Search Results (26)

The sex ratio of the rice stem borer, Chilo suppressalis (Walker), is important for assessing reproductive potential and outbreak risk, but automated sex classification in field trap images is hindered by small targets, variable postures, subtle morphological differences and complex backgrounds. An edge–cloud collaborative system was developed for fine-grained sex classification of the rice stem borer. The edge terminal performs image acquisition, target detection, ROI extraction, and foreground enhancement, while the cloud platform conducts sex classification and result management. To improve small-target localization, YOLO-CSNet was constructed by integrating a global attention mechanism and adaptive spatial feature fusion into YOLO11n. Within detection-constrained ROIs, Haar-like features and an AdaBoost discriminator were used to suppress tray textures, shadows and non-target regions. For sex classification, DRS-ViT combines convolutional patch embedding, a discriminative-region soft-weighting module and a KANsformer encoder to represent weak sex-related cues and model global structural relationships. YOLO-CSNet achieved precision, recall, mAP@0.5, and mAP@0.5:0.95 values of 94.36%, 93.19%, 95.32%, and 73.95%, respectively. DRS-ViT achieved accuracy, precision, recall, and F1-score values of 93.93%, 94.68%, 93.29%, and 93.91%, respectively. In a temporally independent field deployment conducted at one Shandong site from May to June 2026, the system achieved an image-upload success rate of 91.7% and an end-to-end accuracy of 87.9%. The field results support the feasibility of the workflow under the tested conditions. Future work will extend field validation across multiple sites and seasons to evaluate system generalizability. Full article

Accurate detection of sub-millimeter defects in reactor core-plate cotter-pin holes is essential for nuclear safety. However, underwater inspection images often suffer from low signal-to-noise ratios, weak boundary responses, and pseudo-edge interference, resulting in unstable localization of defects. Existing deformable and attention-based detectors remain vulnerable to sampling drift and semantic–boundary inconsistency under such conditions. To address these challenges, an Edge-Geometry-Guided Deformable Detection Network (EGD-Net) is proposed for underwater defect detection. EGD-Net introduces an edge-geometry-constrained deformable sampling mechanism that embeds edge-confidence priors into deformable convolution to improve boundary-aware feature sampling. A cross-level semantic–geometric alignment strategy is designed to enhance the interaction between defect semantics and geometric boundary cues, while a top-down feedback recalibration mechanism improves multi-scale response consistency for weak defects. Experiments on the Core-Plate Pin-Hole Defect (CPHD) dataset demonstrate that EGD-Net achieves the highest AP@[0.5:0.95] on both datasets while maintaining competitive or superior Precision, Recall, and F1-score while reducing engineering center error under a fixed operating point. Performance across the two complementary domains suggests its robustness to variations between coupon images and practical underwater inspection scenes. These results indicate that EGD-Net provides a reliable solution for boundary-sensitive localization of underwater sub-millimeter defects in nuclear inspection. Full article

Objective: To address small bolt defect targets, complex background interference, and limited edge deployment in hilly and mountainous rail transport environments, a detection method balancing accuracy, lightweight design, and real-time performance was proposed. Methods: A track image dataset containing missing bolts, loose bolts, and missing nuts was constructed. Based on YOLOv11m, HFERBC3K2 was developed by replacing the standard bottleneck in C3K2 with a High-Frequency Enhancement Residual Block to strengthen edge, texture, and local structural feature extraction. A Spectral Enhanced Feed-Forward module was introduced into C2PSA to form SEFFNC2PSA, enhancing defect-related frequency components and suppressing background interference through adaptive frequency-domain modulation. The integrated model was named HFSE-YOLOv11. Channel-level structured pruning was then applied, and the model with a pruning ratio of 0.5 was named LHFSE-YOLOv11. Results: On the validation set, HFSE-YOLOv11 achieved 91.7% precision, 93.4% recall, 91.3% mAP@0.5, and 80.2% mAP@0.5:0.95, improving upon YOLOv11m by 3.6, 2.2, 1.2, and 3.1 percentage points, respectively. After pruning, LHFSE-YOLOv11 had 15.9 M parameters, 53.8 GFLOPs, and a 32.5 MB model size, representing reductions of 16.3%, 14.3%, and 11.7%, while mAP@0.5 and mAP@0.5:0.95 decreased by only 0.3 and 0.9 percentage points. On the independent test set, it achieved 91.7% precision, 93.4% recall, 91.0% mAP@0.5, 79.3% mAP@0.5:0.95, and 81.5 FPS, outperforming all compared models in the four detection metrics. Conclusion: LHFSE-YOLOv11 balances accuracy, efficiency, and model size, supporting deployment on vehicle-mounted inspection terminals and resource-constrained edge devices. Full article

Field-road cracks in high-standard farmland are often slender, low-contrast, and surrounded by complex textures that cause U-Net-based models to misclassify aggregates, tire marks, shadows, and repair edges as cracks. To reduce these false positives, this study develops a task-oriented context-guided hard-negative background suppression network (CGHN-Net) based on Squeeze-and-Excitation U-Net (SE-U-Net). The context-guided skip gate (CGSG), a same-resolution adaptation of additive attention gating, uses already upsampled decoder features as semantic guides to filter encoder skip features at all three scales. Hard-negative background suppression loss (HNBS Loss), a background-restricted hard-example mining objective, further targets elevated-probability responses within ground-truth background regions. The dataset comprised 2235 vehicle-acquired grayscale pavement images from independent sessions and mutually exclusive road sections: 1684 for training, 464 for validation, and 87 for testing. Across three random seeds, CGHN-Net achieved Dice, IoU, precision, recall, and FP area ratio values of 0.8682 ± 0.0055, 0.7791 ± 0.0102, 0.8780 ± 0.0161, 0.8734 ± 0.0266, and 0.0042 ± 0.0008, respectively. Against U-Net, Attention U-Net, UNet++, DeepLabV3+, SegFormer-B0, and BGCrack, it achieved the highest Dice, IoU, and recall, indicating the strongest overall overlap and crack recovery. Sequence-aware paired analysis against UNet++ preserved contiguous acquisition order through block lengths of 3, 5, and 10 images, and all block-bootstrap confidence intervals excluded zero. On 100 held-out crack-free images, CGHN-Net also achieved the lowest post-processed image-level false-alarm rate and FP area ratio among the included models. Additional three-seed validation on the independently acquired public CrackForest Dataset (CFD), with the selected models retrained on mutually exclusive CFD partitions, showed that CGHN-Net achieved Dice, IoU, and recall of 0.6679 ± 0.0162, 0.5028 ± 0.0182, and 0.9486 ± 0.0085, respectively, exceeding UNet++ and BGCrack in overlap and crack recovery. The results support the task-oriented combination of same-resolution skip filtering and background-restricted hard-example mining for suppressing texture-induced false responses, while the CFD experiment is interpreted as independent public-dataset retraining rather than zero-shot transfer. Full article

Visible fracture detection in underground roadways is challenging because fracture targets are often elongated, weakly contrasted, irregularly distributed, and easily confused with complex rock-wall textures. In addition, uneven illumination, dust interference, and blurred boundaries further reduce the reliability of conventional crack detection and segmentation methods. To improve fracture instance segmentation under such conditions, this study proposes YOLOv13n-seg-crack, an improved lightweight instance segmentation model based on a self-constructed YOLOv13n-seg baseline. The proposed model introduces three main improvements. First, a C2f-CA module is embedded into the backbone to enhance spatial-position perception and directional feature representation for elongated fractures. Second, a shallow high-resolution branch and auxiliary feature paths, denoted as B2 + H2 + P2, are constructed to strengthen the transmission of fine edge and texture information for small and discontinuous fracture targets. Third, an Edge-aware SIoU (EA-SIoU) loss is designed by adding edge-consistency and aspect-ratio constraints, thereby improving bounding-box localization for narrow and irregular fracture regions. Experiments were conducted on the public Crack Segmentation Dataset and an expanded self-built underground roadway dataset collected at the Woniushan Experimental Base. On the public dataset, YOLOv13n-seg-crack achieved detection Precision, Recall, mAP50, and mAP50:95 of 84.56%, 65.49%, 71.51%, and 52.72%, respectively, and mask Precision, Recall, mAP50, and mAP50:95 of 74.94%, 60.38%, 59.52%, and 21.99%, respectively. Compared with YOLOv13n-seg, the detection mAP50 and mask mAP50 increased by 1.91 and 3.19 percentage points, respectively, while the model maintained an inference speed of 168.73 FPS. Repeated-seed experiments, ablation studies, and degraded-image tests further demonstrate the stability and robustness of the proposed improvements. On the self-built underground roadway dataset containing 100 images and 118 annotated fracture instances, YOLOv13n-seg-crack improved detection mAP50 from 68.72% to 73.36% and mask mAP50 from 30.76% to 33.74%. These results indicate that the proposed method provides an effective and lightweight solution for visible fracture detection and instance segmentation in complex underground roadway scenes. Full article

Given the issues in natural orchard environments, such as large-scale variations of defective citrus fruits, weak texture boundaries, strong illumination changes, branch and leaf occlusion, and significant background interference, this paper constructs a lightweight detection model, RT-DETR-DCEA, based on RT-DETR-R18. This model is improved through four aspects: “fine-grained defective feature extraction—multi-scale feature fusion—up-sampling detail recovery—global feature interaction for noise suppression”. First, a Dynamic Hybrid Convolution Module (DIMB) is introduced into the backbone network, drawing on the ideas of Inception-style multi-branch depthwise convolution and MetaFormer residual mixing. It extracts local textures of various forms through square convolution, horizontal strip convolution, and vertical strip convolution, and utilizes dynamic branch weights to enhance the model’s adaptability to irregular defects such as lesions, mildew, and external damage. Second, a Content-Guided Attention Feature Fusion Network (CGAFN) is designed in the neck network, which achieves adaptive fusion of low-level detail features and high-level semantic features through channel attention, spatial attention, and pixel-level fusion weights. Next, a lightweight upsampling enhancement module called EUCB-SC is constructed, which introduces channel rearrangement and Shift spatial offset into the efficient upsampling convolutional structure to enhance the local spatial interaction capability of upsampled features with low parameter overhead. Finally, adaptive sparse self-attention is introduced into the AIFI module to form AIFI-ASSA, which suppresses irrelevant background interactions through a sparse attention branch and retains necessary contextual information through a dense attention branch. The experimental results demonstrate that on a dataset containing four categories of citrus images—healthy, diseased, moldy, and severely externally damaged—RT-DETR-DCEA achieves 92.1% Precision, 86.1% Recall, and 91.8% mAP@50, with a parameter count of 1.477 × 10⁷ and an inference speed of 81 FPS. Compared with the original RT-DETR-R18 and various YOLO series models, this method strikes a favorable balance among detection accuracy, recall capability, and model lightweightness. This paper also discusses limitations such as data scale, ratio of private data, single training result, and insufficient validation on edge devices, providing a basis for subsequent cross-regional data validation and real-world deployment testing. Full article

Human pose detection is fundamental to quantitative sports training analysis in college general education courses, enabling an objective assessment of college students’ movement quality and the early identification of sports injury risks among non-professional athletes. At present, those detectors based on YOLO have encountered difficulties in capturing the continuous movement patterns of college athletes in routine training, maintaining the regression accuracy of different size posture targets, and maintaining the real-time calculation speed in the campus sports environment. Furthermore, most existing pose-estimation frameworks are optimized for general scenes and fail to address the unique challenges of college physical education settings, including non-standard student movements, diverse skill levels, and strict cost constraints for large-scale deployment. In order to solve these problems, we put forward PPLCNet-YOLOv11, which is a simplified human posture-estimation framework designed for college physical education. This model is optimized by three key improvements: (1) replacing the original backbone network with PPLCNet to enhance feature extraction, while strictly observing the strict FLOPs and parameter restrictions; (2) an enhanced Multi-Scale Attention Mechanism (MSAM) that combines adaptive scale perception, hierarchical channel attention, and pose-sensitive spatial attention to better represent elongated anatomical structures and multi-scale pose cues; and (3) an improved enhanced IoU loss function that incorporates scale-aware and aspect-ratio-aware penalty terms to refine the bounding box adjustment for atypical and sports-specific gestures. Experiments on both a dedicated college student sports pose dataset and two public benchmark datasets (COCO Keypoints 2017 and MPII Human Pose) demonstrate that PPLCNet-YOLOv11 achieves 77.8% mAP@0.5 and 37.09% mAP@0.95 based on the campus dataset, with 82.34% precision and 75.00% recall, while requiring only 2.62 M parameters and 6.38 GFLOPs. Extensive inference speed tests show that the model achieves 127 FPS on an NVIDIA RTX 4090 GPU, 38 FPS on an Intel i7-12700 CPU, and 16 FPS on a Jetson Nano edge device, meeting the real-time requirements of campus sports monitoring. Compared with mainstream lightweight YOLO variants and state-of-the-art specialized pose-estimation models, our proposed method improves mAP@0.5 by 4.93–12.6 percentage points based on the campus dataset. All experiments were repeated five times with different random seeds, and we report mean values with standard deviations and statistical significance tests to ensure result reliability. These results indicate that PPLCNet-YOLOv11 provides an accurate and resource-efficient solution for real-time pose evaluation in college physical training. Full article

Rapid detection of wilt-affected pine crowns in mountainous forests is hindered by occlusion, self-shadowing, and heterogeneous backgrounds in conventional nadir products. We evaluated whether oblique UAV RGB imagery improves crown-level detection relative to nadir imagery under matched site, season, sensor, and workflow conditions. The workflow was designed for rapid post-flight screening of geotagged UAV photographs. Paired nadir orthophotos and 45–70° oblique photographs were acquired over pine stands in Wenshan Prefecture, Yunnan, China, and organized into D1 (nadir), D2 (oblique), and D3 (simple mixed-view concatenation). Three YOLO11 detectors were trained for crown shoot damage ratio (SDR)-derived operational classes: early-stage (SDR < 50%), severely damaged (SDR ≥ 50%), and withered (needle-free dead crowns). A paired crown-level RGB subset (n = 20 crowns observed in both views) was analyzed as supporting evidence for view-dependent appearance differences. The oblique-image model (D2) achieved the highest validation performance, with precision of 0.994, recall of 0.991, F1-score of 0.989, mAP@0.5 of 0.995, and mAP@0.5:0.95 of 0.880. The paired subset showed a significant multivariate RGB profile difference between views (Hotelling’s T2 = 58.91, F = 3.10, p = 0.044), driven mainly by reduced Excess Green and greater dispersion of blue-related traits under oblique viewing. These results indicate that oblique UAV photographs retain additional crown-edge, lateral-structure, and chromatic context for detecting wilt-affected pine crowns. Oblique RGB imagery therefore provides a practical, low-cost input for rapid forest health surveillance and targeted field verification in rugged pine landscapes. Full article

Accurate detection of cardboard boxes is essential to mobile manipulators to perform pick-and-place operations in warehouses. Conventional object detection methods like YOLOv11 struggle in low-texture and occluded environments. This paper presents YOLO-REFB, a novel object detection framework for real-time cardboard box detection in robotic manipulation using a dual-arm mobile robot (DAMR) operating in indoor warehouse environments. The proposed approach enhances the network by integrating the Rectangular Edge Fusion Block (REFB) into the YOLOv11 architecture; it focuses on learning the geometric and structural features of cardboard boxes. Enhanced edge information extraction and feature fusion improve training stability and localization accuracy. A custom dataset of 3501 annotated images, collected under varied conditions, was utilized. The images were randomly assigned to training and validation sets while keeping an 80:20 ratio. They were manually annotated and trained using Roboflow software, ensuring precise alignment of bounding boxes with cardboard box edges for accurate comparison with existing YOLO models. The model outperformed existing YOLO variants (YOLOv8n and YOLOv5n) in terms of precision (89.29%), recall (83.95%), and F1-score (86.54%). YOLO-REFB achieved improved localization metrics, including mean Average Precision (mAP)@0.5 (91.68%) and mAP@0.5:0.95 (68.61%). The inclusion of REFB was essential to performance gains, enabling effective detection of objects in challenging environments. Future developments may include 3D pose estimation and multi-object grasp planning for advanced robotic manipulation. Full article

The automatic extraction of seismic reflection events is fundamental to seismic interpretation and structural identification in oil and gas exploration, particularly for large-scale regional surveys and preliminary basin-scale assessments. Although the B-COSFIRE (Bar-Combination of Shifted Filter Responses) method has demonstrated strong capability in detecting ridge-like structures, its application in large-scale seismic processing is limited by high computational cost and complex filter bank configuration. Conventional edge detectors such as the Canny operator are computationally efficient but often produce fragmented and noise-sensitive results in low signal-to-noise ratio (SNR) seismic data because they rely solely on local gradient information and ignore the spatial continuity of geological horizons. To overcome these limitations, this study proposes a lightweight and computationally efficient framework for rapid seismic event extraction. The method simplifies the B-COSFIRE architecture by replacing its configurable filter bank with a Difference-of-Gaussian (DoG) operator, which enhances ridge-like reflection features while suppressing background interference through a center–surround mechanism. Furthermore, a Spatial Consistency Constraint (SCC) module is introduced to enforce lateral continuity using directional morphological closing operations. This strategy reconstructs disrupted reflection segments and converts isolated detection responses into spatially coherent linear structures. Adaptive thresholding and skeletonization are then applied to obtain single-pixel-wide reflection contours suitable for geological interpretation and regional structural analysis. The proposed method was evaluated using both synthetic seismic models (Ricker wavelet convolution with Gaussian noise, σ = 0.15) and real post-stack seismic profiles characterized by low SNR conditions. Experimental results demonstrate that the proposed method achieves a Precision of 0.9527, Recall of 1.0000, and F1-score of 0.9758 on synthetic data, outperforming both the standard Canny detector (F1: 0.8972) and B-COSFIRE (F1: 0.7311). The Continuity Index reaches 261.00 pixels, substantially higher than Canny (223.67 pixels) and B-COSFIRE (66.86 pixels). Notably, B-COSFIRE exhibits a severely imbalanced detection profile (Precision: 0.5762, Recall: 1.000), indicating excessive false positives that undermine its practical utility. The proposed method additionally achieves the lowest runtime (0.024 s per profile), representing a 44× speedup over B-COSFIRE (1.039 s), while requiring no training data. Overall, the proposed framework provides a practical and efficient solution for automated seismic event extraction. With only a small number of geologically interpretable parameters and strong robustness across different datasets, the method is well-suited for large-scale seismic data processing and preliminary structural assessment in underexplored regions, enabling rapid first-pass evaluation of extensive survey areas before detailed interpretation and reservoir characterization. These characteristics make the method particularly suitable for computer-assisted interpretation workflows in industrial oil and gas exploration. Unlike prior approaches that treat seismic event extraction as a generic edge detection problem, the proposed framework explicitly encodes geological prior knowledge—specifically, the lateral continuity of stratigraphic interfaces—as a morphological constraint, bridging the gap between image processing methodology and geophysical interpretation requirements. Full article

Detecting minute defects, such as spurs on the surface of a Printed Circuit Board (PCB), is extremely challenging due to their small size (average size < 20 pixels), sparse features, and high dependence on circuit topology context. The original Mosaic data augmentation method faces significant challenges with semantic adaptability when dealing with such tasks. Its unrestricted random cropping mechanism easily disrupts the topological structure of minute defects attached to the circuits, leading to the loss of key features. Moreover, a splicing strategy without domain constraints struggles to simulate real texture interference in industrial settings, making it difficult for the model to adapt to the complex and variable industrial inspection environment. To address these issues, this paper proposes a Context-aware and Domain-consistent Mosaic (CD-Mosaic) augmentation algorithm. This algorithm abandons pure randomness and constructs an adaptive augmentation framework that synergizes feature fidelity, geometric generalization, and texture perturbation. Geometrically, an intelligent sampling and dynamic integrity verification mechanism, driven by “utilization-centrality”, is designed to establish a controlled sample quality distribution. This prioritizes the preservation of the topological semantics of dominant samples to guide feature convergence. Meanwhile, an appropriate number of edge-truncated samples are strategically retained as geometric hard examples to enhance the model’s robustness against local occlusion. For texture, a dual-granularity visual perturbation strategy is proposed. Using a homologous texture library, a hard mask is generated in the background area to simulate foreign object interference, and a local transparency soft mask is applied in the defect area to simulate low signal-to-noise ratio imaging. This strategy synthesizes visual hard examples while maintaining photometric consistency. Experiments on an industrial-grade PCB dataset containing 2331 images demonstrate that the YOLOv11m model equipped with CD-Mosaic achieves a significant performance improvement. Compared with the native Mosaic baseline, the core metrics mAP@0.5 and Recall reach 0.923 and 86.1%, respectively, with a net increase of 8.3% and 8.8%; mAP@0.5:0.95 and AP_small, which characterize high-precision localization and small target detection capabilities, are improved to 0.529 (+3.0%) and 0.534 (+3.3%), respectively; the comprehensive metric F1-score jumps to 0.903 (+6.2%). The experiments prove that this method effectively solves the problem of missed detections of industrial minute defects by balancing sample quality and detection difficulty. Moreover, the inference speed of 84.9 FPS fully meets the requirements of industrial real-time detection. Full article

Egg weight monitoring provides critical data for calculating the feed-to-egg ratio, and improving poultry farming efficiency. Installing a computer vision monitoring system in egg collection systems enables efficient and low-cost automated egg weight measurement. However, its accuracy is compromised by egg clustering during transportation and low-contrast edges, which limits the widespread adoption of such methods. To address this, we propose an egg measurement method based on a computer vision and multi-feature extraction and regression approach. The proposed pipeline integrates two artificial neural networks: Central differential-EfficientViT YOLO (CEV-YOLO) and Egg Weight Measurement Network (EWM-Net). CEV-YOLO is an enhanced version of YOLOv11, incorporating central differential convolution (CDC) and efficient Vision Transformer (EfficientViT), enabling accurate pixel-level egg segmentation in the presence of occlusions and low-contrast edges. EWM-Net is a custom-designed neural network that utilizes the segmented egg masks to perform advanced feature extraction and precise weight estimation. Experimental results show that CEV-YOLO outperforms other YOLO-based models in egg segmentation, with a precision of 98.9%, a recall of 97.5%, and an Average Precision (AP) at an Intersection over Union (IoU) threshold of 0.9 (AP90) of 89.8%. EWM-Net achieves a mean absolute error (MAE) of 0.88 g and an R² of 0.926 in egg weight measurement, outperforming six mainstream regression models. This study provides a practical and automated solution for precise egg weight measurement in practical production scenarios, which is expected to improve the accuracy and efficiency of feed-to-egg ratio measurement in laying hen farms. Full article

Droughts significantly impact agriculture, water resources, and ecosystems. Their timely detection is essential for implementing effective mitigation strategies. This study explores the use of multispectral Sentinel-2 remote sensing indices and machine learning techniques to detect drought conditions in three distinct regions of India, such as Jodhpur, Amravati, and Thanjavur, during the Rabi season (October–April). Twelve remote sensing indices were studied to assess different aspects of vegetation health, soil moisture, and water stress, and their possible joint use and influence as indicators of regional drought events. Reference data used to define drought conditions in each region were primarily sourced from official government drought declarations and regional and national news publications, which provide seasonal maps of drought conditions across the country. Based on this information, a district vs. year (3 × 10) ground truth is created, indicating the presence or absence of drought (Drought/No Drought) for each region across the ten-year period. Using this ground truth table, we extended the remote sensing dataset by adding a binary drought label for each observation: 1 for “Drought” and 0 for “No Drought”. The dataset is organized by year (2016–2025) in a two-dimensional format, with indices as columns and observations as rows. Each observation represents a single measurement of the remote sensing indices. This enriched dataset serves as the foundation for training and evaluating machine learning models aimed at classifying drought conditions based on spectral information. The resultant remote sensing dataset was used to predict drought events through various machine learning models, including Random Forest, XGBoost, Bagging Classifier, and Gradient Boosting. Among the models, XGBoost achieved the highest accuracy (84.80%), followed closely by the Bagging Classifier (83.98%) and Random Forest (82.98%). In terms of precision, Bagging Classifier and Random Forest performed comparably (82.31% and 81.45%, respectively), while XGBoost achieved a precision of 81.28%. We applied a seasonal majority voting strategy, assigning a final drought label for each region and Rabi season based on the majority of predicted monthly labels. Using this method, XGBoost and Bagging Classifier achieved $96.67\%$ accuracy, precision, and recall, while Random Forest and Gradient Boosting reached $90\%$ and $83.33\%$, respectively, across all metrics. Shapley Additive Explanation (SHAP) analysis revealed that Normalized Multi-band Drought Index (NMDI) and Day of Season (DOS) consistently emerged as the most influential features in determining model predictions. This finding is supported by the Borda Count and Weighted Sum analysis, which ranked NMDI, and DOS as the top feature across all models. Additionally, Red-edge Chlorophyll Index (RECI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), and Ratio Drought Index (RDI) were identified as important features contributing to model performance. These features help reveal the underlying spatiotemporal dynamics of drought indicators, offering interpretable insights into model decisions. To evaluate the impact of feature selection, we further conducted a feature ablation study. We trained each model using different combinations of top features: Top 1, Top 2, Top 3, Top 4, and Top 5. The performance of each model was assessed based on accuracy, precision, and recall. XGBoost demonstrated the best overall performance, especially when using the Top 5 features. Full article

To address the challenges in ship plate detection under complex maritime scenarios—such as small target size, extreme aspect ratios, dense arrangements, and multi-angle rotations—this paper proposes a multi-module collaborative detection algorithm, RT-DETR-HPA, based on an enhanced RT-DETR framework. The proposed model integrates three core components: an improved High-Frequency Enhanced Residual Block (HFERB) embedded in the backbone to strengthen multi-scale high-frequency feature fusion, with deformable convolution added to handle occlusion and deformation; a Pinwheel-shaped Convolution (PConv) module employing multi-directional convolution kernels to achieve rotation-adaptive local detail extraction and accurately capture plate edges and character features; and an Adaptive Sparse Self-Attention (ASSA) mechanism incorporated into the encoder to automatically focus on key regions while suppressing complex background interference, thereby enhancing feature discriminability. Comparative experiments conducted on a self-constructed dataset of 20,000 ship plate images show that, compared to the original RT-DETR, RT-DETR-HPA achieves a 3.36% improvement in mAP@50 (up to 97.12%), a 3.23% increase in recall (reaching 94.88%), and maintains real-time detection speed at 40.1 FPS. Compared with mainstream object detection models such as the YOLO series and Faster R-CNN, RT-DETR-HPA demonstrates significant advantages in high-precision localization, adaptability to complex scenarios, and real-time performance. It effectively reduces missed and false detections caused by low resolution, poor lighting, and dense occlusion, providing a robust and high-accuracy solution for intelligent ship supervision. Future work will focus on lightweight model design and dynamic resolution adaptation to enhance its applicability on mobile maritime surveillance platforms. Full article

The recognition of point patterns in spatial vector data has important applications in geographic mapping and formation recognition. However, the application of traditional methods to spatial vector data faces two difficulties. Firstly, these data are low signal-to-noise ratio data in which the point patterns are mixed with a large number of normal point clusters; thus, it is difficult to recognize point patterns from these unstructured data using traditional clustering or machine learning methods. Secondly, the lack of edge connectivity relationships in spatial vector data directly hinders the application of graph models. Few studies have systematically solved the above difficulties. In this article, we propose a geometric feature attention scheme to overcome the above challenges. We also present an implementation of the scheme based on the graph method, termed GeoFAN, to extract and classify point patterns simultaneously in spatial vector data. Firstly, the raw data are transformed into a graph structure consisting of adjacency and attribute matrices. Secondly, a geometric feature attention module is proposed to enhance the feature representation of point patterns. Finally, the recognition results of all points are output via GeoFAN. The macro precision, recall, and $F_1$ score of five simulated point pattern types with different attributes and point numbers are 92.8%, 90.3%, and 91.5%, respectively, and GeoFAN is trained with simulated data to recognize real location-based point patterns successfully. The proposed GeoFAN showed superior performance and generalization ability in point pattern recognition. Full article