Search Results (6,624)

Background/Objectives: Accurate peripheral blood cell detection remains difficult in dense smear fields, where touching erythrocytes, small platelets, and staining variability reduce the reliability of box-based object detectors. This study aims to address these limitations by proposing BloodContourNet, a contour-informed and density-aware detection framework for red blood cell, white blood cell, and platelet localization. Method: BloodContourNet is built on YOLOv26-L and integrates three complementary modules. The Hematological Attention Module (HAM) refines high-level features using local convolution and shifted-window attention. The Density-Aware Reweighting Head (DARH) modulates the classification loss for locally sparse or difficult instances without image-level resampling. The Bézier Contour Refinement Head (BCRH) provides a weakly supervised geometric overlap cue for ambiguous dense-region post-processing. Results: Experiments on the TXL-PBC dataset, containing 1260 peripheral smear images and 18,143 annotated cells, benchmarked 25 YOLO variants and 10 Transformer-based or reference detectors under a unified split and evaluation protocol. Across five random seeds, BloodContourNet achieved 99.1% mean Average Precision (mAP) at 50% Intersection-over-Union (IoU) and 87.8% mAP@50:95, improving strict-IoU performance by 1.4 points over YOLOv26-L and 0.7 points over DINO-DETR. Both margins were statistically significant across the five seeds (paired two-sided t-tests, both p < 0.05), and the five-seed 95% confidence interval of the proposed model was [87.5, 88.0]. Conclusions: BloodContourNet primarily improved the strict-localization setting on TXL-PBC, where dense erythrocyte regions and small platelet instances remain challenging for box-based detectors. External patient- or slide-independent validation remains necessary before broader clinical claims can be made. Full article

Detecting small and distant objects in road traffic scenarios remains challenging owing to limited pixel resolution, cluttered backgrounds, and resource constraints on edge computing platforms. This work presents LCA-Net, a computationally efficient framework for small object detection that balances accuracy with model complexity. The framework incorporates three complementary designs: an Adaptive Deformable Downsampling Module (ADDM) that merges asymmetric and deformable convolution operations to improve spatial feature encoding while explicitly accounting for the parameter and computational cost of offset and modulation-mask prediction; a Cross-Scale Feature Fusion Pyramid (CSFFP) specifically engineered for minute objects, which augments multi-scale feature learning and enhances detection of far-field small targets; and a Lightweight Feature-Gated Detection Head (LFGDH) that employs channel–spatial attention to selectively emphasize informative features, thereby reducing both parameter count and computational cost. On Udacity, LCA-Net improves mAP@0.5 by 2.3 percentage points; on VisDrone2019, it improves mAP@0.5 by 1.7 percentage points. Across both benchmarks, the complete model reduces the parameter count by 25.58% and GFLOPs by 16.05% relative to YOLOv8-N. On the RTX A6000, LCA-Net-N reduces forward-pass latency from 1.82 to 1.63 ms, increases throughput from 549 to 613 FPS, and lowers peak GPU memory from 1180 to 1015 MiB. These results demonstrate a favorable accuracy–efficiency trade-off for real-time traffic perception. Full article

In the context of the large-scale integration of high-proportion renewable energy into power grids, Power Conversion Systems (PCS) and Static Var Generator (SVG), as the core power electronic devices for ensuring grid frequency stability and power quality, demand high-level safety and reliability. To tackle challenges such as the wide range of defect sizes in PCS and SVG, the low recognition accuracy for microscopic fuzzy defects, and complex background interference, this paper presents a lightweight and high-precision defect recognition model (RD-YOLO) based on the latest YOLOv11 benchmark. First, an improved Mosaic algorithm is introduced. This algorithm utilizes conflict relationship tables to preserve physical context semantics during traditional non-discriminative data augmentation. Second, to surmount the limitations of scale-aware feature extraction, the YOLOv11 is re-engineered within the backbone network by integrating a Res2Net multi-scale cascaded mechanism. This enhances the network’s capacity to capture both fine-grained defect features and large-scale defect boundaries. Third, Focal Loss is employed for difficult sample detection. Nonlinear gradient modulation is utilized to guide the model to focus on ambiguous defect edges. Finally, the Soft-NMS post-processing strategy significantly enhances the regression accuracy in densely corroded regions. Experimental validation on a self-developed dataset consisting of 8500 high-resolution PCS and SVG defect images reveals that the enhanced RD-YOLO attains an average precision of 89.6% and a frame inference rate of 98 FPS (in RTX 3090), offering robust technical support for intelligent visual maintenance in renewable energy facilities. Full article

Efficient conservation prioritization of Huizhou historic buildings requires joint consideration of visible deterioration and value-bearing architectural elements. This study developed a deep learning-based decision-support framework using an original field dataset of 500 facade images and 2197 audited annotations from five towns in Shexian County, China. Separate YOLOv11n and YOLOv11n-seg models detected six decorative or typological element classes and segmented cracks, spalling, and stains, respectively. Model outputs were converted into a pathology severity index (PSI) based on mask-pixel-area ratios and a decorative value index (DVI) based on weighted element counts; the two indices were combined into a conservation priority index (CPI), whose weighting was examined through sensitivity analysis. On the validation set, decorative-element detection yielded a mAP@50 of 0.655, and pathology segmentation yielded a mask mAP@50 of 0.586. In a preliminary application to four held-out buildings, model-derived priority categories matched the blind ratings of three conservation experts in three cases. The framework offers interpretable evidence for preliminary screening and resource-allocation discussions, but it does not replace field diagnosis. Larger balanced datasets, external building-level validation, and metric calibration are required before regional deployment. Full article

Satellite remote sensing has become a vital data source for monitoring power infrastructure. As critical infrastructure supporting power line operations, the monitoring and maintenance of power towers have become core elements in ensuring grid reliability. However, power tower detection in satellite remote sensing imagery remains challenging because of the substantial scale differences between distribution and transmission towers, the weak feature representation of small objects, and interference from complex backgrounds. To address these challenges, this paper proposes MS-YOLO, a power tower detection algorithm for satellite remote sensing imagery based on multi-scale feature extraction and small object enhancement. First, the poly kernel inception bottleneck (PKI_Bottleneck) module is introduced into the YOLOv9 backbone, enhancing the extraction of scale-diverse features and contextual cues while limiting interference from complex backgrounds. Second, the dual-branch semantic-spatial synergy attention (DSSA) module is introduced. By decoupling deep semantic and shallow spatial information, it effectively preserves small object features while suppressing environmental noise, enhancing the perception capability for small tower objects. Finally, a dynamic focal-weighted intersection over union (DFW-IoU) loss function is introduced to optimize the balance between easy and difficult samples, compelling the model to prioritize small objects and challenging samples during gradient updates. Experimental results demonstrate that MS-YOLO achieves mAP50 values of 79.1% and 95.7% on the two datasets used in this paper, representing improvements of 4.1% and 3.4% over baseline model. These results validate the effectiveness of the improved model for power tower detection in complex remote sensing scenarios. Full article

Background/Objectives: Malignant biliary stricture (MBS) remains difficult to diagnose accurately despite digital single-operator cholangioscopy (DSOC). We developed a deep learning (DL)-based computer-aided detection (CADe) and diagnosis (CADx) system for DSOC-based MBS assessment. Methods: This retrospective multicenter study included 149 patients from one center for model development and internal validation and 25 patients from two independent centers for external evaluation. CADe used a You Only Look Once version 11 (YOLOv11) architecture to localize irregular mucosa, abnormal vasculature, and nodular protrusions defined by the Carlos Robles-Medranda and Mendoza criteria. CADx used a Residual Network-18 classifier with gradient-weighted class activation mapping for interpretability. Results: CADe achieved a mean average precision at 50% intersection-over-union of 91.2%, with a precision of 92.0% and recall of 87.0%. CADx achieved a frame-level area under the receiver operating characteristic curve (AUC) of 0.960 in internal validation and 0.843 in external validation. External frame-level sensitivity was 52.0% and specificity was 95.2%. For the patient-level external endpoint, sensitivity was 85.7%, specificity was 94.4%, accuracy was 92.0%, and AUC was 0.881. Conclusions: The two-stage system combines localization of predefined cholangioscopic features with interpretable diagnostic classification. The small external cohort and marked reduction in frame-level sensitivity preclude firm conclusions regarding generalizability; prospective multicenter and live-procedure evaluation is required. Full article

Early detection of skin cancer significantly improves patient outcomes yet remains challenging due to the visual similarity of lesions and the need for clinical context. This paper proposes a novel Image-driven multimodal deep learning framework for automated skin cancer diagnosis integrating dermoscopic imaging sensors’ clinical metadata and biomedical knowledge graphs. Dermoscopic images acquired from optical skin imaging sensors undergo advanced signal processing including multi-scale CLAHE enhancement and artifact suppression. A YOLOv8-nano sensor-based lesion detector achieves 97.2% mAP@0.5 for region-of-interest extraction. The biomedical knowledge graph (26 nodes 86 edges) encodes dermatological domain knowledge into 32-dimensional disease embeddings. Clinical metadata (age gender anatomical site) is encoded via learned feature vectors. A cross-attention fusion mechanism integrates these multimodal sensor-derived signals. Evaluated on the HAM10000 dataset (10,015 images 7 classes), our full multimodal model achieves 91.35% accuracy outperforming image-only (86.96%) and image+metadata (88.45%) baselines. An ensemble reaches 92.78% state-of-the-art accuracy with significant improvements on challenging classes (BCC +6.0% melanoma +3.8%). Statistical significance is confirmed (p < 0.01 95% CI [90.7% 92.0%]). This work demonstrates that Image-based multimodal signal fusion with structured medical knowledge enhances both diagnostic accuracy and clinical interpretability. Full article

To address the demands of intelligent safflower harvesting scenarios, which require a safflower recognition model with both low computational cost and high detection performance, this paper proposes a lightweight improved model based on YOLOv11n, termed YOLOv11n-Starnet-ADown. To reduce the model’s size, the Starnet network is adopted to replace the backbone network of YOLOv11n. To enhance small-object detection capability while further reducing memory footprint, ADown is used to replace the standard convolutional downsampling module in the neck network of YOLOv11n. The YOLOv11n-Starnet-ADown model was experimentally validated on a self-constructed safflower dataset. The results show that the model achieves an overall precision of 91.6%, a recall of 87.8%, and an mAP@0.5 of 92%; the recognition accuracy for harvestable safflower filaments reaches 96.5%; and the model memory footprint is 3.66 MB, representing a 29.9% reduction compared to the baseline YOLOv11n model. Finally, the detection performance of YOLOv11n-Starnet-ADown was compared with that of four conventional models under different scenarios, confirming the effectiveness of the proposed model. The proposed model exhibits stable detection performance under diverse complex conditions, including overcast skies, occlusion, and backlighting, which adequately satisfies the fundamental requirements for safflower filament detection in real-world environments. Overall, this work offers a lightweight technical solution for the intelligent harvesting of safflower filaments in unstructured settings. Full article

Tunnel lining defects pose significant threats to structural integrity and operational safety. Traditional image processing and machine learning methods often suffer from limited accuracy and poor generalization under complex backgrounds. To address these limitations, this study proposes a lightweight intelligent recognition method based on You Only Look Once version 11 nano (YOLOv11n) for Ground Penetrating Radar (GPR) images of tunnel linings. The backbone is replaced with Mobile Network Version 3 (MobileNetV3) to reduce parameters and Floating Point Operations (FLOPs), while depthwise separable convolution and a streamlined Compressed 2-Stage Fused-Lite (C2f-Lite) structure are integrated into the Neck to further decrease computational overhead. Channel mapping layers are employed to ensure smooth feature transfer, and selective use of Squeeze-and-Excitation (SE) attention and Hard-Swish (H-swish) activation balances detection accuracy with efficiency. Evaluated on a low-power mobile workstation acting as an edge-precursor proxy platform, experimental results demonstrate that the improved YOLOv11n_MobileNetV3 model achieves high accuracy with a mean Average Precision (mAP) at 0.5 of 94.4% and mAP@0.5:0.95 of 62.4%, low computational cost of 4.7 Giga Floating Point Operations (GFLOPs), and fast inference speed of 45 Frames Per Second (FPS). Comparative analysis further confirms its superior balance of detection performance and efficiency over YOLO version 5 (YOLOv5) and YOLO version 8 (YOLOv8) baselines. The proposed approach provides a highly optimized, edge-oriented engineering solution for real-time tunnel lining defect inspection, establishing strong structural and theoretical feasibility for future deployment in embedded systems. Full article

Limited sample diversity poses a major challenge for deep learning-based coal–gangue recognition using mineral laser speckle images under complex industrial conditions. To address this issue, we propose an improved data augmentation framework based on a Deep Convolutional Generative Adversarial Network (DCGAN). Dense Blocks are introduced to enhance high-dimensional feature representation without significantly increasing network complexity, while self-attention modules strengthen multiscale feature interactions between localized flare features and global speckle distributions. Residual-based sampling modules and the Wasserstein GAN with Gradient Penalty (WGAN-GP) objective are further employed to improve gradient propagation and adversarial training stability. Experimental results on synthesizing 512 × 512 mineral laser speckle images show that the proposed model reduces the Fréchet Inception Distance (FID) by 72.75% relative to the baseline DCGAN. Furthermore, the YOLOv5 detectors trained on the augmented datasets achieve a peak mean Average Precision (mAP) of 99.3%, significantly outperforming conventional geometric transformation methods and typical generative baselines including StyleGAN2-ADA and SAGAN. These results demonstrate that the proposed method effectively improves alignment between the synthetic and real distributions, enhances speckle feature diversity and boosts the accuracy and robustness of coal–gangue recognition under limited-sample conditions. Full article

Background: Modern household appliances often present complex interfaces that can be difficult to use, especially for older adults, people with visual impairments, and users with mild cognitive difficulties. In such cases, interacting with appliances may require sustained attention, visuospatial search, working memory, and sequential action planning, while traditional user manuals often provide limited contextual support. Methods: To address this issue, this study presents a proof-of-concept augmented reality (AR) and artificial intelligence (AI)-based system for contextual appliance guidance. The proposed architecture integrates visual sensing, deep learning, and large language models to detect appliance controls, interpret user queries, retrieve relevant information from user manuals, and provide step-by-step guidance directly on the real interface. A YOLOv8 model trained on a custom dataset was used for button detection, YOLO-Seg was employed to enhance visual highlighting through segmentation, and BoT-SORT was used to maintain detection consistency across frames. A Unity-based mobile application displayed real-time AR overlays with customizable visual settings for accessibility needs, such as low vision and color blindness that may be relevant for future accessibility-oriented applications. In addition to its technical pipeline, the system is conceptually relevant as a potential form of external cognitive support because it transforms static manual instructions into situated, sequential, and visually grounded guidance.Results: Experimental results showed promising technical performance for button detection and segmentation, while a preliminary user evaluation in a non-clinical sample suggested good usability, clarity, and acceptability of the interface. Conclusions: These findings support the technical feasibility and preliminary usability of the approach, while cognitive workload, confidence, functional autonomy, and clinical benefit were not directly measured. Targeted validation in older adults, people with visual impairments, and clinical populations is therefore still needed. Future developments will include multimodal feedback, read-aloud guidance, and more specific evaluation of workload, confidence, and functional autonomy. Full article

Detecting small unauthorized UAVs against complex backgrounds is challenging: targets can be just a few pixels wide, background clutter is pervasive, and the detection system must run on resource-constrained edge hardware. This paper presents a lightweight detector built on YOLOv11 that jointly addresses background suppression and edge-deployment efficiency. A serial channel-spatial attention module is embedded into the backbone to sharpen target features and suppress interference. DySample preserves edge details during resolution recovery, and the detection head is restructured by adding a high-resolution P2 branch while removing the large-object P5 head, shifting the focus to small targets without inflating the model. The WIoU v3 loss function stabilizes training by automatically down-weighting low-quality samples. On the DUT Anti-UAV dataset, the proposed model obtains 92.2% mAP@0.5 and 61.5% mAP@0.5:0.95 with only 2.11 M parameters, a reduction of 18.2% relative to the YOLOv11n baseline. Its ability to generalize across different scenarios is verified by cross-dataset evaluation on Det-Fly and LRDDv2. Deployed on an NVIDIA Jetson Orin Nano Super with TensorRT FP16 optimization, the system achieves 37 end-to-end FPS. These findings demonstrate that the presented method significantly improves small-target detection in complex backgrounds while maintaining a lightweight design suitable for real-time edge deployment. Full article

Posture transition behavior in sows approaching parturition provides an important physiological cue for farrowing prediction. However, manual monitoring is time-consuming, labor-intensive and difficult to sustain under nighttime production conditions, while existing machine vision approaches remain limited in their ability to represent continuous posture transitions in complex farm environments. Here, we propose an event-level posture transition recognition framework that integrates YOLOv11n with an RGB–Flow cross-modal temporal network. YOLOv11n is first used to detect basic sow postures at the frame level, after which candidate transition events are automatically generated and refined according to temporal state changes. For each event segment, RGB appearance features and optical-flow motion features are extracted to construct dual-branch spatio-temporal representations. We further develop a multi-scale cross-modal attention temporal network (MS-CMATNet) for event-level behavior classification. The network captures local temporal dynamics through a multi-scale module, enhances interactions between RGB and Flow representations through cross-modal attention, and improves feature discriminability and stability by incorporating temporal–channel attention blocks (TCBAM) and an auxiliary cross-modal consistency loss (AuxCross). Experiments show that MS-CMATNet achieves an Accuracy of 88.14%, a Macro-Recall of 84.04%, and a Weighted-F1 score of 87.66% under the fixed training/validation split, outperforming the compared machine learning models, deep temporal models, and representative temporal and cross-modal baselines. Repeated stratified cross-validation and paired t-tests further confirm that MS-CMATNet achieves statistically reliable improvements over most compared baselines, particularly in Macro-F1 and Weighted-F1. These findings demonstrate the potential of the proposed framework for automated farrowing prediction in smart livestock farming. Full article

UAV inspection images of transmission line spacers often contain small-scale defect targets, complex backgrounds, and weak fine-grained features. We propose MFIA-YOLO, a small-object defect detection model for spacer defects. Using the lightweight YOLOv8n variant as the baseline, we introduce a Multi-scale Spatial Heterogeneous Convolution (MSHC) into the backbone network. This module enhances the extraction of multi-scale features from spacer defect targets. Before the SPPF module, we further construct a Feature Complementary module (FCM). The FCM embeds shallow spatial location information into deep semantic features, thereby alleviating spatial information degradation during small-object detection. In the detection head, a C2f_IAFF module is adopted to adaptively fuse features at different scales through iterative attention-based feature fusion. This design improves the representation of defect targets in complex scenes. In addition, a transmission line spacer defect dataset is constructed from UAV inspection images collected in Xilingol League, Inner Mongolia. Experimental results showed that MFIA-YOLO achieved an mAP50 of 96.53% and an mAP50–95 of 83.50%. Compared with representative YOLO-series models, MFIA-YOLO achieved a better balance between detection accuracy and model complexity. These results demonstrate its effectiveness for accurate spacer defect detection in transmission lines. Full article

Open-surface coalescence of microdroplets is essential for droplet-based microreactors, emulsion processing, and multiphase microfluidics, yet existing methods often require closed channels or patterned electrodes. Here, we report a corona-driven open-oil-film platform that achieves voltage-regulated coalescence of aqueous microdroplets in a simple needle–plate electrode configuration. Positive corona discharge induces coupled electrohydrodynamic effects—including ion transport, interfacial charge redistribution, and Maxwell stresses—that drive oil-film contraction and charge-regulated droplet bouncing, thereby reducing inter-droplet spacing and promoting successive merging. The coalescence rate and final droplet size are tunable via the applied voltage and oil volume: complete coalescence into a single droplet is achieved at 12 kV, and an optimal oil volume of 60 μL maximizes confinement efficiency. To enable quantitative, frame-by-frame analysis, we develop an improved YOLOv5–OC-SORT framework that yields an overall mAP@0.5 of 0.905 for automatic droplet detection and tracking. As a proof-of-concept, the platform achieves electro-demulsification of a surfactant-stabilized water-in-oil emulsion, increasing the average droplet diameter from ~0.005 mm to ~0.2 mm and enabling effective oil–water separation. This work provides a simple, electrode-pattern-free strategy for controllable droplet coalescence and open-surface emulsion breaking. Full article