Search Results (14,075)

Apples are cultivated over a large global area with high yields, and efficient robotic harvesting requires accurate detection and localization, particularly in complex orchard environments where occlusion by leaves and fruits poses substantial challenges. To address this, we proposed a YOLO-CSB model-based method for apple detection and localization, designed to overcome occlusion and enhance the efficiency and accuracy of mechanized harvesting. Firstly, a comprehensive apple dataset was constructed, encompassing various lighting conditions and leaf obstructions, to train the model. Subsequently, the YOLO-CSB model, built upon YOLO11s, was developed with improvements including the integration of a lightweight CSFC Block to reconstruct the backbone, making the model more lightweight; the SEAM component is introduced to improve feature restoration in areas with occlusions, complemented by the efficient BiFPN approach to boost detection precision. Additionally, a 3D positioning technique integrating YOLO-CSB with an RGB-D camera is presented. Validation was conducted via ablation analyses, comparative tests, and 3D localization accuracy assessments in controlled laboratory and structured orchard settings, The YOLO-CSB model demonstrated effectiveness in apple target recognition and localization, with notable advantages under leaf and fruit occlusion conditions. Compared to the baseline YOLO11s model, YOLO-CSB improved mAP by 3.02% and reduced the parameter count by 3.19%. Against mainstream object detection models, YOLO-CSB exhibited significant advantages in detection accuracy and model size, achieving a mAP of 93.69%, precision of 88.82%, recall of 87.58%, and a parameter count of only 9.11 M. The detection accuracy in laboratory settings reached 100%, with average localization errors of 4.15 mm, 3.96 mm, and 4.02 mm in the X, Y, and Z directions, respectively. This method effectively addresses complex occlusion environments, enabling efficient detection and precise localization of apples, providing reliable technical support for mechanized harvesting. Full article

Accurate fine-scale forest mapping is fundamental for ecological monitoring and resource management. While deep learning semantic segmentation methods have advanced the interpretation of high-resolution UAV imagery, their generalization across diverse forest regions remains challenging due to high spatial heterogeneity. To address this, we propose two enhanced versions based on the PP-LiteSeg architecture for robust cross-regional forest segmentation. Version 01 (V01) integrates a multi-branch attention fusion module composed of parallel channel, spatial, and pixel attention branches. This design enables fine-grained feature enhancement and precise boundary delineation in structurally regular artificial forests, such as the Huayuan Forest Farm. As a result, V01 achieves a mIoU of 92.64% and an F1-score of 96.10%, representing an approximately 18 percentage-point mIoU improvement over PSPNet and DeepLabv3+. Building on this, Version 02 (V02) introduces a lightweight residual connection that directly shortcuts the fused features, thereby improving feature stability and robustness under complex textures and illumination, and demonstrates stronger performance in naturally heterogeneous forests (Longhai Township), attaining an mIoU of 91.87% and an F1-score of 95.77% (5.72 percentage-point mIoU gain over DeepLabv3+). We further conduct comprehensive comparisons against conventional CNN baselines as well as representative lightweight and transformer-based models (BiSeNetV2 and SegFormer-B0). In bidirectional cross-region transfer (train on one region and directly test on the other), V02 exhibits the most stable performance with minimal degradation, highlighting its robustness under domain shift. On a combined cross-regional dataset, V02 achieves a leading mIoU of 91.50%, outperforming U-Net, DeepLabv3+, and PSPNet. In summary, V01 excels in boundary delineation for regular plantation forests, whereas V02 shows more stable generalization across highly varied natural forest landscapes, providing practical solutions for region-adaptive UAV forest segmentation. Full article

Accurate semantic segmentation of high-resolution remote sensing imagery is crucial for applications such as land cover mapping, urban development monitoring, and disaster response. However, remote sensing data still present inherent challenges, including complex spatial structures, significant intra-class variability, and diverse object scales, which demand models capable of capturing rich contextual information from both local and global regions. To address these issues, we propose ArgusNet, a novel segmentation framework that enhances multi-scale representations through a series of carefully designed fusion mechanisms. At the core of ArgusNet lies the synergistic integration of Adaptive Windowed Additive Attention (AWAA) and 2D Selective Scan (SS2D). Specifically, our AWAA extends additive attention into a window-based structure with a dynamic routing mechanism, enabling multi-perspective local feature interaction via multiple global query vectors. Furthermore, we introduce a decoder optimization strategy incorporating three-stage feature fusion and a Macro Guidance Module (MGM) to improve spatial detail preservation and semantic consistency. Experiments on benchmark remote sensing datasets demonstrate that ArgusNet achieves competitive and improved segmentation performance compared to state-of-the-art methods, particularly in scenarios requiring fine-grained object delineation and robust multi-scale contextual understanding. Full article

Soil organic matter (SOM) is a key indicator of arable land quality and the global carbon cycle; accurate regional-scale SOM estimation is vitally significant for sustainable agricultural development and climate change research. This study evaluates a multisource data-fusion approach for improving cropland SOM prediction in Yucheng City, Shandong Province, China. We applied a Local Energy Weighted Discrete Wavelet Transform (LEW-DWT) to fuse multi-temporal Landsat 8 imagery (2014–2023). Quantitative analysis (e.g., Information Entropy and Average Gradient) demonstrated that LEW-DWT effectively preserved high-frequency spatial details and texture features of fragmented croplands better than traditional DWT and simple splicing methods. These were combined with 41 environmental predictors to construct composite Ev–Tn–Mm features (environmental variables, temporal NDVI features, and multi-temporal multispectral information). Random Forest (RF) and Convolutional Neural Network (CNN) models were trained and compared to assess the contribution of the fused data to SOM mapping. Key findings are: (1) Comparative analysis showed that the LEW-DWT fusion strategy achieved the lowest spectral distortion and highest spatial fidelity. Using the fused multitemporal dataset, the CNN attained the highest predictive performance for SOM (R² = 0.49). (2) Using the Ev–Tn–Mm features, the CNN achieved R² = 0.62, outperforming the RF model (R² = 0.53). Despite the limited sample size, the optimized shallow CNN architecture effectively extracted local spatial features while mitigating overfitting. (3) Variable importance analysis based on the RF model reveals that mean soil moisture is the primary single variable influencing the SOM, (relative importance 15.22%), with the NDVI phase among time-series features (1.80%) and the SWIR1 band among fused multispectral bands (1.38%). (4) By category, soil moisture-related variables contributed 45.84% of total importance, followed by climatic factors. The proposed multisource fusion framework offers a practical solution for regional SOM digital monitoring and can support precision agriculture and soil carbon management. Full article

Offshore oil exploration and the volume of imported crude oil shipping have increased steadily, elevating the risk of oil spills. An advanced offshore oil film identification method is proposed to realize the accurate and robust recognition and segmentation of oil films from marine radar images in offshore oil spill detection. This method integrates feature engineering with an improved Beetle Antennae Search (BAS) optimization algorithm, aiming to address the key issues of low discrimination between oil films and complex marine backgrounds and insufficient spill boundary localization accuracy in radar image analysis. First, the raw radar image was transformed into the Cartesian coordinate system, and a filtering procedure was applied to attenuate interference. Subsequently, the gray distribution and local contrast of the denoised image was further improved. Afterwards, the complexity of the grayscale distribution within each feature map was quantified using Shannon entropy. The Top-K feature maps with the highest entropy values were subsequently used to construct an information-rich subset. The subset was then processed through a pixel-wise averaging strategy to generate a coupled feature image. Then, Otsu threshold was used to refine ocean wave regions. Finally, the oil films were segmented with an improved BAS optimization algorithm. The fitness function of the improved BAS algorithm was augmented through the integration of edge fitting accuracy, and a target-proximity penalization scheme. Through an adaptive step-length modulation paradigm and Perceptual Mechanism, it can achieve a marked improvement in search accuracy and achieving precise segmentation of oil slicks. The detection accuracy of the proposed method is significantly enhanced relative to the traditional BAS algorithm and existing marine radar oil spill detection methods. The IOU, Dice, recall and F1-score reached 81.2%, 89.6%, 85.2%, and 90.1% respectively. This method not only advances the methodological rigor of spill detection but also provides critical data support for the development of more effective control and remediation practices. Full article

Surgical robots are increasingly utilized in medicine for their reliability and convenience. An accurate kinematic model is essential for precise robot control and enhanced surgical safety. However, the high nonlinearity and computational complexity of kinematics pose significant challenges to traditional numerical methods. This study designs a surgical robotic arm and establishes the motion mapping relationship between the joint space and the end-effector workspace. Subsequently, a hybrid kinematic estimation model based on deep pyramid convolutional neural network (DPCNN) is proposed, which integrates data sampling and an attention mechanism to improve computational accuracy. The Latin hypercube sampling technique is used to improve the uniformity of dataset sampling, and the triplet-fusion self-attention mechanism (TFSAM) is employed for multi-scale feature information. Experimental results show that the TFSAM-DPCNN model achieves coefficient of determination (R²) values exceeding 0.99 across all testing scenarios. Compared with other models, the proposed model reduced the root mean square error (RMSE) by up to 81.34%, exhibiting superior performance. Furthermore, the developed 3D simulation platform validates the effectiveness of the proposed model. This study offers a robust solution for multi-degree-of-freedom robot modeling, with potential applications across a range of robotic motion control systems. Full article

Landslide susceptibility maps (LSMs) are crucial for risk mitigation, but integrating Multi-temporal Interferometric Synthetic Aperture Radar (MT-InSAR) data is often hampered by a lack of physical interpretation. To address this issue, this study proposes an enhanced modeling framework that integrates multi-source monitoring data by coupling dynamic deformation features. Ground deformation velocity is obtained using MT-InSAR and embedded as dynamic physical constraints into the loss function of a Multi-Layer Perceptron (MLP) model. This approach enables the joint optimization of static geological factors and dynamic deformation characteristics in landslide susceptibility prediction. The proposed framework was applied to Zunyi City, Guizhou Province, China, utilizing an inventory of landslide hazard sites and a dataset of 16 susceptibility factors for model training and evaluation. The results demonstrated that the dynamically constrained model significantly improved predictive performance (AUC = 0.976, an increase of 0.032 compared to the baseline model), and enhanced spatial consistency, reflected by an average increase of 0.0184 in predicted susceptibility for inventoried landslide hazard sites. The framework also outperformed other conventional machine learning models across multiple evaluation metrics. Furthermore, SHAP (SHapley Additive exPlanations) analysis revealed that slope (18.68%), DEM (13.26%), rainfall (11.57%), and mining activities (8.79%) were the primary contributing factors in high-susceptibility areas. This study offers a physically interpretable and robust methodology that advances landslide risk assessment and contributes to disaster prevention strategies. Full article

Accurate crop type mapping remains challenging in regions where persistent cloud cover limits the availability of optical imagery. Multi-temporal dual-polarization Sentinel-1 SAR data offer an all-weather alternative, yet existing approaches often underutilize polarization information and rely on single-scale temporal aggregation. This study proposes PTU-Net, a polarization–temporal U-Net designed specifically for pixel-wise crop segmentation from SAR time series. The model introduces a Polarization Channel Attention module to construct physically meaningful VV/VH combinations and adaptively enhance their contributions. It also incorporates a Multi-Scale Temporal Self-Attention mechanism to model pixel-level backscatter trajectories across multiple spatial resolutions. Using a 12-date Sentinel-1 stack over Kings County, California, and high-quality crop-type reference labels, the model was trained and evaluated under a spatially independent split. Results show that PTU-Net outperforms GRU, ConvLSTM, 3D U-Net, and U-Net–ConvLSTM baselines, achieving the highest overall accuracy and mean IoU among all tested models. Ablation studies confirm that both polarization enhancement and multi-scale temporal modeling contribute substantially to performance gains. These findings demonstrate that integrating polarization-aware feature construction with scale-adaptive temporal reasoning can substantially improve the effectiveness of SAR-based crop mapping, offering a promising direction for operational agricultural monitoring. Full article

High-temperature superconducting (HTS) conductor on round core (CORC) cables possess the combined features of high current-carrying capacity, strong mechanical properties, and excellent isotropic flexibility. The current relative research on the electromagnetic properties of straight CORC cables has been exceedingly mature. In high-field magnets, CORC cables are typically bent into coils to meet the compactness requirement. Evaluating the bending characteristics of CORC cables, particularly their post-bending electromagnetic properties, holds great scientific significance. In this paper, CORC cables with different sizes of central formers were fabricated to explore the impacts of the bending process and strain on their transport AC loss characteristics. A mapping method was proposed to couple mechanical and electromagnetic models. Results show that the cable sample with a 4 mm outer diameter of the central former exhibits a superior bending characteristic. The bending process on the transport AC loss of CORC cable lies in the redistribution of the magnetic field, while strain mainly affects AC loss by leading to local critical current (Ic) degradation. CORC cables with small bending diameters require electromagnetic–mechanical-coupling simulation to predict their electromagnetic characteristics accurately. Conclusions drawn from this paper will provide invaluable guidance for the fabrication of bent CORC cables. Full article

In underwater detection tasks involving bleached corals, band disease corals, and white pox disease corals, several challenges persist, including high morphological variability, difficulty in identifying small pathological regions, interference from complex underwater environments, and constraints imposed by underwater hardware. To address these issues, a lightweight underwater diseased coral target detection method, termed CD-YOLO, is proposed. Specifically, (1) a lightweight network named CDShuffleNet is constructed to replace the YOLO11 backbone, aiming to reduce model complexity while preserving detection performance; (2) a SPDConv downsampling convolution module is introduced to reduce the loss of fine-grained coral detail information during the downsampling process; and (3) attention mechanisms are incorporated through an engineering-oriented integration of EMA into the C2PSA module and the adoption of SENetV2, in order to enhance the representation of color and shape features of pathological regions and suppress interference from complex underwater environments. Experimental results demonstrate that the proposed improvements yield consistent gains in both model lightweighting and detection performance under the adopted evaluation settings. Specifically, the number of parameters, computational cost, and model size are reduced by 20.6%, 21.9%, and 18.9%, respectively, while mAP increases by 4.3 percentage points. Comparative experiments further show that the proposed method achieves a markedly higher mAP than several other state-of-the-art models. In addition, experiments conducted on the BHD Coral dataset provide preliminary evidence of cross-dataset adaptability of the proposed model. Overall, this study presents a task-oriented and application-driven improvement, demonstrating that the effective integration of lightweight components can achieve a favorable balance between model efficiency and detection performance in underwater diseased coral detection tasks. Full article

Video synthetic aperture radar could provide more valuable information than static images. However, it suffers from several difficulties, such as strong clutter, low signal-to-noise ratio, and variable target scale. The task of moving target detection is therefore difficult to achieve. To solve these problems, this paper proposes a model and data co-driven learning method called look once on principal components (PC-YOLO). Unlike preceding works, we regarded the imaging scenario as a combination of low-rank and sparse scenes in theory. The former models the global, slowly varying background information, while the latter expresses the localized anomalies. These were then separated using the principal component decomposition technique to reduce the clutter while simultaneously enhancing the moving targets. The resulting principal components were then handled by an improved version of the look once framework. Since the moving targets featured various scales and weak scattering coefficients, the hierarchical attention mechanism and the cross-scale feature fusion strategy were introduced to further improve the detection performance. Finally, multiple rounds of experiments were performed to verify the proposed method, with the results proving that it could achieve more than 30% improvement in mAP compared to classical methods. Full article

We developed a deep learning model for automated extraction and assessment of earthquake damage from dashcam and post-disaster images. By combining a custom-designed deep multi-layer perceptron model with an enhanced feature extraction methodology, we accurately classify image patches into “No Damage” (Class 0) and “Damage” (Class 1). The proposed model incorporates a rich set of image-based features, including color statistics, edge properties, and texture descriptors, along with strategies to mitigate class imbalance. Experimental results demonstrate the model’s high performance in identifying damaged areas, particularly its excellent recall for the “Damage” class, which is critical for rapid disaster response and damage mapping. Full article

The rapid spread of fires underscores the urgency of high-accuracy fire smoke detection for public safety, but early fires pose major challenges—small flame/smoke targets, blurred boundaries, low contrast, and complex background interference—limiting the performance of existing models. To address these issues, this paper proposes SFFA-YOLO, an engineering-oriented improved algorithm based on the YOLOv11 framework for fire smoke detection, which achieves a balanced trade-off between detection precision, real-time performance, and lightweight deployment. The model integrates three synergistic optimization modules for targeted scene adaptation: (1) the FMFA module for cross-scale feature fusion to enhance thin smoke and small flame recognition; (2) the SGCA module for joint channel-spatial feature focusing to improve target localization accuracy; (3) the SDA-Loss function for dynamic weight adjustment based on target size and clarity to stabilize small target detection. Validated on the self-built FS-Blend dataset (supplemented with difficult samples such as distant thin smoke and backlit flames), SFFA-YOLO outperforms mainstream models (YOLOv8, YOLOv9, Faster R-CNN) in key metrics. Compared with the YOLOv11s baseline, it achieves a 2.5% Precision improvement and 3.9% mAP@0.5 improvement while reducing parameters by 12.8%, confirming its reliability as a real-time fire smoke detection solution. Full article

X-ray imaging is the most widely used modality for fracture diagnosis in clinical practice due to its efficiency and accessibility. However, automated X-ray fracture detection faces two major challenges. First, fracture regions often contain subtle and low-contrast crack patterns, making it difficult for models to capture essential fine details. Second, fractures exhibit strong directional variability, while conventional detection frameworks have limited capacity to model rotation changes. To address these issues, we propose FDEA-Net, an enhanced detection framework tailored for fracture analysis. It integrates two lightweight improvement modules. The Fracture Detail Enhancer (FDE) strengthens high-frequency textures and fine-grained structural cues that are closely associated with fracture lines. The Rotation Aware Encoder (RAE) encodes rotation-sensitive representations, improving recognition under diverse fracture orientations. Experiments on a large-scale X-ray fracture dataset show clear performance gains, achieving an mAP50 of 0.742 and an F1-score of 0.738. These findings verify the effectiveness of combining detail enhancement with rotation-aware feature modeling. FDEA-Net provides an efficient and generalizable solution for reliable detection of subtle fractures in medical imaging. Full article

The detection of defects in key transmission-line equipment under complex environments often suffers from insufficient accuracy and reliability due to background interference and multi-scale feature variations. To address this issue, this paper proposes an improved defect detection model based on YOLOv11, named DCDW-YOLOv11. The model introduces deformable convolution C2f_DCNv3 in the backbone network to enhance adaptability to geometric deformations of targets, and incorporates the convolutional block attention module (CBAM) to highlight defect features while suppressing background interference. In the detection head, a dynamic head structure (DyHead) is adopted to achieve cross-layer multi-scale feature fusion and collaborative perception, along with the WIoU loss function to optimize bounding box regression and sample weight allocation. Experimental results demonstrate that on the transmission-line equipment defect dataset, DCDW-YOLOv11 achieves an accuracy, recall, and mAP of 94.4%, 92.8%, and 96.3%, respectively, representing improvements of 2.8%, 7.0%, and 4.4% over the original YOLOv11, and outperforming other mainstream detection models. The proposed method can provide high-precision and highly reliable defect detection support for intelligent inspection of transmission lines in complex scenarios. Full article