and high-frequency detail authenticity, achieving synergistic optimization of objective precision and subjective quality for medical images. To validate the effectiveness of the proposed algorithm, IDCASR-MMF is compared with 11 state-of-the-art methods across five datasets (Set5, Set14, BSD100, Urban100, and Bone FD). Experimental results demonstrate that the proposed algorithm achieves superior PSNR and SSIM values on multiple datasets, confirming that IDCASR-MMF can effectively reconstruct high-resolution medical images from low-resolution inputs. Full article

High-resolution remote sensing stereo matching is challenging due to heavy computation and the difficulty of handling textureless areas, repetitive structures, and occlusions. To tackle these issues, we design BDNet (Balancing Dual-path Network)—a stereo matching network that seeks a reasonable trade-off between accuracy and efficiency for remote sensing applications. In the feature extraction stage, BDNet adopts progressive dilation with rates 5, 4, and 3, together with a decoupled multi-scale reduction (DMSR) module, which reduces multi-scale feature channels from 320 to 32. We also introduce a strip attention module to make the network more sensitive to horizontal and vertical structures commonly seen in urban scenes. For cost volume construction, the number of correlation groups is lowered from 40 to 8, in line with the compact 32-channel feature representation. For cost aggregation, a dual-path parallel hourglass architecture is designed, which preserves fine details through a high-resolution path while capturing global context through a low-resolution path. An attention-guided fusion module adaptively integrates features from both paths, improving accuracy in challenging regions such as textureless areas and disparity discontinuities. Experiments on the US3D and WHU-Stereo datasets demonstrate that BDNet achieves the best accuracy among the selected baseline methods on US3D, with D1 errors of 16.05% on Jacksonville and 11.84% on Omaha. It requires only 1.43 M parameters and 125.43 G FLOPs, achieving a favorable balance between accuracy and efficiency. Zero-shot generalization experiments on Omaha and WHU-Stereo further suggest the model’s potential for cross-domain adaptation to different satellite sensors and urban scenes. Full article

Autonomous acoustic remote sensing of underwater infrastructure is challenging due to the physical characteristics of 3D sonar and the geometric degeneracy commonly encountered in feature-poor underwater environments. Accurate localization is essential for integrating sequential sonar observations into globally consistent 3D maps; however, existing odometry methods often rely on isotropic noise assumptions despite the highly directional nature of acoustic sensing. This mismatch may cause unreliable measurements to be over-trusted, leading to severe trajectory drift and distortion in sonar-derived 3D reconstructions. To address these challenges, we propose RA-SIDO, a robust and adaptive tightly coupled 3D sonar–inertial–depth odometry framework based on the Error-State Iterated Kalman Filter (ESIKF), which fuses measurements from a 3D sonar, an inertial measurement unit (IMU), and a depth sensor for reliable underwater acoustic mapping. The proposed method introduces two mechanisms to handle sonar-specific uncertainties: (1) a physics-based anisotropic acoustic measurement model that distinguishes high-resolution radial range measurements from highly uncertain cross-range angular measurements; (2) an online degeneracy-awareness module that continuously evaluates the minimum eigenvalue of the translational information matrix and dynamically adjusts sensor fusion weights to avoid over-trusting ill-conditioned constraints. Real-world experiments were conducted with an unmanned surface vehicle in underwater infrastructure inspection scenarios. RA-SIDO achieved an ATE RMSE of $0.8924\mathrm{m}$, reducing the error by $16.8\%$ compared with SIDO, the strongest baseline. In addition, the proposed method effectively suppresses longitudinal slip and produces globally consistent 3D acoustic maps of submerged structures. These results validate the potential of RA-SIDO as a robust localization and mapping solution for underwater remote sensing, infrastructure inspection, and acoustic 3D reconstruction in challenging aquatic environments. Full article