Search Results (55)

To address the challenges of rapid and accurate grape variety identification in natural orchard environments, along with the demand for efficient deployment on mobile devices, we propose in this paper YOLOv11n-GrapeLite, a lightweight model built upon an enhanced YOLOv11n architecture. First, an Efficient Channel Attention (ECA) mechanism is incorporated into the Neck layer. This mechanism adaptively recalibrates feature channel weights to emphasize those relevant to grape variety recognition, suppress background interference, and enhance target feature perception in complex scenes. Second, an adaptive downsampling (ADown) strategy is employed to replace the traditional convolutional downsampling module, reducing computational complexity while preserving critical features. Finally, the original C3k2 module is redesigned as a multi-scale convolution block (MSCB). This block integrates depthwise separable convolutions with multi-scale convolutions, which achieves significant parameter compression and enhances multi-scale feature extraction. Experimental results demonstrate that the proposed model achieves a mean average precision (mAP) of 91.5%, representing a 0.2% improvement over the original YOLOv11n, along with a 0.6% increase in recall. These results indicate outstanding robustness in complex field scenarios. The model’s parameter count was reduced to 1.87 million, computational complexity to 5.0 GFLOPS, and model size to 4.1 MB. These figures represent reductions of 27.8%, 23.1%, and 25.5%, respectively, compared to the original YOLOv11n, demonstrating significant lightweight optimization. Compared to mainstream models such as YOLOv6, YOLOv8n, YOLOv9s, YOLOV12, YOLOv13 and YOLOv26, the proposed model achieves superior performance in parameter count, computational load, and model size, while maintaining competitive detection accuracy. The YOLOv11n-GrapeLite model efficiently adapts to mobile terminal deployment, providing a feasible and efficient technical solution for real-time, precise identification of grape varieties in complex field scenarios. Full article

Postprandial plasma amino acid (AA) kinetics serve as essential indicators of digestive efficiency and systemic metabolic status in pigs. Traditional kinetic analysis relies on Non-Linear Least Squares (NLS) regression using compartmental models, yet these methods typically demand repeated blood sampling and precise initialization to ensure convergence. In this study, we developed a Physics-Informed Neural Network (PINN) framework by integrating mechanistic Ordinary Differential Equations (ODEs) directly into the deep learning loss function. The framework was evaluated using a benchmark dataset. Specifically, we performed a retrospective analysis by downsampling the original high-frequency data to simulate dense and sparse sampling strategies. The results demonstrate that while both models exhibit high fidelity under dense sampling, PINN maintains superior robustness and predictive accuracy under data-constrained conditions. Under the sparse sampling scenario, PINN reduced the Root Mean Square Error (RMSE) compared to NLS in key metabolic profiles, such as Methionine in the FAA group (p < 0.01) and Lysine in the HYD group (p < 0.05). Unlike NLS, which is sensitive to initial guesses, PINN successfully utilized physical laws as a regularization term to robustly solve the inverse problem, demonstrating superior parameter identification stability and predictive consistency under data-constrained conditions compared to NLS. We concluded that the PINN framework provides a reliable and consistent alternative for modeling the AA dynamics. In the future, it may be possible to reconstruct highly accurate physiological trajectories under optimized sparse sampling conditions. Full article

Apple leaf disease identification with high precision is one of the main challenges in precision agriculture. The datasets usually have class imbalance problems and environmental changes, which negatively impact deep learning approaches. In this paper, an ablation study is proposed to test three different scenarios: V1, a hybrid balanced dataset consisting of 10,028 images; V2, an imbalanced dataset as a baseline consisting of 14,582 original images; and V3, a 3× physical augmentation approach based on the 14,582 images. The classification performance of YOLOv11x was benchmarked against three state-of-the-art CNN architectures: ResNet-152, DenseNet-201, and EfficientNet-B1. The methodology incorporates controlled downsampling for dominant classes alongside scenario-based augmentation for minority classes, utilizing CLAHE-based texture enhancement, illumination simulation, and sensor noise generation. All the models were trained for up to 100 epochs under identical experimental conditions, with early stopping based on validation performance and an 80/20 train-validation split. The experimental results demonstrate that the impact of balancing strategies is model-dependent and does not universally improve performance. This highlights the importance of aligning data balancing strategies with architectural characteristics rather than applying uniform resampling approaches. YOLOv11x achieved its peak accuracy of 99.18% within the V3 configuration, marking a +0.62% improvement over the V2 baseline (99.01%). In contrast, EfficientNet-B1 reached its optimal performance in the V2 configuration (98.43%) without additional intervention. While all the models exhibited consistently high AUC values (≥99.94%), DenseNet-201 achieved the highest value (99.97%) across both V2 and V3 configurations. In fine-grained discrimination, the superior performance of YOLOv11x on challenging cases is verified, with only one incorrect classification (Rust to Scab), while ResNet-152 and DenseNet-201 incorrectly classified eight and seven samples, respectively. Degradation sensitivity analysis under controlled Gaussian noise and motion blur indicated that CNN baseline models maintained stable performance. High minority-class reliability, including a 96.20% F1-score for Grey Spot and 100% precision for Mosaic, further demonstrates effective fine-grained discrimination. Results indicate that data preservation with physically inspired augmentation (V3) is better than resampling-based balancing (V1), especially in terms of global accuracy and minority-class performance. Full article

Accurate segmentation of 3D dental structures is essential for oral diagnosis, orthodontic planning, and digital dentistry. With the rapid advancement of 3D scanning and modeling technologies, high-resolution dental data have become increasingly common. However, existing approaches still struggle to process such high-resolution data efficiently. Current models often suffer from excessive parameter counts, slow inference, high computational overhead, and substantial GPU memory usage. These limitations compel many studies to downsample the input data to reduce training and inference costs—an operation that inevitably diminishes critical geometric details, blurs tooth boundaries, and compromises both fine-grained structural accuracy and model robustness. To address these challenges, this study proposes DiffusionNet++, an end-to-end segmentation framework capable of operating directly on raw high-resolution dental data. Building upon the standard DiffusionNet architecture, our method introduces a normal-enhanced multi-feature input strategy together with a lightweight SE channel-attention mechanism, enabling the model to effectively exploit local directional cues, curvature variations, and other higher-order geometric attributes while adaptively emphasizing discriminative feature channels. Experimental results demonstrate that the coordinates + normal feature configuration consistently delivers the best performance. DiffusionNet++ achieves substantial improvements in overall accuracy (OA), mean Intersection over Union (mIoU), and individual class IoU across all data types, while maintaining strong robustness and generalization on challenging cases, such as missing teeth and partially scanned data. Qualitative visualizations further corroborate these findings, showing superior boundary consistency, finer structural preservation, and enhanced recovery of incomplete regions. Overall, DiffusionNet++ offers an efficient, stable, and highly accurate solution for high-resolution 3D tooth segmentation, providing a powerful foundation for automated digital dentistry research and real-world clinical applications. Full article

Mamba, based on the state space model (SSM), offers an efficient alternative to the quadratic complexity of attention, showing promise for long-sequence data processing and global modeling in 3D object detection. However, applying it to this domain presents specific challenges: traditional serialization methods can compromise the spatial structure of 3D data, and the standard single-layer SSM design may limit cross-layer feature extraction. To address these issues, this paper proposes MSHI-Mamba, a Mamba-based multi-stage hierarchical interaction architecture for 3D backbone networks. We introduce a cross-layer complementary cross-attention module (C3AM) to mitigate feature redundancy in cross-layer encoding, as well as a bi-shift scanning strategy (BSS) that uses hybrid space-filling curves with shift scanning to better preserve spatial continuity and expand the receptive field during serialization. We also develop a voxel densifying downsampling module (VD-DS) to enhance local spatial information and foreground feature density. Experimental results obtained on the KITTI and nuScenes datasets demonstrate that our approach achieves competitive performance, with a 4.2% improvement in the mAP on KITTI, validating the effectiveness of the proposed components. Full article

Current management strategies for sorghum aphids heavily rely on indiscriminate chemical application, leading to severe environmental consequences and impacting food safety. While precision spraying offers a viable remediation for pesticide overuse, its effectiveness depends on accurately locating and classifying pests. To address the critical challenge of segmenting small, swarming aphids in complex field environments, we propose FESW-UNet, a dual-domain attention network that integrates Fourier-enhanced attention, spatial attention, and wavelet-based downsampling into a UNet backbone. We introduce an efficient multi-scale attention (EMA) module between the encoder and decoder to enhance global context perception, enabling the model to capture more accurate relationships between global and local features in the field. In the feature extraction stage, we embed a simple attention module (SimAM) to target key infestation regions while suppressing background noise, thereby enhancing pixel-level discrimination. Furthermore, we replace conventional downsampling with Haar wavelet downsampling (HWD) to reduce resolution while preserving structural edge details. Finally, a Fourier-enhanced attention module (FEAM) is added to the skip-connection layers. By using complex-valued weights to regulate frequency-domain features, FEAM effectively fuses global low-frequency structures with local high-frequency details, thereby enhancing feature representation diversity. Experiments on the Aphid Cluster Segmentation dataset demonstrate that FESW-UNet outperforms other models, achieving an mIoU of 68.76%, mPA of 78.19%, and mF1 of 79.01%. The model also demonstrated strong adaptability on the AphidSeg-Sorghum dataset, achieving an mIoU of 81.22%, mPA of 87.97%, and mF1 of 88.60%. The proposed method offers an efficient and feasible technical solution for monitoring and controlling sorghum aphids through image segmentation, demonstrating broad application potential. Full article

Crop classification of farmland is of great significance for crop monitoring and yield estimation. Airborne hyperspectral systems can provide large-format hyperspectral farmland images. However, traditional machine learning-based classification methods rely heavily on handcrafted feature design, resulting in limited representation capability and poor computational efficiency when processing large-format data. Meanwhile, mainstream deep-learning-based hyperspectral image (HSI) classification methods primarily rely on patch-based input methods, where a label is assigned to each patch, limiting the full utilization of hyperspectral datasets in agricultural applications. In contrast, this paper focuses on the semantic segmentation task in the field of computer vision and proposes a novel HSI crop classification framework named All-Attention Transformer (A²Former), which combines CNN and Transformer based on a fully attention-based mechanism. First, a CNN-based encoder consisting of two blocks, the overlap-downsample and the spectral–spatial attention weights block (SSWB) is constructed to extract multi-scale spectral–spatial features effectively. Second, we propose a lightweight C-VIT block to enhance high-dimensional features while reducing parameter count and computational cost. Third, a Transformer-based decoder block with gated-style weighted fusion and interaction attention (WIAB), along with a fused segmentation head (FH), is developed to precisely model global and local features and align semantic information across multi-scale features, thereby enabling accurate segmentation. Finally, a checkerboard-style sampling strategy is proposed to avoid information leakage and ensure the objectivity and accuracy of model performance evaluation. Experimental results on two public HSI datasets demonstrate the accuracy and efficiency of the proposed A²Former framework, outperforming several well-known patch-free and patch-based methods on two public HSI datasets. Full article

Efficient and accurate identification of spectra from large databases remains a critical challenge in spectroscopic analysis. Previous coarse-to-fine frameworks, typically combining Principal Component Analysis (PCA)-based preprocessing and k-d tree search, have shown that structured search can reduce computational cost without sacrificing accuracy. Building on this foundation, we propose an enhanced algorithm that integrates an improved preprocessing and a novel limited axis check (LAC) method. The preprocessing stage applies running average filtering, downsampling, and threshold-based noise-cutting, followed by PCA to construct a compact, noise-suppressed spectral representation. In the search stage, the proposed LAC algorithm replaces conventional tree-based structures by performing an axis-wise limited-range search and voting strategy to efficiently locate the candidate spectrum closest to the query within the reduced PCA domain. A subsequent refined search determines the closest spectrum by computing distances to the shortlisted candidates. Experimental results demonstrate that the proposed approach attains accuracy equivalent to that of the full search while markedly reducing computational complexity. These results confirm that the integration of enhanced preprocessing and LAC substantially accelerates the spectral search process. Full article

The rapid expansion of the goose farming industry creates a growing need for real-time flock counting and individual-level behavior monitoring. To meet this challenge, this study proposes an improved YOLOv8-based model, termed DAEF-YOLO (DualConv-augmented C2f, ADown down-sampling, Efficient Channel Attention integrated into SPPF, and FocalerIoU regression loss), designed for simultaneous recognition of Sanhua goose individuals and their diverse behaviors. The model incorporates three targeted architectural improvements: (1) a C2f-Dual module that enhances multi-scale feature extraction and fusion, (2) ECA embedded in the SPPF module to refine channel interaction with minimal parameter cost and (3) an ADown down-sampling module that preserves cross-channel information continuity while reducing information loss. Additionally, the adoption of the FocalerIoU loss function enhances bounding-box regression accuracy in complex detection scenarios. Experimental results demonstrate that DAEF-YOLO surpasses YOLOv5s, YOLOv7-Tiny, YOLOv7, YOLOv9s, and YOLOv10s in both accuracy and computational efficiency. Compared with YOLOv8s, DAEF-YOLO achieved a 4.56% increase in precision, 6.37% in recall, 5.50% in F1-score, and 4.59% in mAP@0.5, reaching 94.65%, 92.17%, 93.39%, and 96.10%, respectively. A generalizable classification strategy is further introduced by adding a complementary “Other” category to include behaviors beyond predefined classes. This approach ensures complete recognition coverage and demonstrates strong transferability for multi-task detection across species and environments. Ablation studies indicated that mAP@0.5 remained consistent (~96.1%), while mAP@0.5:0.95 improved in the absence of the “Other” class (75.68% vs. 69.82%). Despite this trade-off, incorporating the “Other” category ensures annotation completeness and more robust multi-task behavior recognition under real-world variability. Full article

Detecting small split pins on transmission lines poses significant challenges, including low accuracy in complex backgrounds and slow inference speeds. To address these limitations, this study proposes a novel two-stage collaborative detection framework. The first stage utilizes a Yolo11x-based model to localize and crop components containing split pins from high-resolution images. This procedure transforms the difficult small-object detection problem into a more manageable, conventional detection task on a simplified background. For the second stage, a new high-performance detector, Mamba-YOLO-SPDC, is introduced. This model enhances the Yolo11 backbone by incorporating a Vision State Space (VSS) block, which leverages Mamba—a State Space Model (SSM) with linear computational complexity—to efficiently capture global context. Furthermore, a Space-to-Depth Convolution (SPD-Conv) module is integrated into the neck to mitigate the loss of fine-grained feature information during downsampling. Experimental results confirm the efficacy of the two-stage strategy. On the cropped dataset, the Mamba-YOLO-SPDC model achieves a mean Average Precision (mAP) of 61.9%, a 238% improvement over the 18.3% mAP obtained by the baseline Yolo11s on the original images. Compared to the conventional SAHI framework, the proposed method provides superior accuracy with a substantial increase in inference speed. This work demonstrates that the ‘localize first, then detect’ strategy, powered by the Mamba-YOLO-SPDC model, offers an effective balance between accuracy and efficiency for small object detection. Full article

Background: Coverage uniformity is pivotal in whole genome sequencing (WGS), as uneven read distributions can obscure clinically relevant variants and compromise downstream analyses. While enzyme-based fragmentation methods for WGS library preparation are widely used, they can introduce sequence-specific biases that disproportionately affect high-GC or low-GC regions. Here, we compare four PCR-free WGS library preparation workflows—one employing mechanical fragmentation and three based on enzymatic fragmentation—to assess their impact on coverage uniformity and variant detection. Results: Libraries were generated with Coriell NA12878 and DNA isolated from DNA blood, saliva, and formalin-fixed paraffin-embedded (FFPE) samples. Sequencing was performed on an Illumina NovaSeq 6000, followed by alignment to the human reference genome (GRCh38/hg38) and local realignment. We assessed coverage at both chromosomal and gene levels, including 504 clinically relevant genes detected in the TruSight™ Oncology 500 (TSO500) panel. Additionally, we examined the relationship between GC content and normalized coverage, as well as variant detection across high- and low-GC regions. Conclusions: Our findings show that mechanical fragmentation yields a more uniform coverage profile across different sample types and across the GC spectrum. Enzymatic workflows, on the other hand, demonstrated more pronounced coverage imbalances, particularly in high-GC regions, potentially affecting the sensitivity of variant detection. This effect was evident in analyses focusing on the TSO500 gene set, where uniform coverage is critical for accurate identification of disease-associated variants and for minimizing false negatives. Downsampling experiments further revealed that mechanical fragmentation maintained lower Single Nucleotide Polymorphism (SNPs) false-negative and false-positive rates at reduced sequencing depths, thereby highlighting the advantages of consistent coverage for resource-efficient WGS. This study introduces a novel framework for evaluating WGS coverage uniformity, providing guidance for optimizing library preparation protocols in clinical and translational research. By quantifying how fragmentation strategies influence coverage depth and variant calling accuracy, laboratories can refine their sequencing workflows to ensure more reliable detection of clinically actionable variants—especially in high-GC regions often implicated in hereditary disease and oncology. Full article

Soybean rust, caused by the fungus Phakopsora pachyrhizi, is recognized as the most devastating disease affecting soybean crops worldwide. In practical applications, performing accurate Phakopsora pachyrhizi segmentation (PPS) is essential for elucidating the morphodynamics of soybean rust, thereby facilitating effective prevention strategies and advancing research on related soybean diseases. Despite its importance, studies focusing on PPS-related datasets and the automatic segmentation of Phakopsora pachyrhizi remain limited. To address this gap, we propose an efficient semantic segmentation model named MS-UNet (Multi-Scale Confusion UNet Network). In the hierarchical Vision Transformer (ViT) module, the feature maps are down-sampled to reduce the lengths of the keys (K) and values (V), thereby minimizing the computational complexity. This design not only lowers the resource demands of the transformer but also enables the network to effectively capture multi-scale and high-resolution features. Additionally, depthwise separable convolutions are employed to compensate for positional information, which alleviates the difficulty the ViT faces in learning robust positional encodings, especially for small datasets. Furthermore, MS-UNet dynamically generates labels for both hard-to-segment and easy-to-segment regions, compelling the network to concentrate on more challenging locations and improving its overall segmentation capability. Compared to the existing state-of-the-art methods, our approach achieves a superior performance in PPS tasks. Full article

As the core component of photovoltaic (PV) power generation systems, PV cells are susceptible to subtle surface defects, including thick lines, cracks, and finger interruptions, primarily caused by stress and material brittleness during the manufacturing process. These defects substantially degrade energy conversion efficiency by inducing both optical and electrical losses, yet existing detection methods struggle to precisely identify and localize them. In addition, the complexity of background noise and other factors further increases the challenge of detecting these subtle defects. To address these challenges, we propose a novel PV Cell Surface Defect Detector (PSDD) that extracts subtle defects both within the backbone network and during feature fusion. In particular, we propose a plug-and-play Subtle Feature Refinement Module (SFRM) that integrates into the backbone to enhance fine-grained feature representation by rearranging local spatial features to the channel dimension, mitigating the loss of detail caused by downsampling. SFRM further employs a general attention mechanism to adaptively enhance key channels associated with subtle defects, improving the representation of fine defect features. In addition, we propose a Background Noise Suppression Block (BNSB) as a key component of the feature aggregation stage, which employs a dual-path strategy to fuse multiscale features, reducing background interference and improving defect saliency. Specifically, the first path uses a Background-Aware Module (BAM) to adaptively suppress noise and emphasize relevant features, while the second path adopts a residual structure to retain the original input features and prevent the loss of critical details. Experiments show that PSDD outperforms other methods, achieving the highest $mA{P}_{50}$ scores of 93.6% on the PVEL-AD. Full article

Space-based on-orbit servicing missions impose stringent requirements for precise identification and localization of satellite components, while existing detection algorithms face dual challenges of insufficient accuracy and excessive computational resource consumption. This paper proposes SLD-YOLO, a lightweight satellite component detection model based on improved YOLO11, balancing accuracy and efficiency through structural optimization and lightweight design. First, we design RLNet, a lightweight backbone network that employs reparameterization mechanisms and hierarchical feature fusion strategies to reduce model complexity by 19.72% while maintaining detection accuracy. Second, we propose the CSP-HSF multi-scale feature fusion module, used in conjunction with PSConv downsampling, to effectively improve the model’s perception of multi-scale objects. Finally, we introduce SimAM, a parameter-free attention mechanism in the detection head to further improve feature representation capability. Experiments on the UESD dataset demonstrate that SLD-YOLO achieves measurable improvements compared to the baseline YOLO11s model across five satellite component detection categories: mAP50 increases by 2.22% to 87.44%, mAP50:95 improves by 1.72% to 63.25%, while computational complexity decreases by 19.72%, parameter count reduces by 25.93%, model file size compresses by 24.59%, and inference speed reaches 90.4 FPS. Validation experiments on the UESD_edition2 dataset further confirm the model’s robustness. This research provides an effective solution for target detection tasks in resource-constrained space environments, demonstrating practical engineering application value. Full article

Agricultural pest detection through image analysis is a key technology in automated pest-monitoring systems. However, some existing pest detection models face excessive model complexity. This study proposes YOLO-LCE, a lightweight model based on the YOLOv8 architecture for agricultural pest detection. Firstly, a Lightweight Complementary Residual (LCR) module is proposed to extract complementary features through a dual-branch structure. It enhances detection performance and reduces model complexity. Additionally, Efficient Partial Convolution (EPConv) is proposed as a downsampling operator. It adopts an asymmetric channel splitting strategy to efficiently utilize features. Furthermore, the Ghost module is introduced to the detection head to reduce computational overhead. Finally, WIoUv3 is used to improve detection performance further. YOLO-LCE is evaluated on the Pest24 dataset. Compared to the baseline model, YOLO-LCE achieves mAP50 improvement of 1.7 percentage points, mAP50-95 improvement of 0.4 percentage points, and precision improvement of 0.5 percentage points. For computational efficiency, parameters are reduced by 43.9%, and GFLOPs are reduced by 33.3%. These metrics demonstrate that YOLO-LCE improves detection accuracy while reducing computational complexity, providing an effective solution for lightweight pest detection. Full article