Search Results (34,189)

Due to the small size of defects, partial occlusion, and cluttered background, insulator defect detection in transmission lines remains challenging. To address these issues, this paper proposes an improved Single Shot MultiBox Detector (SSD) framework. Firstly, a feature pyramid network is introduced for bidirectional multi-scale feature fusion to enhance the representation of small defects. Secondly, after fusing the feature maps, a convolutional block attention module is embedded to suppress background interference and highlight responses related to defects. Thirdly, focus loss replaces the original confidence loss to alleviate the imbalance of foreground and background during the training process. The proposed method achieved 99.03% insulator AP, 98.27% defect AP, and 98.65% mAP on a self-built dataset, which is 9.97 percentage points higher than the baseline SSD. The ablation study confirmed the complementary contributions of the three modules. The proposed detector significantly improves the detection reliability and robustness in complex detection scenarios, providing effective technical support for intelligent maintenance of transmission equipment. Full article

Visible and infrared (IR) image fusion has become an important strategy for improving computer vision performance under low illumination, occlusion, and some poor-visibility conditions. By integrating complementary textural information from visible images with thermal or IR cues, VIR fusion can enhance object localization, detection robustness, and facial-expression recognition (FER). This review examines VIR fusion techniques and datasets for computer vision applications, with object detection (OD) considered as a relatively mature scene-level task and FER considered as an emerging human-centered application. It summarizes major multimodal datasets, compares early-fusion approaches, including sensor- and feature-level fusion, with late-fusion approaches, including score- and decision-level fusion, and discusses representative machine learning and deep learning methods. The review also evaluates commonly used performance metrics and identifies current limitations, including dataset imbalance, sensor misalignment, limited demographic diversity in facial-expression datasets, computational complexity, and weak real-time generalization. Finally, key application areas, including surveillance, healthcare, remote sensing, autonomous systems, and human–computer interaction, are discussed. This review highlights the need for better-aligned multimodal datasets, standardized evaluation protocols, lightweight fusion architectures, and robust models capable of operating in dynamic real-world environments. Full article

Accurate hyperspectral image classification is fundamental to geospatial applications but is often constrained by annotation scarcity. To achieve high classification performance under small-sample conditions, we propose the Memory-Guided Adaptive Spectral–Spatial Perception model, which incorporates a three-level globalization strategy. At the single-sample level, an adaptive perception Transformer combines deformable and dilated convolutions with a Transformer encoder to capture global context from individual samples. At the intra-batch level, we introduce a metric learning strategy that explicitly captures structural dependencies and feature relationships among samples within each mini-batch, enabling comprehensive feature aggregation in a localized context. At the cross-batch level, a memory-guided strategy constructs a dynamic memory bank to store and retrieve features from same-class samples across training iterations, bridging past and present distributions to enhance generalization. Using only 1% of the SaliLMSS, Pavia University and Kennedy Space Center datasets and 0.5% of the WHU-LongKou dataset as training samples, our method achieves outstanding overall accuracy of 96.15%, 97.81%, 89.22% and 99.32%, respectively, outperforming existing methods. Full article

Within the domain of Earth observation, tracking terrestrial transitions via high-resolution optical data plays a fundamental role. Nevertheless, current methods face critical challenges, including the difficulty in collaborative modeling of local details and global features and the singularity of bi-temporal difference representation, along with insufficient cross-scale feature communication, thereby constraining both the precision and resilience of models when applied to complicated environments. To solve these problems, we propose LADENet (Locally Adaptive Mamba and Multi-scale Feature Enhancement Network), an innovative framework that synergizes CNN, Transformer, and Mamba paradigms. By leveraging customized local contextual refinement alongside sophisticated hierarchical fusion, this integration delivers highly precise and resilient detection performance. LADENet adopts a weight-sharing multi-level Transformer encoder combined with a sequence reduction mechanism to generate multi-scale global features, achieving precise alignment of bi-temporal features and global context modeling while reducing computational complexity. To realize accurate localization and local enhancement of changed regions, we design a dual spatiotemporal adaptive local feature marking module based on State-Space Scanning (SSS). This module screens high-saliency changed regions through an adaptive scanning strategy, realizes pixel-aligned spatiotemporal feature fusion via cross-temporal state-space scanning, and introduces a sliding window boundary calibration mechanism to alleviate boundary information loss caused by window segmentation. To strengthen the feature representation of changed regions, a dual-branch difference enhancement module is constructed, which collaboratively captures global change trends and fine-grained local features through an attention-enhanced difference branch and a multi-scale convolution concatenation branch, effectively suppressing background interference. To address the semantic gap between cross-scale features, a global cross-scale spatial feature fusion decoder is proposed, which balances local detail preservation and global context perception through the synergy of spatial attention and two-dimensional selective scanning, completing refined multi-scale feature fusion and spatial resolution recovery. To rigorously validate the proposed LADENet, comprehensive experiments were conducted across four widely adopted bi-temporal benchmarks: LEVIR-CD, WHU-CD, CLCD-CD, and GVLM-CD. The presented architecture establishes substantial superiority over existing cutting-edge methodologies across primary evaluation criteria. Specifically, it yields an F1-measure of 91.06% alongside an IoU of 85.28% in the LEVIR-CD tests, while registering 90.51% (F1) and 82.45% (IoU) for WHU-CD. Similarly, robust outcomes are delivered on CLCD-CD (82.15% F1, 72.83% IoU) as well as GVLM-CD (89.12% F1, 77.78% IoU). These results demonstrate that LADENet possesses excellent detection accuracy, boundary delineation capability and generalization performance in diverse and intricate bi-temporal observation environments. Full article

Background: Cardiac involvement in cryoglobulinemia (CG) is rare but potentially fatal, and its clinical spectrum remains poorly characterized. Methods: This retrospective study enrolled 11 patients with cardiac involvement among 885 patients with CG at Peking Union Medical College Hospital between January 2015 and March 2026. We analyzed its clinical characteristics, radiological features and management. Results: Among 885 CG patients, 11 (1.2%; 4 type I, 7 type II) had cardiac involvement. Cardiac symptoms included dyspnea (n = 6), chest tightness (n = 4), edema (n = 3), and orthopnea (n = 1). All patients had elevated N-terminal pro-B-type natriuretic peptide (median 29,799 pg/mL). Echocardiography, performed in all 11 patients, revealed left heart enlargement (n = 9), reduced left ventricular ejection fraction (n = 7), myocardial disease (n = 6), pericardial effusion (n = 4), and pulmonary hypertension (n = 3). Cardiac magnetic resonance in 5 of 11 patients showed non-ischemic late gadolinium enhancement in two cases. For first-line therapy, 6 of 11 patients received rituximab-based regimens, 3 of 11 received bortezomib-based regimens, and 1 of 11 received antiviral therapy with corticosteroids; 1 patient declined treatment. All 10 treated patients achieved initial cardiac improvement, with 5 relapsing and 2 dying during a median follow-up of 57 months (range 9–130 months). The estimated 4-year overall and progression-free survival rates were 77.9% (95% CI: 0.546–1.000) and 50.0% (95% CI: 0.269–0.929), respectively. Conclusions: Cardiac involvement in CG is rare and associated with diverse structural and functional abnormalities. Cardiac involvement should be considered in CG patients presenting with unexplained cardiac manifestations after excluding alternative causes. B-cell-targeted therapy induced an initial response, but relapse is common. Early intervention is essential given the substantial relapse burden and potential for severe morbidity. Full article

Rapid and accurate identification of various faults occurring in transmission lines is essential for restoring normal line operation. However, existing transmission line fault diagnosis methods still face challenges in terms of noise immunity and diagnostic accuracy. To address these issues, this paper proposes a deep learning method based on recurrence plots and a convolutional neural network–bidirectional gated recurrent unit–attention mechanism model. The voltage and current signals of transmission lines are transformed into recurrence plots in both the time and frequency domains. Parallel convolutional neural networks are then employed to extract local features from the two domains, while bidirectional gated recurrent units are used to capture temporal dependencies. Furthermore, multi-head self-attention and cross-attention mechanisms are introduced to enhance key features within each domain and achieve adaptive fusion of inter-domain feature information. A transmission line model is established in Simulink to collect data under various fault conditions and influencing factors, thereby verifying the effectiveness and adaptability of the proposed method. Experimental results show that the proposed method achieves fault recognition accuracies of 99.63%, 96.68%, and 75.38% under NL1, NL2, and NL3 Gaussian-noise conditions, respectively, and maintains accuracies of 99.02%, 95.93%, and 72.43% under mixed-noise conditions. Compared with other deep learning models, the proposed method demonstrates higher diagnostic accuracy and stronger robustness. Full article

Preventing large-scale illegal migration is one of the EU’s highest priorities. In this study, we analyze the potential for integrating and fusing remote sensor data with a wider range of data streams to enhance border security situational awareness, specifically targeting illegal migration. The aim was to develop a dynamic predictive risk analysis model to identify high-risk zones for illegal border crossings at Croatia’s external EU borders. The model’s methodological framework is based on the integration of Geographic Information Systems (GISs), Multi-Criteria Analysis (MCA), and the Analytic Hierarchy Process (AHP). The model utilizes various environmental and infrastructure variables derived from the open-source databases ESA WorldCover and OpenStreetMap to generate a categorized risk map showing areas of lowest, moderate, and highest risk for illegal border crossing. The model was quantitatively verified using a weighted detection-versus-background design against 7481 geocoded border crossing incidents, demonstrating high predictive skill and robust calibration (Continuous Boyce Index up to 0.97) when controlling for patrol effort bias and spatial autocorrelation. High-resolution historical satellite imagery showing activities related to illegal migration was used for the generation of labeled datasets for AI training. Features such as suspicious vans, river boats, tire tracks, tents, illegal campsites, and clusters of individuals were observed in high-resolution Airbus and Maxar historical satellite images. The model can be used for various practical applications, including the strategic allocation of surveillance resources and the enhancement of frontier and pre-frontier intelligence, enabling more informed actions and optimized operations. Full article

Background/Objectives: To develop and evaluate a deep learning-based quality control system for Lumbar Spinal Digital Radiographs (LSDR), designed to automate and improve their evaluation and reduce reliance on manual reviews. Methods: This retrospective study utilized a deep learning workflow comprising image segmentation, feature extraction, and a classification model. The dataset, including anteroposterior (AP) and lateral (LAT) X-ray images, was expanded through data augmentation techniques. Four U-Net-based models were assessed: standard U-Net, Swin-UNet, Attention U-Net, and Attention U-Net with the weight map, with the latter selected for its superior performance. Extracted features, such as brightness, contrast, and anatomical positioning, were used in an XGBoost classifier, which was evaluated using mean intersection over union (mIoU), accuracy, sensitivity, specificity, and AUC. Results: The Attention U-Net with weighted attention outperformed the other models, achieving high mIoU scores in both AP and LAT views. The XGBoost classifier achieved the best performance in classifying images as “qualified” or “unqualified,” with an AUC of approximately 0.9, high accuracy, and balanced sensitivity and specificity. This approach effectively addressed class imbalances and improved model accuracy compared to traditional machine learning models such as MLP and SVM. Conclusions: The developed automated quality control system demonstrated potential for enhancing image quality, enhancing diagnostic reliability, and optimizing clinical workflow efficiency. Full article

Landslides are among the most common and destructive geological hazards and pose a significant threat to the long-term stability of infrastructure systems. In particular, long-distance power transmission corridors often traverse mountainous and forested regions, where landslides can endanger tower foundations and transmission line safety. Such landslides predominantly occur in sloped forested areas, where dense vegetation causes severe occlusion that blurs landslide boundaries and creates strong visual similarity with surrounding land covers. Consequently, accurate and efficient landslide identification from remote sensing imagery remains a significant challenge. To address these challenges, we propose a structural constrained contrastive learning network (SC-Net) for reliable landslide extraction from remote sensing images. First, a multi-structural feature extraction module is designed to capture landslide-specific geometric characteristics. These features are further enhanced by fusing multi-scale semantic representations extracted from a pretrained backbone network through an attention-based adaptive feature fusion module. Additionally, a mask-constrained object-level contrastive learning strategy is introduced to enforce global structural consistency at the landslide object-level, thereby improving the discriminability between landslide and non-landslide regions. Extensive experiments conducted on the publicly available CAS landslide dataset demonstrate the effectiveness of the proposed method. The proposed SC-Net achieves IoU scores of 89.89% and 79.76% on the CAS-UAV and CAS-SAT datasets, respectively, outperforming the best-performing baseline by 2.09% and 0.46%. The proposed method provides an effective solution for large-scale landslide monitoring and demonstrates potential for applications in power transmission corridor inspection and infrastructure safety assessment. Full article

Small object detection is fundamentally constrained by the lack of discriminative fine-grained features. Although introducing higher resolution detection scales can improve performance, it also amplifies background noise. In addition, the independently decoupled design of conventional detection heads is insufficient to address the persistent challenges of missed detections and false positives for small objects. To this end, we propose MSIA-YOLO, a YOLOv11-based detector with multi-scale semantic interaction and alignment, optimized from three complementary perspectives: feature modeling, high resolution semantic compensation, and task coordinated alignment. First, Receptive Field Attention Convolution (RFAConv) is integrated into the backbone to enhance critical local details, such as edge and texture cues, via receptive field aware attention. Second, to alleviate fine detail attenuation caused by repeated downsampling, we construct a CHSP-P2 small object detection framework with an additional P2 branch. A scale sequence fusion mechanism is further introduced to perform high resolution semantic compensation through cross scale hybrid inputs. Finally, we design a DTIA-Head (Dynamic Task Interaction and Alignment Head), which promotes joint optimization of classification and localization through dynamic task interaction and spatial alignment. Extensive experiments on the public datasets VisDrone, TinyPerson, and RSOD show that, compared with the YOLOv11n baseline, MSIA-YOLO improves mAP50 by 7.7%, 10.3%, and 1.0%, respectively, while also outperforming several advanced detectors. These results demonstrate the effectiveness and generalization capability of the proposed method in small object, dense object, and complex scene object detection scenarios. Full article

Deep multiscale learning has emerged as a promising venue for robust image detection and multi-object tracking in adverse conditions, but the current solutions tend to be impacted by the issues of occlusion, scale variation, and background clutter, focusing on each of them separately and restricting the generalization. In a direction to address these gaps, this piece of writing proposes a unified model that incorporates HRNet to extract high-resolution features, DETR to make use of transformers for detection, and TrackFormer to identify in an identity-preserving manner. Data was based on the MOT17 benchmark dataset, which provides various urban video sequences, including annotated bounding boxes and identities, to guarantee a test that is rigorous. The approaches were selected due to their complementary advantages: HRNet keeps fine-grained spatial information, DETR allows us to locate the objects in an accurate way, and TrackFormer tracks the trajectories across fragments. Experiments show good performance, with a mean detection AP of 70.9, precision of 76.5, recall of 72.8, MOTA of 74.8, IDF1 of 70.2, and HOTA of 63.6, maintaining real-time performance of 26 FPS with a latency of 38.5 ms per frame. In general, this work offers a globally scalable, end-to-end system for problems like surveillance and self-driving, and future work aims to address outrageously dense scenes, enhance cross-dataset generalization, and come up with lightweight systems to deploy these edges. Full article

Lane detection is a fundamental perception task for autonomous driving and intelligent transportation systems. Although existing methods have achieved promising performance, many of them mainly focus on individual lane instances and insufficiently exploit the structural relationships among lanes, such as relative ordering, geometric continuity, and spatial parallelism. This limitation may lead to broken lanes, ordering errors, and geometric inconsistencies in complex road scenarios. To address these issues, we propose TPDNet, a topology-aware lane detection framework that incorporates structural reasoning into the detection pipeline at three complementary levels. First, a Topology-aware Perception Reasoner (TPR) is introduced at the feature level to capture relational dependencies among lane features and enhance the representation of global road topology. Second, a Topology-Decoupled Head (TDH) is designed at the prediction level to decouple geometric regression from lane classification, thereby reducing task interference and improving prediction stability. Third, a Topology Consistency Loss (TCL) is formulated as a complementary supervision term to encourage smoothness and ordering consistency in predicted lanes. Extensive experiments on three public benchmarks demonstrate the effectiveness of the proposed method. On CULane, TPDNet achieves an F1@50 of 81.46 with ResNet101 and remains competitive with the strongest compared methods, while showing improved robustness in challenging scenarios such as Curve and Dazzle light. On TuSimple, TPDNet obtains an F1 score of 98.01 among the compared methods, while maintaining competitive accuracy. On CurveLanes, TPDNet achieves an mF1 of 58.74, exceeding the strongest baseline by 4.98 points. These results suggest that topology-aware reasoning can improve the generalization capability of lane detection and help produce more structurally coherent lane predictions under diverse road conditions. Full article

To address the stringent demands of intelligent connected vehicles for high bandwidth, low latency, and highly reliable communication, this paper systematically summarizes the semantic communication technology of the Internet of Vehicles (IoV) based on information “meaning” transmission, covering basic theory, key technologies, application practice and challenge and trends. First, the paper expounds the knowledge driven and task oriented paradigm characteristics of semantic communication and its efficiency advantages in the IoV. Second, in terms of key technologies, semantic extraction achieves efficient feature compression through multimodal fusion and Generative Artificial Intelligence (GAI); semantic coding employs hierarchical codebooks and adaptive strategies to optimize transmission efficiency; semantic transmission leverages deep reinforcement learning for the joint scheduling of resources such as spectrum and power; and semantic decoding utilizes reconstruction networks and GAI to enhance resilience against impairments. Application practices demonstrate that semantic communication can significantly compress image data transmission volume for autonomous driving collaborative perception while maintaining high-fidelity reconstruction under adverse channel conditions. It significantly reduces the communication load and improves the system utility in vehicle-to-infrastructure coordination and in-vehicle service. Despite facing technical challenges such as semantic consistency, dynamic adaptability, and security trustworthiness, future semantic communication will evolve towards deep integration with distributed collaborative knowledge networks, lightweight real-time decision-making agents, and integrated “communication, sensing, and computing” architectures, positioning itself as a key enabling technology for empowering Sixth Generation mobile communication (6G) of intelligent vehicular networks. Full article

In intensive aquaculture, non-invasive real-time monitoring of morphological traits and body weight of largemouth bass (Micropterus salmoides) is essential for precision feeding and yield estimation. Manual measurement is laborious and stressful, whereas vision-based methods are challenged by insufficient dual-view feature fusion, poor robustness to underwater noise, and over-parameterized models unsuitable for edge deployment. To address these issues, a lightweight framework, MECT-MobileViT, is proposed based on MobileViT-xxs. A Morphometric-Guided Multi-Scale Fusion module is designed to couple physical priors with dual-branch visual features, strengthening shape–weight association. An ECA-NL attention block employing instance normalization, GLU gating, and threshold filtering is embedded to enhance feature robustness against visual disturbances typical in aquaculture and to accentuate critical morphological features. A three-stage synergistic pruning strategy—attention head pruning, structured channel pruning, and depthwise separable attention substitution—is applied to achieve substantial compression while preserving representational capacity. Experiments on a self-built lateral–dorsal dual-view dataset show that the proposed model significantly outperforms mainstream benchmarks. The pruned version attains an R² of 0.8266 and an RMSE of 16.4201, with less than 2% accuracy degradation relative to the best unpruned model, and contains only 7.34 M parameters. This study demonstrates a promising prototype for contactless, stress-free weight estimation in largemouth bass and offers new technical insights into feature fusion, noise suppression, and collaborative model compression for aquaculture visual perception. Full article

Pig vocalization recognition can support non-invasive monitoring in precision livestock farming, but labelled pig-sound recordings are often limited for specific behaviours or physiological states. Under few-shot conditions, deep models may overfit, whereas traditional acoustic features may not fully describe class-specific time-frequency patterns. This study proposed PSA-AP, a pig-sound adaptation pipeline that uses log-Mel spectrograms and integrates SpecAugment-based domain expansion, ImageNet-pretrained ResNet18 knowledge transfer, and ArcFace-based feature alignment. The method was designed to reduce dependence on limited labelled samples, improve task-adapted representation learning, and enhance inter-class separability in the embedding space. Experiments were conducted on a five-class few-shot pig vocalization classification task, including eat, estrous, farrowing (fap), howl, and oink sounds collected from 10 adult Landrace pigs. Using $K=\{5,10,15,20,25,30\}$ labelled wav files per class and five random seeds, each selected training wav file and each held-out test wav file was converted into one 1.0 s log-Mel spectrogram for model training or evaluation. Final evaluation was based on the last checkpoint of each training run. PSA-AP achieved the best mean Accuracy, Macro-F1, and UAR at every K-shot setting. At $K=30$, PSA-AP reached 90.60% Accuracy, 90.49% Macro-F1, and 90.60% UAR, exceeding Raw by 7.80, 7.82, and 7.80 percentage points, respectively. These results indicate that the proposed integration of domain expansion, knowledge transfer, and feature alignment provides a feasible supervised adaptation strategy for few-shot pig vocalization recognition within the current protocol. Full article