Search Results (32,953)

Accurate leaf area measurement is essential for plant growth monitoring and ecological research; however, it is often challenged by perspective distortion and color inconsistencies resulting from variations in shooting conditions and plant status. To address these issues, this study proposes a visual and semi-automatic measurement system. The system utilizes Hough transform-based perspective transformation to correct perspective distortions and incorporates manually sampled points to obtain prior color information, effectively mitigating color inconsistency. Based on this prior knowledge, the level-set function is automatically initialized. The leaf extraction is achieved through level-set curve evolution that minimizes an energy function derived from a multivariate Gaussian distribution model, and the evolution process allows visual monitoring of the leaf extraction progress. Experimental results demonstrate robust performance under diverse conditions: the standard deviation remains below 1 cm², the relative error is under 1%, the coefficient of variation is less than 3%, and processing time is under 10 s for most images. Compared to the traditional labor-intensive and time-consuming manual photocopy-weighing approach, as well as OpenPheno (which lacks parameter adjustability) and ImageJ 1.54g (whose results are highly operator-dependent), the proposed system provides a more flexible, controllable, and robust semi-automatic solution. It significantly reduces operational barriers while enhancing measurement stability, demonstrating considerable practical application value. Full article

Background/Objectives: Single-phase CT angiography (sCTA) is widely used to assess collateral circulation in acute ischemic stroke, but its static nature can lead to an underestimation of collateral flow. Our study aimed to develop and validate a direct, qualitative dynamic CTA (dCTA) collateral score based on CTP source images, without the need for post-processing software, to provide a more accurate prognostic tool. Methods: We retrospectively analyzed 112 patients with anterior circulation ischemic stroke from a prospective registry who underwent non-contrast CT, sCTA, and CTP within 8 h of onset. Collateral circulation was graded using a 4-point sCTA score and our novel 4-point dCTA score, which incorporates temporal filling patterns. We used linear regression to compare the association of both scores with CTP-derived core/hypoperfusion volumes, infarct growth, and final infarct volume. Results: The dCTA method frequently reclassified patients with poor collaterals on sCTA to good collaterals on dCTA (n = 23), while the reverse was rare (n = 5). A better collateral score was significantly associated with smaller core volume for both sCTA and dCTA, but the dCTA score demonstrated a superior model fit (R² = 0.36 vs. 0.32). Similar superior correlations for dCTA were observed for hypoperfusion, infarct growth, and final infarct volumes. Critically, only the dCTA score significantly modified the association between core volume and time since stroke onset (p for interaction = 0.04). Conclusions: A collateral score derived from CTP source images (dCTA) offers a more reliable prediction of infarct lesion sizes and progression than conventional sCTA. By incorporating temporal resolution without requiring extra software, dCTA provides a robust correlation with stroke temporal evolution and represents a readily implementable tool to enhance patient selection in acute stroke. Full article

Automated Road defect detection using Unmanned Aerial Vehicles (UAVs) has emerged as an efficient and safe solution for large-scale infrastructure inspection. However, object detection in aerial imagery poses unique challenges, including the prevalence of extremely small targets, complex backgrounds, and significant scale variations. Mainstream deep learning-based detection models often struggle with these issues, exhibiting limitations in detecting small cracks, high computational demands, and insufficient generalization ability for UAV perspectives. To address these challenges, this paper proposes a novel comprehensive network, RoadNet, specifically designed for high-precision road defect detection in UAV-captured imagery. RoadNet innovatively integrates Transformer modules with a convolutional neural network backbone and detection head. This design not only significantly enhances the global feature modeling capability crucial for understanding complex aerial contexts but also maintains the computational efficiency necessary for potential real-time applications. The model was trained and evaluated on a self-collected UAV road defect dataset (UAV-RDD). In comparative experiments, RoadNet achieved an outstanding mAP@0.5 score of 0.9128 while maintaining a fast-processing speed of 210.01 ms per image, outperforming other state-of-the-art models. The experimental results demonstrate that RoadNet possesses superior detection performance for road defects in complex aerial scenarios captured by drones. Full article

The detection of internal solitary waves (ISWs) in the ocean using Synthetic Aperture Radar (SAR) images is important for the safety of marine engineering structures. Based on 4120 Sentinel SAR images obtained from 2014 to 2024, an ISW dataset covering the Andaman Sea (AS), the South China Sea (SCS), the Sulu Sea (SS), and the Celebes Sea (CS) is constructed, and a deep learning dataset containing 3495 detection samples and 2476 segmentation samples is also established. Based on the YOLOv8 lightweight model, combined with an anti-interference strategy, a multi-size block detection strategy, and a post-processing repair module, an ISW detection method is proposed. This method reduces the false detection rate by 44.20 percentage points in terms of anti-interference performance. In terms of repair performance, the repair rate reaches 85.2%, and the error connection rate is less than 3.1%. The detection results of applying this method to Sentinel images in multiple sea areas show that there are significant regional differences in ISW activities in different sea areas: in the AS, ISW activities peak in the dry season of March and are mainly concentrated in the eastern and southern regions; the western part of the SS and the southern part of the CS are also the core areas of ISW activities. From the perspective of temporal characteristics, the SS maintains a relatively high ISW activity level throughout the dry season, while the CS exhibits more complex seasonal dynamic features. The lightweight detection method proposed in this study has good applicability and can provide support for marine disaster prevention work. Full article

As ultra-high resolution liquid crystal displays (LCDs) advance, crosstalk has become a critical challenge due to the reduced spacing of electronic circuits and increased signal frequencies. In particular, vertical crosstalk (V-CT) in vertical-alignment LCDs arises mainly from fringing electric fields generated by data lines, along with secondary contributions from data line–pixel coupling effect, thin-film transistor leakage, and other factors. To resolve V-CT, we propose a memory-efficient compensation algorithm implemented on a field-programmable gate array as a customized timing controller. The proposed algorithm achieves compensation accuracy within 2% while significantly reducing memory requirements. A conventional 7680 × 4320 pixel LCD panel requires approximately 796 MB of memory for compensation data, whereas our method reduces this to only 0.37 MB—a nearly 2000-fold reduction—by referencing only preceding pixel information. This approach enables cost-effective implementation, faster processing, and enhanced image quality. Overall, the proposed method provides a practical and scalable solution for resolving V-CT in 8K LCD panels, establishing a new benchmark for high-resolution display technologies. Full article

Short fibre-reinforced polymers (SFRPs) are increasingly used in structural applications where mechanical integrity under complex loading is critical. However, conventional modelling approaches often fail to accurately predict mechanical behaviour in weldline regions formed during injection moulding, where microstructural anomalies and pre-existing damage significantly degrade performance. This study addresses these limitations by extending a hybrid micro–macromechanical constitutive framework to incorporate localised initial damage at weldlines. Calibration and validation of the model were conducted using directional tensile tests on dumbbell-shaped polyamide 66 specimens reinforced with 25 wt% glass fibres, featuring controlled weldline geometry. Digital image correlation (DIC) was employed to capture strain fields, while injection moulding simulations provided fibre orientation distributions and weldline positioning. Results demonstrate that incorporating initial damage and its independent evolution for the cold weld region significantly improves prediction accuracy in weldline zones without compromising model efficiency. The proposed approach can be integrated seamlessly with existing finite element framework and offers a robust solution for simulating SFRP components with weldlines, enhancing reliability in safety-critical applications. Full article

Schizophrenia is a prevailing yet severely debilitating psychiatric disorder characterized by a convoluted etiology. Although antipsychotics have been available for over half a century, they primarily mitigate symptoms rather than providing definitive care. This limitation suggests that the neurotransmitter systems targeted by these medications are not the root cause of the disorder. Ongoing research seeks to elucidate the cellular, molecular, and circuitry pathways that contribute to the development of schizophrenia. Unfortunately, its precise pathogenesis remains incompletely understood. Accumulating evidence implicates dysregulated neurogenesis and aberrant neurodevelopmental processes as key contributors to disease progression. Recent advances in proteomics and imaging technology have facilitated the emergence of novel models of schizophrenia, emphasizing the roles of neuroinflammation, sex steroids, and cortisol. This paper aims to organize and map the intercorrelations and potential causal effects between various mechanistic models to gain deeper insight on how these mechanisms contribute to the cause, risks, and symptoms of the disorder. Furthermore, we discuss the potential therapeutic strategies that target these pathological pathways. Elucidating these mechanisms may ultimately advance our understanding of schizophrenia’s etiological foundations and guide the development of curative interventions. Full article

Addressing the challenges of multi-scene precision pesticide application for field broccoli crops and computational limitations of edge devices, this study proposes a lightweight broccoli detection method named DWG-YOLOv8, based on an improved YOLOv8s architecture. Firstly, Ghost Convolution is introduced into the C2f module, and the standard CBS module is replaced with Depthwise Separable Convolution (DWConv) to reduce model parameters and computational load during feature extraction. Secondly, a CDSL module is designed to enhance the model’s feature extraction capability. The CBAM attention mechanism is incorporated into the Neck network to strengthen the extraction of channel and spatial features, enhancing the model’s focus on the target. Experimental results indicate that compared to the original YOLOv8s, the DWG-YOLOv8 model has a size decreased by 35.6%, a processing time reduced by 1.9 ms, while its precision, recall, and mean Average Precision (mAP) have increased by 1.9%, 0.9%, and 3.4%, respectively. In comparative tests on complex background images, DWG-YOLOv8 showed reductions of 1.4% and 16.6% in miss rate and false positive rate compared to YOLOv8s. Deployed on edge devices using field-collected data, the DWG-YOLOv8 model achieved a comprehensive recognition accuracy of 96.53%, representing a 5.6% improvement over YOLOv8s. DWG-YOLOv8 effectively meets the lightweight requirements for accurate broccoli recognition in complex field backgrounds, providing technical support for object detection in intelligent precision pesticide application processes for broccoli. Full article

To investigate the failure characteristics and high-strain-rate mechanical response of polyvinyl alcohol-modified alkali-activated materials (PAAMs) under static and dynamic impact loads, quasi-static and uniaxial impact compression tests were performed on AAMs with varying PVA content. These tests employed a universal testing machine and an 80 mm diameter split Hopkinson pressure bar (SHPB). Digital image correlation (DIC) was then utilized to study the surface strain field of the composite material, and the crack propagation process during sample failure was analyzed. The experimental results demonstrate that the compressive strength of AAMs diminishes with higher PVA content, while the flexural strength initially increases before decreasing. It is suggested that the optimal PVA content should not exceed 5%. When the strain rate varies from 25.22 to 130.08 s⁻¹, the dynamic compressive strength, dissipated energy, and dynamic compressive increase factor (DCIF) of the samples all exhibit significant strain rate effects. Furthermore, the logarithmic function model effectively fits the dynamic strength evolution pattern of AAMs. DIC observations reveal that, under high strain rates, the crack mode of the samples gradually transitions from tensile failure to a combined tensile–shear multi-crack pattern. Furthermore, the crack propagation rate rises as the strain rate increases, which demonstrates the toughening effect of PVA on AAMs. Full article

Background: Non-Hodgkin lymphomas (NHLs) are a heterogeneous group of indolent or aggressive lymphoproliferative neoplasms arising from lymph nodes or in extranodal locations. Computed tomography (CT) is the imaging modality of choice, while the definitive diagnosis is confirmed by analyzing tissue samples. The aim of this study was to determine the correlation between CT characteristics and histopathological types of abdominal lymphomas. Methods: A retrospective cross-sectional study included 119 patients with histopathologically confirmed abdominal lymphomas who underwent CT of the abdomen and pelvis prior to treatment. The following CT parameters were extracted: morphological presentation (enlarged lymph nodes/conglomerates, solid mass/masses, gastrointestinal wall thickening, abdominal organ involvement, intra- and extraperitoneal infiltrates), location, two-dimensional size, propagation if present, and postcontrast enhancement. Results: Enlarged lymph nodes were a slightly more common CT morphological appearance in the indolent B NHL group, while gastrointestinal (GI) wall thickening, solid masses, and infiltrates were more frequent in the aggressive B NHL group (p = 0.0256). Aggressive B-cell lymphomas had larger size at time of diagnosis compared to other types (p = 0.0436). CT postcontrast enhancement showed lymphomas originating from the gastrointestinal tract, which presented as wall thickening, had the highest enhancement (p = 0.0065 and p = 0.0485). Conclusions: Observed differences in abdominal lymphomas’ histopathological and imaging characteristics including location/origin, CT morphological appearance, and postcontrast enhancement revealed that extranodal lymphomas were more often of the aggressive B-cell type, aggressive B-cell types were larger, and GI tract lymphomas showed the most prominent enhancement. These findings can help in the diagnostic process and enable better management of lymphomas. Full article

Recent advances in vision-language models such as BLIP-2 have made AI-generated image descriptions increasingly fluent and difficult to distinguish from human-authored texts. This paper investigates whether such differences can still be reliably detected by introducing a novel bilingual dataset of English and Romanian captions. The English subset was derived from the T4SA dataset, while AI-generated captions were produced with BLIP-2 and translated into Romanian using MarianMT; human-written Romanian captions were collected via manual annotation. We analyze the problem from two perspectives: (i) semantic alignment, using CLIP similarity, and (ii) supervised classification with both traditional and transformer-based models. Our results show that BERT achieves over 95% cross-validation accuracy (F1 = 0.95, ROC AUC = 0.99) in distinguishing AI from human texts, while simpler classifiers such as Logistic Regression also reach competitive scores (F1 ≈ 0.88). Beyond classification, semantic and linguistic analyses reveal systematic cross-lingual differences: English captions are significantly longer and more verbose, whereas Romanian texts—often more concise—exhibit higher alignment with visual content. Romanian was chosen as a representative low-resource language, where studying such differences provides insights into multilingual AI detection and challenges in vision-language modeling. These findings emphasize the novelty of our contribution: a publicly available bilingual dataset and the first systematic comparison of human vs. AI-generated captions in both high- and low-resource languages. Full article

This paper presents new fast discrete Krawtchouk transform (DKT) algorithms for input sequences of length 3 to 8. Small-sized DKT algorithms can be utilized in image processing applications to extract local image features formed by a sliding spatial window, and they can also serve as building blocks for developing larger-sized algorithms. Existing strategies to reduce the computational complexity of DKT mainly focus on modifying the recurrence relations for Krawtchouk polynomials, dividing the input signals into blocks or layers, or using different methods to approximate the coefficient values. Algorithms developed using the first two strategies are computationally intensive, which introduces a significant time delay in the computation process. Algorithms based on the approximation of polynomial coefficient values reduce computation time but at the expense of reduced accuracy. We use a different approach based on reducing the block structure of the matrix to one of the previously developed block-structural patterns, which allows us to factorize the resulting matrix in such a way that it leads to a reduction in the computational complexity of the synthesized algorithm. We describe the algorithmic solutions we have obtained through data flow graphs. The proposed DKT algorithms reduce the number of multiplications, additions, and shifts by an average of 58%, 27%, and 68%, respectively, compared to the direct computation of DKT via matrix-vector product. These characteristics were averaged across the considered input sizes (from 3 to 8). Full article

Wind turbine blade damage detection is crucial for advancing wind energy as a sustainable alternative to fossil fuels. Existing methods based on image processing technologies face challenges such as limited adaptability to complex environments, trade-offs between model accuracy and computational efficiency, and inadequate real-time inference capabilities. In response to these limitations, we put forward MSWindD-YOLO, a lightweight real-time detection model for wind turbine blade damage. Building upon YOLOv5s, our work introduces three key improvements: (1) the replacement of the Focus module with the Stem module to enhance computational efficiency and multi-scale feature fusion, integrating EfficientNetV2 structures for improved feature extraction and lightweight design, while retaining the SPPF module for multi-scale context awareness; (2) the substitution of the C3 module with the GBC3-FEA module to reduce computational redundancy, coupled with the incorporation of the CBAM attention mechanism at the neck network’s terminus to amplify critical features; and (3) the adoption of Shape-IoU loss function instead of CIoU loss function to facilitate faster model convergence and enhance localization accuracy. Evaluated on the Wind Turbine Blade Damage Visual Analysis Dataset (WTBDVA), MSWindD-YOLO achieves a precision of 95.9%, a recall of 96.3%, an mAP@0.5 of 93.7%, and an mAP@0.5:0.95 of 87.5%. With a compact size of 3.12 MB and 22.4 GFLOPs inference cost, it maintains high efficiency. After TensorRT acceleration on Jetson Orin NX, the model attains 43 FPS under FP16 quantization for real-time damage detection. Consequently, the proposed MSWindD-YOLO model not only elevates detection accuracy and inference efficiency but also achieves significant model compression. Its deployment-compatible performance in edge environments fulfills stringent industrial demands, ultimately advancing sustainable wind energy operations through lightweight lifecycle maintenance solutions for wind farms. Full article

Unmanned aerial vehicle (UAV) imagery provides an efficient approach for monitoring cotton defoliation and boll-opening rates. Deep learning, particularly convolutional neural networks (CNNs), has been widely applied in image processing and agricultural monitoring, achieving strong performance in tasks such as disease detection, weed recognition, and yield prediction. However, existing models often suffer from heavy computational costs and slow inference speed, limiting their real-time deployment in agricultural fields. To address this challenge, we propose a lightweight cotton maturity recognition model, RTCMNet (Real-time Cotton Monitoring Network). By incorporating a multi-scale convolutional attention (MSCA) module and an efficient feature fusion strategy, RTCMNet achieves high accuracy with substantially reduced computational complexity. A UAV dataset was constructed using images collected in Xinjiang, and the proposed model was benchmarked against several state-of-the-art networks. Experimental results demonstrate that RTCMNet achieves 0.96 and 0.92 accuracy on defoliation rate and boll-opening rate classification tasks, respectively. Meanwhile, it contains only 0.35 M parameters—94% fewer than DenseNet121—and only requires an inference time of 33 ms, representing a 97% reduction compared to DenseNet121. Field tests further confirm its real-time performance and robustness on UAV platforms. Overall, RTCMNet provides an efficient and low-cost solution for UAV-based cotton maturity monitoring, supporting the advancement of precision agriculture. Full article

The aim of the study was to explore the psychosocial perceptions that young adults have regarding gender-based violence, including those based on their personal experiences, and to highlight perceptions related to social media and how its use might be connected to gender-based violence. The participants were 40 university students from Northwestern Italy with an average age of 21.8 years (range: 19–25); 50% were women. Sampling was non-probabilistic and followed a purposive convenience strategy. Semi-structured interviews were conducted online and audio-recorded, and data were analyzed using the reflective thematic approach. The results revealed that young adults are very aware, at a theoretical level, of “offline” physical, psychological, and verbal gender-based violence and its effects, while they do not give much consideration to online violence, despite often being victims of it, as revealed by their accounts, for example, through unsolicited explicit images or persistent harassment on social media. Therefore, the results of this research highlight the need to develop primary prevention programs focused on increasing awareness and providing young people with more tools to identify when they have been victims of violence, both online and offline, and to process the emotional experiences associated with such events. Full article