Search Results (361)

Accurate broiler weight estimation in commercial farms is hindered by noisy scale data and multi-broiler occupancy. To address this challenge, we propose a KDE-based framework enhanced with systematic preprocessing, including coefficient of variation (CV), relative change (ROC), and absolute change (AC). In this study, kernel density estimation (KDE) is employed not as a predictive model, but as a distributional tool to robustly extract representative flock weight from noisy, high-frequency scale measurements under commercial farm conditions. In the absence of physical ground-truth, our evaluation focused on the framework’s ability to consistently detect the single, representative peak in the KDE distribution. Weekly thresholds were empirically optimized for the preprocessing filters. Results show that the combined ROC + AC method consistently produced unimodal peak distributions and improved the Peak Detection Rate (PDR) from 91.2% (raw data) to 97.9%. Single-Entity Filtering, assisted by cameras, further mitigated density distortions caused by prolonged occupancy, while CV-only and ROC-only filtering yielded less stable representative values. These findings demonstrate that rigorous preprocessing is essential for reliable KDE-based weight estimation under real-world farm conditions. The proposed framework not only improves data quality and stabilizes distributions but also provides a practical foundation for real-time monitoring and AI-driven precision livestock farming models. Full article

Unmanned Aerial Vehicle (UAV) imagery has emerged as a critical data source in remote sensing, playing an important role in vehicle detection for intelligent traffic management and urban monitoring. Deep learning–based detectors rely heavily on large-scale, high-quality annotated datasets, however, collecting and labeling real-world UAV data are both costly and time-consuming. Owing to its controllability and scalability, synthetic data has become an effective supplement to address the scarcity of real data. Nevertheless, the significant domain gap between synthetic data and real data often leads to substantial performance degradation during real-world deployment. To address this challenge, this paper proposes a high-fidelity synthetic data generation framework designed to reduce the Sim2Real gap. First, UAV oblique photogrammetry is utilized to reconstruct real-world 3D model, ensuring geometric and textural authenticity; second, diversified rendering strategies that simulate real-world illumination and weather variations are adopted to cover a wide range of environmental conditions; finally, an automated ground-truth generation algorithm based on semantic masks is developed to achieve pixel-level precision and cost-efficient annotation. Based on this framework, we construct a synthetic dataset named UAV-SynthScene. Experimental results show that multiple mainstream detectors trained on UAV-SynthScene achieve competitive performance when evaluated on real data, while significantly enhancing robustness in long-tail distributions and improving generalization on real datasets. Full article

Mitral valve orifice area is a key functional metric that depends on complex geometric features, motivating a systematic assessment of the relative influence of these parameters. In this study, the mitral valve geometry is parameterized using twelve geometric variables, and a global sensitivity analysis based on Sobol indices is performed to quantify their relative importance. Because global sensitivity analysis requires many simulations, a Gaussian Process regressor is developed to efficiently predict the orifice area from the geometric inputs. Structural simulations of the mitral valve are carried out in Abaqus, focusing exclusively on the valve mechanics. The predicted distribution of orifice areas obtained from the Gaussian Process shows strong agreement with the ground-truth simulation results, and similar agreement is observed when only the most influential geometric parameters are varied. The analysis identifies a subset of geometric parameters that dominantly govern the mitral valve orifice area and can be reliably extracted from medical imaging modalities such as echocardiography. These findings establish a direct link between echocardiographic measurements and physics-based simulations and provide a framework for patient-specific assessment of mitral valve mechanics, with potential applications in guiding interventional strategies such as MitraClip placement. Full article

Bounding box regression (BBR) loss plays a critical role in object detection within computer vision. Existing BBR loss functions are typically based on the Intersection over Union (IoU) between predicted and ground truth boxes. However, these methods neither account for the effect of predicted box scale on regression nor effectively address the drift problem inherent in BBR. To overcome these limitations, this paper introduces a novel BBR loss function, termed Gaussian Adaptive Ochiai BBR loss (GAOC), which combines the Ochiai Coefficient (OC) with a Gaussian Adaptive (GA) distribution. The OC component normalizes by the square root of the product of bounding box dimensions, ensuring scale invariance. Meanwhile, the GA distribution models the distance between the top-left and bottom-right corners (TL/BR) coordinates of predicted and ground truth boxes, enabling a similarity measure that reduces sensitivity to positional deviations. This design enhances detection robustness and accuracy. GAOC was integrated into YOLOv5 and RT-DETR and evaluated on the PASCAL VOC and MS COCO 2017 benchmarks. Experimental results demonstrate that GAOC consistently outperforms existing BBR loss functions, offering a more effective solution. Full article

Road marking lines can be extracted from aerial images using semantic segmentation (SS) models; however, in this work, a conditional generative adversarial network, RoadMark-cGAN, is proposed for direct extraction of these representations with image-to-image translation techniques. The generator features residual and attention blocks added in a functional bottleneck, while the discriminator features a modified PatchGAN, with an optimized encoder and an attention block added. The proposed model is improved in three versions (v2 to v4), in which dynamic dropout techniques and a novel “Morphological Boundary-Sensitive Class-Balanced” (MBSCB) loss are progressively added to better handle the high class imbalance present in the data. All models were trained on a novel “RoadMarking-binary” dataset (29,405 RGB orthoimage tiles of 256 × 256 pixels and their corresponding ground truth masks) to learn the distribution of road marking lines found on pavement. The metrical evaluation on the test set containing 2045 unseen images showed that the best proposed model achieved average improvements of 45.2% and 1.7% in the Intersection-over-Union (IoU) score for the positive, underrepresented class when compared to the best Pix2Pix and SS models, respectively, trained for the same task. Finally, a qualitative, visual comparison was conducted to assess the quality of the road marking predictions of the best models and their mapping performance. Full article

We address the problem of 6D object pose estimation in aerosol environments, where RGB and depth sensors experience correlated degradation due to scattering and absorption. Handling such spatially varying degradation typically requires depth restoration, but obtaining ground-truth complete depth in aerosol conditions is prohibitively expensive. To overcome this limitation without relying on costly depth completion, we propose RA6D, a framework that integrates attention-guided reliability modeling with feature distillation. The attention map generated during RGB dehazing reflects aerosol distribution and provides a compact indicator of depth reliability. By embedding this attention as an additional feature in an Attention-Guided Point cloud (AGP), the network can adaptively respond to spatially varying degradation. In addition, to address the scarcity of aerosol-domain data, we employ clean-to-aerosol feature distillation, transferring robust representations learned under clean conditions. Experiments on aerosol benchmarks show that RA6D achieves higher accuracy and significantly faster inference than restoration-based pipelines, offering a practical solution for real-time robotic perception under severe visual degradation. Full article

With the increasing frequency of traffic safety issues and the rapid development of autonomous driving technology, traffic sign detection is highly susceptible to adverse weather conditions such as changes in light intensity, fog, rain, snow, and partial occlusion, which places higher demands on the accurate recognition of traffic signs. This paper proposes an improved DAYOLO model based on YOLOv8n, aiming to balance detection accuracy and model complexity. First, the Bottleneck in the C2f module of the YOLOv8n backbone network is replaced with Bottleneck DAttention. Introducing DAttention allows for more effective feature extraction, thereby improving model performance. Second, an ultra-lightweight and efficient upsampler, Dysample, is introduced into the neck network to further improve performance and reduce computational overhead. Finally, a Task-Aligned Dynamic Detection Head (TADDH) is introduced. TADDH enhances task interaction through a dynamic mechanism and utilizes shared convolutional modules to reduce parameters and improve efficiency. Simultaneously, an additional Layer2 detection head is added to the model to strengthen the extraction and fusion of features at different scales, thereby improving the detection accuracy of small traffic signs. Furthermore, replacing SlideLoss with NWDLoss can better handle prediction results with more complex distributions and more accurately measure the distance between predicted and ground truth boxes in the feature space during object detection. Experimental results show that DAYOLO achieves 97.2% mAP on the SDCCVP dataset, which is 5.3 higher than the baseline model YOLOv8n; the frame rate reaches 120, which is 37.8% higher than YOLOv8; and the number of parameters is reduced by 6.2%, outperforming models such as YOLOv3, YOLOv5, YOLOv6, and YOLOv7. In addition, DAYOLO achieves 80.8 mAP on the TT100K dataset, which is 9.2% higher than the baseline model YOLOv8n. The proposed method achieves a balance between model size and detection accuracy, meets the needs of traffic sign detection, and provides new ideas and methods for future research in the field of traffic sign detection. Full article

This study introduces the Hybrid Integrated Prediction-Error Reconstruction-based Anomaly Detection (HIPER-CHAD) model, which addresses the challenge of reliably detecting subtle anomalies in noisy multivariate indoor environmental time-series data. The main objective is to separate temporal modeling of normal behavior from probabilistic modeling of prediction uncertainty, ensuring that the anomaly score becomes robust to stochastic fluctuations while remaining sensitive to truly abnormal events. The HIPER-CHAD architecture first employs a Long Short-Term Memory (LSTM) network to forecast the next time step’s sensor readings, subsequently forming a residual error vector that captures deviations from the expected temporal pattern. A Variational Autoencoder (VAE) is then trained on these residual vectors rather than on the raw sensor data to learn the distribution of normal prediction errors and quantify their probabilistic unicity. The final anomaly score integrates the VAE’s reconstruction error with its Kullback–Leibler (KL) divergence, yielding a statistically grounded measure that jointly reflects the magnitude and distributional abnormality of the residual. The proposed model is evaluated on a real-world multivariate indoor environmental dataset and compared against eight traditional machine learning and deep learning baselines using a synthetic ground truth generated by a 99th percentile-based criterion. HIPER-CHAD achieves an F1-score of 0.8571, outperforming the next best model, the LSTM Autoencoder (F1 = 0.8095), while maintaining perfect recall. Furthermore, a time-step sensitivity analysis demonstrates that a 20-step window yields an optimal F1-score of 0.884, indicating that the proposed residual-based hybrid design provides a reliable and accurate framework for anomaly detection in complex multivariate time-series data. Full article

Volume electron microscopy (Volume-EM) has transformed structural cell biology by enabling nanometre-resolution imaging across cellular and tissue scales. Serial-section TEM, Serial Block-Face Scanning Electron Microscopy (SBF-SEM), Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) and multi-beam SEM now routinely generate terabyte-scale volumes that capture organelles, synapses and neural circuits in three dimensions, while cryogenic Volume-EM extends this landscape by preserving vitrified, fully hydrated specimens in a near-native state. Together, these room-temperature and cryogenic modalities define a continuum of approaches that trade off volume, resolution, throughput and structural fidelity, and increasingly interface with correlative light microscopy and cryo-electron tomography. In parallel, advances in computation have turned Volume-EM into a data-intensive discipline. Multistage preprocessing pipelines for alignment, denoising, stitching and intensity normalisation feed into automated segmentation frameworks that combine convolutional neural networks, affinity-based supervoxel agglomeration, flood-filling networks and, more recently, diffusion-based generative restoration. Weakly supervised and self-supervised learning, multi-task objectives and human-AI co-training mitigate the scarcity of dense ground truth, while distributed storage and streaming inference architectures support segmentation and proofreading at the terascale and beyond. Open resources such as COSEM, MICRONS, OpenOrganelle and EMPIAR provide benchmark datasets, interoperable file formats and reference workflows that anchor method development and cross-laboratory comparison. In this review, we first outline the physical principles and imaging modes of conventional and cryogenic Volume-EM, then describe current best practices in data acquisition and preprocessing, and finally survey the emerging ecosystem of AI-driven segmentation and analysis. We highlight how cryo-Volume-EM expands the field towards native-state structural biology, and how multimodal integration with light microscopy, cryo-electron tomography (cryo-ET) and spatial omics is pushing Volume-EM from descriptive imaging towards predictive, mechanistic, cross-scale models of cell physiology, disease ultrastructure and neural circuit function. Full article

Quantifying riverscape topography is challenging because riverscapes comprise of both wet and dry surfaces. Advances have been made in demonstrating the capability of mounting topo-bathymetric LiDAR (Light Detection and Ranging) sensors on crewed, occupied aircraft to quantify riverscape topography. However, only recently has miniaturisation of electronic components enabled topo-bathymetric LiDAR to be mounted on consumer-grade Unoccupied Aerial Vehicles (UAVs). We evaluate the capability of a demonstration YellowScan Navigator topo-bathymetric, full waveform LiDAR sensor, mounted on a DJI Matrice 600 UAV, to survey a 1 km long reach of the braided River Feshie, Scotland. Ground-truth data, with centimetre accuracy, were collected across wet areas using an echo-sounder, and in wet and dry areas using RTK-GNSS (Real-Time Kinematic Global Navigation Satellite System). The processed point cloud had a density of 62 points/m². Ground-truth mean errors (and standard deviation) across dry gravel bars were 0.06 ± 0.04 m, along shallow channel beds were −0.03 ± 0.12 m and for deep channels were −0.08 m ± 0.23 m. Geomorphic units with a concave three-dimensional shape (pools, troughs), associated with deeper water, had larger negative errors and wider ranges of residuals than planar or convex units. The case study demonstrates the potential of using UAV topo-bathymetric LiDAR to enhance survey efficiency but a need to evaluate spatial error distribution. Full article

Sabina vulgaris is a keystone shrub species endemic to arid northwestern China, renowned for its exceptional drought tolerance, sand fixation capabilities, and critical role in desert ecosystem stability. This study investigates the impact of coal mining activities on the spatiotemporal dynamics of S. vulgaris shrublands in the ecologically fragile Mu Us Sandy Land, focusing on the Longde Coal Mine adjacent to the Shenmu S. vulgaris Nature Reserve. Utilizing seven periods (2013–2025) of 2 m resolution Gaofen-1 (GF-1) satellite imagery spanning 12 years of mining operations, we implemented a deep learning approach combining UAV-derived hyperspectral ground truth data and the SegU-Net semantic segmentation model to map shrub distribution via GF-1 data with high precision. Classification accuracy was rigorously validated through confusion matrix analysis (incorporating the Kappa coefficient and overall accuracy metrics). Results reveal contrasting trends: while the S. vulgaris Protection Area exhibited substantial expansion (e.g., Southern Section coverage grew from 2.6 km² in 2013 to 7.88 km² in 2025), mining panels experienced significant degradation. Within Panel 202, coverage declined by 15.4% (58.4 km² to 49.5 km²), and Panel 203 showed a 18.5% decrease (3.16 km² to 2.57 km²) over the study period. These losses correlate spatially and temporally with mining-induced groundwater depletion and land subsidence, disrupting the shrub’s shallow-root water access strategy. The study demonstrates that coal mining drives fragmentation and coverage reduction in S. vulgaris communities through mechanisms including (1) direct vegetation destruction, (2) aquifer disruption impairing drought adaptation, and (3) habitat fragmentation. These findings underscore the necessity for targeted ecological restoration strategies integrating groundwater management and progressive reclamation in mining-affected arid regions. Full article

Understanding and monitoring benthic habitat distribution is essential for implementing ecosystem-based fisheries management (EBFM). Satellite remote sensing offers a rapid and cost-effective approach to marine habitat assessments; however, its application requires context-specific adjustment to account for environmental variability and differing study aims. As such, predictor variables must be tailored to the specific site and target habitat. This study uses Sentinel-2 Level 2A surface reflectance satellite imagery and stability selection via Random Forest Recursive Feature Elimination to assess the importance of remote sensing indices for mapping moderately deep (<20 m) seagrass habitats in relation to the Marine Stewardship Council-certified Western Australia Enhanced Greenlip Abalone Fishery (WAEGAF). Of the seven indices tested, the Normalised Difference Aquatic Vegetation Index (NDAVI) and Depth Invariant Index for the blue and green bands were selected in the optimal model on every run. The kernelised NDAVI and Water-Adjusted Vegetation Index also scored highly (both 0.92) and were included in the final classification and regression models. Both models performed well and predicted a similar cover and distribution of seagrass within the fishery compared to the surrounding area, providing a baseline and supporting EBFM of the WAEGAF within the surrounding marine protected area. Importantly, the use of indices from freely accessible ready-to-use satellite products via Google Earth Engine workflows and expedited ground truth image annotation using highly accurate (0.96) automatic image annotation provides a rapidly repeatable method for delivering ecosystem information for this fishery. Full article

Modern aircraft usually employ control allocation to distribute virtual control commands among redundant effectors. Infeasible virtual command can occur frequently due to aggressive maneuvers and limited control authority. This paper proposes a lightweight command scaling law for incremental flight control allocation. The method scales the raw incremental virtual command by a direction-preserving gain $K\in$ [0,1]. It is updated via gradient descent on a Lyapunov function that balances allocation error against deviation from unity gain. The proposed adaptive update law ensures the convergence of K to a value that corresponds to the attainable portion of infeasible commands, independent of the specific allocator used. At the same time, feasible virtual commands will be preserved. Its performance was evaluated through open-loop ray sweeps of the attainable moment set and closed-loop INDI simulations for a yaw-limited eVTOL. The results demonstrate that the adaptive scaling gain closely approximates the linear programming ground truth while offering significantly higher computational efficiency. Furthermore, it effectively mitigates cross-axis coupling, reduces peak excursions, and alleviates rotor saturation. These findings highlight the method’s effectiveness, modularity, and suitability for real-time implementation in aerospace applications. Full article

Regional seismic phases are essential for imaging Earth’s internal structure. Although extensive regional seismic networks are publicly available worldwide, only a small fraction of recorded phase arrivals are picked for constraining earthquake source parameters, leaving most data untapped. Recent deep-learning methods offer powerful tools for automatic phase picking, yet their performance often lags behind that of human experts, particularly at relatively large epicentral distances such as the case of the Pn phase (~200–2000 km). Here, we systematically assess the effect of different test-time augmentation strategies on the Pn phase picking performance using PickNet and PhaseNet, along with the Seis-PnSn dataset containing data worldwide to simulate the out-of-distribution situation. We also propose quality control measures to obtain reliable results when ground truths are unknown. Our experiments show that filter-bank augmentation is more effective than the shift augmentation and the rotation augmentation, improving the proportion of picks within ±0.5/1.0 s errors to 53.87%/70.82% compared with the baseline of 48.98%/66.94% for PickNet and ±0.5/1.0 s errors to 48.45%/67.06% compared with the baseline of 46.32%/64.28% for PhaseNet. After the quality control using the standard deviation of different augmentation results, the proportion is further boosted to 67.39%/78.53% for PickNet and 57.99%/74.72% for PhaseNet. Additionally, we provide the workflow in our study as scripts for real-world data processing. Our work enhances both the accuracy and accessibility of regional seismic phase picking, thereby contributing to the studies of Earth’s internal structure and earthquake source characterization. Full article

Turbulent flow separation over lifting surfaces impacts high-lift systems such as aircraft, wind turbines, and turbomachinery, and contributes to noise, lift loss, and vibrations. Accurate detection of flow separation is therefore essential to enable active control strategies and to mitigate its adverse effects. Several machine learning models are compared for detecting flow separation from surface pressure fluctuations. The models were trained on experimental data covering various airfoils, angles of attack (0°–23°), and Reynolds numbers, with ${\mathrm{Re}}_c=0.8–4.5\times {10}^6$. For supervised learning, the ground-truth binary labels (attached or separated flow) were derived from static pressure distributions, lift coefficients, and the power spectral densities of surface pressure fluctuations. Three machine learning techniques (multilayer perceptron, support vector machine, logistic regression) were utilized with fine-tuned hyperparameters. Promising results are obtained, with the support vector machine achieving the highest performance (accuracy 0.985, Matthews correlation coefficient 0.975), comparable to other models, with advantages in runtime and model size. However, most misclassifications occur near separation onset due to gradual transition, suggesting areas for model refinement. Sensitivity to database parameters is discussed alongside flow physics and data quality. Full article