Search Results (990)

Focusing on the problem of insufficient detection accuracy caused by blurred target boundaries, variable scales, and severe noise interference in side-scan sonar images, this paper proposes a high-precision detection network named ESL-YOLO, which integrates edge perception and adaptive quality assessment. Firstly, an Edge Fusion Module (EFM) is designed, which integrates the Sobel operator into depthwise separable convolution. Through a dual-branch structure, it realizes effective fusion of edge features and spatial features, significantly enhancing the ability to recognize targets with blurred boundaries. Secondly, a Self-Calibrated Dual Attention (SCDA) Module is constructed. By means of feature cross-calibration and multi-scale channel attention fusion mechanisms, it achieves adaptive fusion of shallow details and deep-rooted semantic content, improving the detection accuracy for small-sized targets and targets with elaborate shapes. Finally, a Location Quality Estimator (LQE) is introduced, which quantifies localization quality using the statistical characteristics of bounding box distribution, effectively reducing false detections and missed detections. Experiments on the SIMD dataset show that the mAP@0.5 of ESL-YOLO reaches 84.65%. The precision and recall rate reach 87.67% and 75.63%, respectively. Generalization experiments on additional sonar datasets further validate the effectiveness of the proposed method across different data distributions and target types, providing an effective technical solution for side-scan sonar image target detection. Full article

Detecting manipulated document images is essential for verifying the authenticity of official records and preventing document forgery. However, forgery artifacts are often subtle and localized in fine-grained regions, such as text boundaries or character outlines, where visual symmetry and structural regularity are typically expected. These manipulations can disrupt the inherent symmetry of document layouts, making the detection of such inconsistencies crucial for forgery identification. Conventional CNN-based models face limitations in capturing such edge-level asymmetric features, as edge-related information tends to weaken through repeated convolution and pooling operations. To address this issue, this study proposes an edge-focused method composed of two components: the Edge Attention (EA) layer and the Edge Concatenation (EC) layer. The EA layer dynamically identifies channels that are highly responsive to edge features in the input feature map and applies learnable weights to emphasize them, enhancing the representation of boundary-related information, thereby emphasizing structurally significant boundaries. Subsequently, the EC layer extracts edge maps from the input image using the Sobel filter and concatenates them with the original feature maps along the channel dimension, allowing the model to explicitly incorporate edge information. To evaluate the effectiveness and compatibility of the proposed method, it was initially applied to a simple CNN architecture to isolate its impact. Subsequently, it was integrated into various widely used models, including DenseNet121, ResNet50, Vision Transformer (ViT), and a CAE-SVM-based document forgery detection model. Experiments were conducted on the DocTamper, Receipt, and MIDV-2020 datasets to assess classification accuracy and F1-score using both original and forged text images. Across all model architectures and datasets, the proposed EA–EC method consistently improved model performance, particularly by increasing sensitivity to asymmetric manipulations around text boundaries. These results demonstrate that the proposed edge-focused approach is not only effective but also highly adaptable, serving as a lightweight and modular extension that can be easily incorporated into existing deep learning-based document forgery detection frameworks. By reinforcing attention to structural inconsistencies often missed by standard convolutional networks, the proposed method provides a practical solution for enhancing the robustness and generalizability of forgery detection systems. Full article

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article

This paper applies a multi-level social network analysis to examine Aragón’s innovation ecosystem, focusing on a decade of competitive public projects (2014–2023) aligned with the region’s Smart Specialisation Strategy (S3) 2021–2027. By mapping and weighting the participation of regional entities across regional, national, and European calls, the study uncovers how all types of local actors organise themselves around key specialisation areas. Moreover, a comparative benchmark is introduced by analysing more than 33,000 Horizon 2020 and Horizon Europe initiatives without Aragonese partners, revealing how to fill structural gaps and enrich the regional ecosystem through international collaboration. Results show strong funding concentration in four fields—Energy, Health, Agri-Food, and Advanced Technologies—while other historically strategic areas like Hydrogen and Water remain underrepresented. Although leading institutions (UNIZAR, CIRCE, ITA, AITIIP) play central roles in connecting academia and industry, direct collaboration among them is limited, pointing to missed synergies. Expanding previous SNA-based assessments, this study introduces a diagnostic tool to guide policy, proposing targeted actions such as challenge-driven calls, dedicated support programs, and cross-border consortia with top EU partners. Applied to two contrasting specialisation areas, the method offers sector-specific recommendations, helping policymakers align Aragón’s innovation capabilities with EU priorities and strengthen its position in both established and emerging domains. Full article

Smoke appears earlier than flames, so image-based fire monitoring techniques mainly focus on the detection of smoke, which is regarded as one of the effective strategies for preventing the spread of initial fires that eventually evolve into serious fires. Smoke monitoring in mine fires faces serious challenges: the underground environment is complex, with smoke and backgrounds being highly integrated and visual features being blurred, which makes it difficult for existing image-based monitoring techniques to meet the actual needs in terms of accuracy and robustness. The conventional ground-based methods are directly used in the underground with a high rate of missed detection and false detection. Aiming at the core problems of mixed target and background information and high boundary uncertainty in smoke images, this paper, inspired by the principle of information entropy, proposes a method for recognizing smoke from mine fires by integrating entropy-enhanced image processing and improved YOLOv8. Firstly, according to the entropy change characteristics of spatio-temporal information brought by smoke diffusion movement, based on spatio-temporal entropy separation, an equidistant frame image differential fusion method is proposed, which effectively suppresses the low entropy background noise, enhances the detail clarity of the high entropy smoke region, and significantly improves the image signal-to-noise ratio. Further, in order to cope with the variable scale and complex texture (high information entropy) of the smoke target, an improvement mechanism based on entropy-constrained feature focusing is introduced on the basis of the YOLOv8m model, so as to more effectively capture and distinguish the rich detailed features and uncertain information of the smoke region, realizing the balanced and accurate detection of large and small smoke targets. The experiments show that the comprehensive performance of the proposed method is significantly better than the baseline model and similar algorithms, and it can meet the demand of real-time detection. Compared with YOLOv9m, YOLOv10n, and YOLOv11n, although there is a decrease in inference speed, the accuracy, recall, average detection accuracy mAP (50), and mAP (50–95) performance metrics are all substantially improved. The precision and robustness of smoke recognition in complex mine scenarios are effectively improved. Full article

The growing mismatch between ecosystem service (ES) supply and demand underscores the importance of thoroughly understanding their spatiotemporal patterns and key drivers to promote ecological civilization and sustainable development at the regional level in China. This study investigates six key ES indicators across mainland China—habitat quality (HQ), carbon sequestration (CS), water yield (WY), sediment delivery ratio (SDR), food production (FP), and nutrient delivery ratio (NDR)—by integrating a suite of analytical approaches. These include a spatiotemporal analysis of trade-offs and synergies in supply, demand, and their ratios; self-organizing maps (SOM) for bundle identification; and interpretable machine learning models. While prior research studies have typically examined ES at a single spatial scale, focusing on supply-side bundles or associated drivers, they have often overlooked demand dynamics and cross-scale interactions. In contrast, this study integrates SOM and SHAP-based machine learning into a dual-scale framework (grid and city levels), enabling more precise identification of scale-dependent drivers and a deeper understanding of the complex interrelationships between ES supply, demand, and their spatial mismatches. The results reveal pronounced spatiotemporal heterogeneity in ES supply and demand at both grid and city scales. Overall, the supply services display a spatial pattern of higher values in the east and south, and lower values in the west and north. High-value areas for multiple demand services are concentrated in the densely populated eastern regions. The grid scale better captures spatial clustering, enhancing the detection of trade-offs and synergies. For instance, the correlation between HQ and NDR supply increased from 0.62 (grid scale) to 0.92 (city scale), while the correlation between HQ and SDR demand decreased from −0.03 to −0.58, indicating that upscaling may highlight broader synergistic or conflicting trends missed at finer resolutions. In the spatiotemporal interaction network of supply–demand ratios, CS, WY, FP, and NDR persistently show low values (below −0.5) in western and northern regions, indicating ongoing mismatches and uneven development. Driver analysis demonstrates scale-dependent effects: at the grid scale, HQ and FP are predominantly influenced by socioeconomic factors, SDR and WY by ecological variables, and CS and NDR by climatic conditions. At the city level, socioeconomic drivers dominate most services. Based on these findings, nine distinct supply–demand bundles were identified at both scales. The largest bundle at the grid scale (B3) occupies 29.1% of the study area, while the largest city-scale bundle (B8) covers 26.5%. This study deepens the understanding of trade-offs, synergies, and driving mechanisms of ecosystem services across multiple spatial scales; reveals scale-sensitive patterns of spatial mismatch; and provides scientific support for tiered ecological compensation, integrated regional planning, and sustainable development strategies. Full article

Semi-supervised object detection (SSOD) in remote sensing is challenged by the accumulation of pseudo-label errors in complex scenes with dense objects and high intra-class variability. While teacher–student frameworks enable learning from unlabeled data, erroneous pseudo-labels such as false positives and missed detections can be reinforced over time, which degrades model performance. To address this issue, we propose the Error-Mitigation Teacher (EMT), a unified framework designed to suppress error propagation during SSOD training. EMT consists of three lightweight modules. First, the Adaptive Pseudo-Label Filtering (APLF) module removes noisy pseudo boxes via a second-stage RCNN and adjusts class-specific thresholds through dynamic confidence filtering. Second, the Confidence-Based Loss Reweighting (CBLR) module reweights training loss by evaluating the teacher model’s ability to reconstruct its own pseudo-labels, using the resulting loss as an indicator of label reliability. Third, the Enhanced Supervised Learning (ESL) module improves class-level balance by adjusting supervised loss weights according to pseudo-label statistics. EMT demonstrates consistent performance gains over representative state-of-the-art SSOD methods on DOTA, DIOR, and SSDD datasets. Notably, EMT achieves a 2.9% absolute mAP₅₀ improvement on DIOR using only 10% of labeled data, without incurring additional inference cost. These results highlight EMT’s effectiveness in improving SSOD for remote sensing. Full article

Accurate and real-time detection of rice shelling rate (SR) and brown rice breakage rate (BR) is crucial for intelligent hulling sorting but remains challenging because of small grain size, dense adhesion, and uneven illumination causing missed detections and blurred boundaries in traditional YOLOv8n. This paper proposes a high-precision, lightweight solution based on an enhanced YOLOv8n with improvements in network architecture, feature fusion, and attention mechanism. The backbone’s C2f module is replaced with C2f-Faster-CGLU, integrating partial convolution (PConv) local convolution and convolutional gated linear unit (CGLU) gating to reduce computational redundancy via sparse interaction and enhance small-target feature extraction. A bidirectional feature pyramid network (BiFPN) weights multiscale feature fusion to improve edge positioning accuracy of dense grains. Attention mechanism for fine-grained classification (AFGC) is embedded to focus on texture and damage details, enhancing adaptability to light fluctuations. The Detect_Rice lightweight head compresses parameters via group normalization and dynamic convolution sharing, optimizing small-target response. The improved model achieved 96.8% precision and 96.2% mAP. Combined with a quantity–mass model, SR/BR detection errors reduced to 1.11% and 1.24%, meeting national standard (GB/T 29898-2013) requirements, providing an effective real-time solution for intelligent hulling sorting. Full article

To address the challenges of image inpainting in scenarios with extensive or irregular missing regions—particularly detail oversmoothing, structural ambiguity, and textural incoherence—this paper proposes an Image Structure-Guided (ISG) framework that hierarchically integrates structural priors with semantic-aware texture synthesis. The proposed methodology advances a two-stage restoration paradigm: (1) Structural Prior Extraction, where adaptive edge detection algorithms identify residual contours in corrupted regions, and a transformer-enhanced network reconstructs globally consistent structural maps through contextual feature propagation; (2) Structure-Constrained Texture Synthesis, wherein a multi-scale generator with hybrid dilated convolutions and channel attention mechanisms iteratively refines high-fidelity textures under explicit structural guidance. The framework introduces three innovations: (1) a hierarchical feature fusion architecture that synergizes multi-scale receptive fields with spatial-channel attention to preserve long-range dependencies and local details simultaneously; (2) spectral-normalized Markovian discriminator with gradient-penalty regularization, enabling adversarial training stability while enforcing patch-level structural consistency; and (3) dual-branch loss formulation combining perceptual similarity metrics with edge-aware constraints to align synthesized content with both semantic coherence and geometric fidelity. Our experiments on the two benchmark datasets (Places2 and CelebA) have demonstrated that our framework achieves more unified textures and structures, bringing the restored images closer to their original semantic content. Full article

Accurate crop row detection is crucial for determining weed pressure (weeds item per square meter). However, this task is complicated by the similarity between crops and weeds, the presence of missing plants within rows, and the varying growth stages of both. Our hypothesis was that in drone imagery captured at altitudes of 20–30 m—where individual plant details are not discernible—weed presence among crops can be statistically detected, allowing for the generation of a weed distribution map. This study proposes a computer vision detection method using images captured by unmanned aerial vehicles (UAVs) consisting of six main phases. The method was tested on 208 images. The algorithm performs well under normal conditions; however, when the weed density is too high, it fails to detect the row direction properly and begins processing misleading data. To investigate these cases, 120 artificial datasets were created with varying parameters, and the scenarios were analyzed. It was found that a rate variable—in-row concentration ratio (IRCR)—can be used to determine whether the result is valid (usable) or invalid (to be discarded). The F1 score is a metric combining precision and recall using a harmonic mean, where “1” indicates that precision and recall are equally weighted, i.e., β = 1 in the general Fβ formula. In the case of moderate weed infestation, where 678 crop plants and 600 weeds were present, the algorithm achieved an F1 score of 86.32% in plant classification, even with a 4% row disturbance level. Furthermore, IRCR also indicates the level of weed pressure in the area. The correlation between the ground truth weed-to-crop ratio and the weed/crop classification rate produced by the algorithm is 98–99%. As a result, the algorithm is capable of filtering out heavily infested areas that require full weed control and capable of generating weed density maps on other cases to support precision weed management. Full article

Traditional bathymetry measures require a large number of human hours, and many bathymetry records are obsolete or missing. Automated measures of bathymetry would reduce costs and increase accessibility for research and applications. In this paper, we optimized a recent machine learning model, named CatBoostOpt, to estimate bathymetry based on high-resolution WorldView-2 (WV-2) multi-spectral optical satellite images. CatBoostOpt was demonstrated across the Florida Big Bend coastline, where the model learned correlations between in situ sound Navigation and Ranging (Sonar) bathymetry measurements and the corresponding multi-spectral reflectance values in WV-2 images to map bathymetry. We evaluated three different feature transformations as inputs for bathymetry estimation, including raw reflectance, log-linear, and log-ratio transforms of the raw reflectance value in WV-2 images. In addition, we investigated the contribution of each spectral band and found that utilizing all eight spectral bands in WV-2 images offers the best solution for handling complex water quality conditions. We compared CatBoostOpt with linear regression (LR), support vector machine (SVM), random forest (RF), AdaBoost, gradient boosting, and deep convolutional neural network (DCNN). CatBoostOpt with log-ratio transformed reflectance achieved the best performance with an average root mean square error (RMSE) of 0.34 and coefficient of determination (${\mathrm{R}}^2$) of 0.87. Full article

Unmanned aerial vehicles are increasingly used in civil Search and Rescue operations due to their rapid deployment and wide-area coverage capabilities. However, detecting missing persons from aerial imagery remains challenging due to small object sizes, cluttered backgrounds, and limited onboard computational resources, especially when managed by civil agencies. In this work, we present a comprehensive methodology for optimizing YOLO-based object detection models for real-time Search and Rescue scenarios. A two-stage transfer learning strategy was employed using VisDrone for general aerial object detection and Heridal for Search and Rescue-specific fine-tuning. We explored various architectural modifications, including enhanced feature fusion (FPN, BiFPN, PB-FPN), additional detection heads (P2), and modules such as CBAM, Transformers, and deconvolution, analyzing their impact on performance and computational efficiency. The best-performing configuration (YOLOv5s-PBfpn-Deconv) achieved a mAP@50 of 0.802 on the Heridal dataset while maintaining real-time inference on embedded hardware (Jetson Nano). Further tests at different flight altitudes and explainability analyses using EigenCAM confirmed the robustness and interpretability of the model in real-world conditions. The proposed solution offers a viable framework for deploying lightweight, interpretable AI systems for UAV-based Search and Rescue operations managed by civil protection authorities. Limitations and future directions include the integration of multimodal sensors and adaptation to broader environmental conditions. Full article

Trajectory prediction under multimodal information is critical for autonomous driving, necessitating the integration of dynamic vehicle states and static high-definition (HD) maps to model complex agent–scene interactions effectively. However, existing methods often employ static scene encodings and unstructured latent spaces, limiting their ability to capture evolving spatial contexts and produce diverse yet contextually coherent predictions. To tackle these challenges, we propose MS-SLV, a novel generative framework that introduces (1) a time-aware scene encoder that aligns HD map features with vehicle motion to capture evolving scene semantics and (2) a structured latent model that explicitly disentangles agent-specific intent and scene-level constraints. Additionally, we introduce an auxiliary lane prediction task to provide targeted supervision for scene understanding and improve latent variable learning. Our approach jointly predicts future trajectories and lane sequences, enabling more interpretable and scene-consistent forecasts. Extensive evaluations on the nuScenes dataset demonstrate the effectiveness of MS-SLV, achieving a 12.37% reduction in average displacement error and a 7.67% reduction in final displacement error over state-of-the-art methods. Moreover, MS-SLV significantly improves multi-modal prediction, reducing the top-5 Miss Rate (${\mathrm{MR}}_5$) and top-10 Miss Rate (${\mathrm{MR}}_{10}$) by 26% and 33%, respectively, and lowering the Off-Road Rate (ORR) by 3%, as compared with the strongest baseline in our evaluation. Full article

Biophilic design has emerged as a multidimensional response to growing concerns about health, well-being, and ecological balance in the built environment. Despite its rising prominence, research on the topic remains fragmented across building typologies, user groups, and geographic contexts. This study presents a comprehensive review of the biophilic design literature, employing a hybrid methodology combining structured content analysis and bibliometric mapping. All peer-reviewed studies indexed in the Web of Science and Scopus were manually screened for architectural relevance and systematically coded. A total of 435 studies were analysed to identify key trends, thematic patterns, and research gaps in the biophilic design discipline. This review categorises the literature by methodological strategies, building typologies, spatial scales, population groups, and specific biophilic design parameters. It also examines geographic and cultural dimensions, including climate responsiveness, heritage buildings, policy frameworks, theory development, pedagogy, and COVID-19-related research. The findings show a strong emphasis on institutional contexts, particularly workplaces, schools, and healthcare, and a reliance on perception-based methods such as surveys and experiments. In contrast, advanced tools like artificial intelligence, simulation, and VR are notably underused. Few studies engage with neuroarchitecture or neuroscience-informed approaches, despite growing recognition of how spatial design can influence cognitive and emotional responses. Experimental and biometric methods remain scarce among the few relevant contributions, revealing a missed opportunity to connect biophilic strategies with empirical evidence. Regarding biophilic parameters, greenery, daylight, and sensory experience are the most studied parameters, while psychological parameters remain underexplored. Cultural and climate-specific considerations appear in relatively few studies, and many fail to define a user group or building typology. This review highlights the need for more inclusive, context-responsive, and methodologically diverse research. By bridging macro-scale bibliometric patterns with fine-grained thematic insights, this study provides a replicable review model and valuable reference for advancing biophilic design as an evidence-based, adaptable, and human-centred approach to sustainable architecture. Full article

Magnetic tiles are an important component of permanent magnet motors, and the quality of magnetic tiles directly affects the performance and service life of a motor. It is necessary to perform defect detection on magnetic tiles in industrial production and remove those with defects. The YOLOv8-AHF algorithm is proposed to improve the ability of network feature information extraction and solve the problem of missed detection or poor detection results in surface defect detection due to the small volume of permanent magnet motor tiles, which reduces the deviation between the predicted box and the true box simultaneously. Firstly, a hybrid module of a combination of atrous convolution and depthwise separable convolution (ADConv) is introduced in the backbone of the model to capture global and local features in magnet tile detection images. In the neck section, a hybrid attention module (HAM) is introduced to focus on the regions of interest in the magnetic tile surface defect images, which improves the ability of information transmission and fusion. The Focal-Enhanced Intersection over Union loss function (Focal-EIoU) is optimized to effectively achieve localization. We conducted comparative experiments, ablation experiments, and corresponding generalization experiments on the magnetic tile surface defect dataset. The experimental results show that the evaluation metrics of YOLOv8-AHF surpass mainstream single-stage object detection algorithms. Compared to the You Only Look Once version 8 (YOLOv8) algorithm, the performance of the YOLOv8-AHF algorithm was improved by 5.9%, 4.1%, 5%, 5%, and 5.8% in terms of mAP@0.5, mAP@0.5:0.95, F1-Score, precision, and recall, respectively. This algorithm achieved significant performance improvement in the task of detecting surface defects on magnetic tiles. Full article