Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

Search Results (206)

Search Parameters:
Keywords = photography experiment

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 1971 KiB  
Article
FFG-YOLO: Improved YOLOv8 for Target Detection of Lightweight Unmanned Aerial Vehicles
by Tongxu Wang, Sizhe Yang, Ming Wan and Yanqiu Liu
Appl. Syst. Innov. 2025, 8(4), 109; https://doi.org/10.3390/asi8040109 - 4 Aug 2025
Abstract
Target detection is essential in intelligent transportation and autonomous control of unmanned aerial vehicles (UAVs), with single-stage detection algorithms used widely due to their speed. However, these algorithms face limitations in detecting small targets, especially in aerial photography from unmanned aerial vehicles (UAVs), [...] Read more.
Target detection is essential in intelligent transportation and autonomous control of unmanned aerial vehicles (UAVs), with single-stage detection algorithms used widely due to their speed. However, these algorithms face limitations in detecting small targets, especially in aerial photography from unmanned aerial vehicles (UAVs), where small targets are often occluded, multi-scale semantic information is easily lost, and there is a trade-off between real-time processing and computational resources. Existing algorithms struggle to effectively extract multi-dimensional features and deep semantic information from images and to balance detection accuracy with model complexity. To address these limitations, we developed FFG-YOLO, a lightweight small-target detection method for UAVs based on YOLOv8. FFG-YOLO incorporates three modules: a feature enhancement block (FEB), a feature concat block (FCB), and a global context awareness block (GCAB). These modules strengthen feature extraction from small targets, resolve semantic bias in multi-scale feature fusion, and help differentiate small targets from complex backgrounds. We also improved the positioning accuracy of small targets using the Wasserstein distance loss function. Experiments showed that FFG-YOLO outperformed other algorithms, including YOLOv8n, in small-target detection due to its lightweight nature, meeting the stringent real-time performance and deployment requirements of UAVs. Full article
Show Figures

Figure 1

25 pages, 8654 KiB  
Article
Analysis of Flow Field and Machining Parameters in RUREMM for High-Precision Micro-Texture Fabrication on SS304 Surfaces
by Wenjun Tong and Lin Li
Processes 2025, 13(8), 2326; https://doi.org/10.3390/pr13082326 - 22 Jul 2025
Viewed by 282
Abstract
Micro-textures are crucial for enhancing surface performance in diverse applications, but traditional radial electrochemical micromachining (REMM) suffers from process complexity and workpiece damage. This study presents radial ultrasonic rolling electrochemical micromachining (RUREMM), an advanced technique integrating an ultrasonic field to improve electrolyte renewal, [...] Read more.
Micro-textures are crucial for enhancing surface performance in diverse applications, but traditional radial electrochemical micromachining (REMM) suffers from process complexity and workpiece damage. This study presents radial ultrasonic rolling electrochemical micromachining (RUREMM), an advanced technique integrating an ultrasonic field to improve electrolyte renewal, disrupt passivation layers, and optimize electrochemical reaction uniformity on SS304 surfaces. Aimed at overcoming challenges in precision machining, the research explores the synergistic effects of ultrasonic energy and flow field dynamics, offering novel insights for high-quality metal micromachining applications. The research establishes a mathematical model to analyze the interaction between the ultrasonic energy field and electrolytic machining and optimizes the flow field in the narrow electrolytic gap using Fluent software, revealing that an initial electrolyte velocity of 4 m/s and ultrasonic amplitude of 35 μm ensure optimal stability. High-speed photography is employed to capture bubble distribution and micro-pit formation dynamics, while SS304 surface experiments analyze the effects of machining parameters on micro-dimple localization and surface quality. The results show that optimized parameters significantly improve micro-texture quality, yielding micro-pits with a width of 223.4 μm, depth of 28.9 μm, aspect ratio of 0.129, and Ra of 0.205 μm, providing theoretical insights for high-precision metal micromachining. Full article
(This article belongs to the Section Manufacturing Processes and Systems)
Show Figures

Figure 1

18 pages, 33092 KiB  
Article
Yarn Color Measurement Method Based on Digital Photography
by Jinxing Liang, Guanghao Wu, Ke Yang, Jiangxiaotian Ma, Jihao Wang, Hang Luo, Xinrong Hu and Yong Liu
J. Imaging 2025, 11(8), 248; https://doi.org/10.3390/jimaging11080248 - 22 Jul 2025
Viewed by 248
Abstract
To overcome the complexity of yarn color measurement using spectrophotometry with yarn winding techniques and to enhance consistency with human visual perception, a yarn color measurement method based on digital photography is proposed. This study employs a photographic colorimetry system to capture digital [...] Read more.
To overcome the complexity of yarn color measurement using spectrophotometry with yarn winding techniques and to enhance consistency with human visual perception, a yarn color measurement method based on digital photography is proposed. This study employs a photographic colorimetry system to capture digital images of single yarns. The yarn and background are segmented using the K-means clustering algorithm, and the centerline of the yarn is extracted using a skeletonization algorithm. Spectral reconstruction and colorimetric principles are then applied to calculate the color values of pixels along the centerline. Considering the nonlinear characteristics of human brightness perception, the final yarn color is obtained through a nonlinear texture-adaptive weighted computation. The method is validated through psychophysical experiments using six yarns of different colors and compared with spectrophotometry and five other photographic measurement methods. Results indicate that among the seven yarn color measurement methods, including spectrophotometry, the proposed method—based on centerline extraction and nonlinear texture-adaptive weighting—yields results that more closely align with actual visual perception. Furthermore, among the six photographic measurement methods, the proposed method produces most similar to those obtained using spectrophotometry. This study demonstrates the inconsistency between spectrophotometric measurements and human visual perception of yarn color and provides methodological support for developing visually consistent color measurement methods for textured textiles. Full article
(This article belongs to the Section Color, Multi-spectral, and Hyperspectral Imaging)
Show Figures

Figure 1

15 pages, 5251 KiB  
Article
Experimental Investigation of Flow Characteristics Inside a Venturi Tube Under Gas-Containing Conditions
by Qiang Guo, Chaoshan Lu, Xianbei Huang, Aibo Jiang and Xiaodong Liu
Water 2025, 17(14), 2080; https://doi.org/10.3390/w17142080 - 11 Jul 2025
Viewed by 358
Abstract
Gas–liquid two-phase flow is very common in fluid machinery and has complex multiphase flow characteristics. Under the gas-containing conditions, common issues in fluid machinery include the transport of liquid, bubble variations, and pressure drop characteristics; these can be analyzed using a simplified venturi [...] Read more.
Gas–liquid two-phase flow is very common in fluid machinery and has complex multiphase flow characteristics. Under the gas-containing conditions, common issues in fluid machinery include the transport of liquid, bubble variations, and pressure drop characteristics; these can be analyzed using a simplified venturi tube. In order to investigate the influence of incoming gas on the gas–liquid flow, a venturi tube with the range of inlet gas volume fraction (IGVF) from 0 to 16% was used in this experiment. The development of a two-phase flow was recorded by using high-speed photography. Under different initial liquid flow rates and gas content conditions, the evolution of the two-phase flow was similar, with the main difference being the rate of evolution. The incoming gas mainly underwent a process from column shape to expansion and then to fragmentation passing through the venturi tube. In the experimental images, the projected area of the main bubble increased linearly with the increase in IGVF. Meanwhile, the transporting ability of the venturi tube was weakened due to the blockage caused by high gas content, especially when the IGVF exceeded 10%. The pressure drop characteristics indicated an increase in losses with the increase in gas content. Full article
Show Figures

Figure 1

23 pages, 10465 KiB  
Article
Dynamically Triggered Damage Around Rock Tunnels: An Experimental and Theoretical Investigation
by Wanlu Wang, Ming Tao, Wenjun Ding and Rui Zhao
Appl. Sci. 2025, 15(14), 7716; https://doi.org/10.3390/app15147716 - 9 Jul 2025
Viewed by 276
Abstract
Dynamic impact experiments based on high-speed photography and digital image correlation (DIC) techniques were carried out on sandstone specimens containing arched holes to investigate the effect of the incident angle. In addition, the complex function method based on conformal mapping was used to [...] Read more.
Dynamic impact experiments based on high-speed photography and digital image correlation (DIC) techniques were carried out on sandstone specimens containing arched holes to investigate the effect of the incident angle. In addition, the complex function method based on conformal mapping was used to theoretically calculate the transient dynamic stress distributions around the arched holes. The test results indicated that the strength and modulus of elasticity of the specimens under dynamic impact decreased and then increased with the increase of the inclination angle of the holes from 0 to 90° at intervals of 15°, reaching a minimum value at 60°, due to the large stress concentration at this angle leading to the shear failure of the specimen. During the experiment, rock debris ejections, spalling, and heaving were observed around the holes, and the rock debris ejections served as an indicator to identify the early fracture. The damage mechanism around the holes was revealed theoretically, i.e., the considerable compressive stress concentration in the perpendicular incidence direction around the arched hole and the tensile stress concentration on the incidence side led to the initiation of the damage around the cavity, and the theoretical results were in satisfactory agreement with the experimental results. In addition, the effect of the initial stress on the dynamic response of the arched tunnel was discussed. Full article
(This article belongs to the Special Issue Advances in Failure Mechanism and Numerical Methods for Geomaterials)
Show Figures

Figure 1

20 pages, 1766 KiB  
Article
A Photovoice Study on the Lived Experiences of Youth and Mothers of Incarcerated Fathers and Husbands, Highlighting the Relevance of Abolitionist Social Work Practice
by Elizabeth K. Allen, Jason Ostrander and Kate Kelly
Soc. Sci. 2025, 14(7), 411; https://doi.org/10.3390/socsci14070411 - 29 Jun 2025
Viewed by 319
Abstract
This community-based participatory research (CBPR) study explored, using a Photovoice methodology, the lived expeiences of northeastern Black and/or African American youth and mothers who were currently experiencing the incarceration of their fathers and husbands. Grounded in critical theories of dual consciousness and comparative [...] Read more.
This community-based participatory research (CBPR) study explored, using a Photovoice methodology, the lived expeiences of northeastern Black and/or African American youth and mothers who were currently experiencing the incarceration of their fathers and husbands. Grounded in critical theories of dual consciousness and comparative conflict, the findings provide valuable insights into how this population navigates the intersections of family, school, and community within the context of the criminal legal system, and, in the process, underscore the relevance of Abolitionist practice in capturing their theoretically lived experiences. Participants documented through photography and narrative reflections the multifaceted impacts of incarceration on fathers and husbands, including disrupted family dynamics, social stigma, and barriers to community resources. A focus group with the mothers of these youth highlighted the profound impact of incarceration on their family structure, revealing significant emotional burdens for caregivers as well as personal changes to parenting styles as a result of this project. A central theme that emerged was the development of a “double” or “dual consciousness”—an ability to see humanity and injustice in their circumstances, fueling a desire for systemic change. Overall, this CBPR project amplifies the voices of marginalized youth and mothers, illuminating how the criminal legal system perpetuates cycles of trauma, stigma, and disempowerment. The implications call for a radical reimagining of the role of social work in creating more equitable, restorative, and healing-centered communities, including an immediate embrace of Abolitionist practice concepts and interventions. Full article
Show Figures

Figure 1

28 pages, 1707 KiB  
Review
Video Stabilization: A Comprehensive Survey from Classical Mechanics to Deep Learning Paradigms
by Qian Xu, Qian Huang, Chuanxu Jiang, Xin Li and Yiming Wang
Modelling 2025, 6(2), 49; https://doi.org/10.3390/modelling6020049 - 17 Jun 2025
Viewed by 942
Abstract
Video stabilization is a critical technology for enhancing video quality by eliminating or reducing image instability caused by camera shake, thereby improving the visual viewing experience. It has deeply integrated into diverse applications—including handheld recording, UAV aerial photography, and vehicle-mounted surveillance. Propelled by [...] Read more.
Video stabilization is a critical technology for enhancing video quality by eliminating or reducing image instability caused by camera shake, thereby improving the visual viewing experience. It has deeply integrated into diverse applications—including handheld recording, UAV aerial photography, and vehicle-mounted surveillance. Propelled by advances in deep learning, data-driven stabilization methods have emerged as prominent solutions, demonstrating superior efficacy in handling jitter while achieving enhanced processing efficiency. This review systematically examines the field of video stabilization. First, this paper delineates the paradigm shift from classical to deep learning-based approaches. Subsequently, it elucidates conventional digital stabilization frameworks and their deep learning counterparts along with establishing standardized assessment metrics and benchmark datasets for comparative analysis. Finally, this review addresses critical challenges such as robustness limitations in complex motion scenarios and latency constraints in real-time processing. By integrating interdisciplinary perspectives, this work provides scholars with academically rigorous and practically relevant insights to advance video stabilization research. Full article
Show Figures

Graphical abstract

19 pages, 4003 KiB  
Article
The Risk to the Undersea Engineering Ecosystem of Systems: Understanding Implosion in Confined Environments
by Craig Tilton and Arun Shukla
J. Mar. Sci. Eng. 2025, 13(6), 1180; https://doi.org/10.3390/jmse13061180 - 17 Jun 2025
Viewed by 640
Abstract
As humans continue to develop the undersea engineering ecosystem of systems, the consequences of catastrophic events must continue to be investigated and understood. Almost every undersea pressure vessel, from pipelines to sensors to unmanned vehicles, has the potential to experience a catastrophic collapse, [...] Read more.
As humans continue to develop the undersea engineering ecosystem of systems, the consequences of catastrophic events must continue to be investigated and understood. Almost every undersea pressure vessel, from pipelines to sensors to unmanned vehicles, has the potential to experience a catastrophic collapse, known as an implosion. This collapse can be caused by hydrostatic pressure or any combination of external loadings from natural disasters to pressure waves imparted by other implosion or explosion events. During an implosion, high-magnitude pressure waves can be emitted, which can cause adverse effects on surrounding structures, marine life, or even people. The imploding structure, known as an implodable volume, can be in a free-field or confined environment. Confined implosion is characterized by a surrounding structure that significantly affects the flow of fluid around the implodable volume. Often, the confining structure is cylindrical, with one closed end and one open end. This work seeks to understand the effect of fluid flow restriction on the physics of implosion inside a confining tube. To do so, a comprehensive experimental study is conducted using a unique experimental facility. Thin-walled aluminum cylinders are collapsed inside a confining tube within a large pressure vessel. High-speed photography and 3D Digital Image Correlation are used to gather structural displacement and velocities during the event while an array of dynamic pressure sensors capture the pressure data inside the confining tube. The results of this work show that by changing the size of the open end, referred to as the flow area ratio, there can be a significant effect on the structural deformations and implosion severity. It also reveals that only certain configurations of holes at the open end of the tube play a role in the dynamic pressure pulse measured at the closed end of the tube. By understanding the consequences of an implosion, designers can make decisions about where these pressure vessels should be in relation to other pressure vessels, critical infrastructure, marine life, or people. In the same way that engineers design for earthquakes and analyze the impact their structures have on the environment around them, contributors to the undersea engineering ecosystem should design with implosion in mind. Full article
(This article belongs to the Section Ocean Engineering)
Show Figures

Figure 1

25 pages, 3953 KiB  
Article
Radical Imagination: An Afrofuturism and Creative Aging Program for Black Women’s Brain Health and Wellness
by Tanisha G. Hill-Jarrett, Ashley J. Jackson, Alinda Amuiri and Gloria A. Aguirre
Int. J. Environ. Res. Public Health 2025, 22(6), 875; https://doi.org/10.3390/ijerph22060875 - 31 May 2025
Viewed by 828
Abstract
Intersectional oppression and invisibility are primary drivers of cognitive and mental health disparities that affect Black women’s wellness. Older Black women additionally experience compounding effects of ageism, which may place them at increased risk for a decline in cognitive functioning and mental wellness. [...] Read more.
Intersectional oppression and invisibility are primary drivers of cognitive and mental health disparities that affect Black women’s wellness. Older Black women additionally experience compounding effects of ageism, which may place them at increased risk for a decline in cognitive functioning and mental wellness. To date, limited strengths-based, culturally relevant programming has focused on aging Black women. Fewer have incorporated Black women elders into conversations on Black liberation and the transformational change needed to create possible futures rooted in equity, healing, and health. This manuscript describes the inception and development of Radical Imagination, a creative aging program for Black women in the San Francisco Bay Area. Over ten weeks, 42 Black women (M age = 73.6, SD = 6.20; range: 58–85 years old) participated in the program, which incorporated brain and mental health education, art-making, storytelling, and photography. Grounded in principles of Afrofuturism and radical healing, participants explored past narratives of Black women and created a collective vision for a future that centers on Black women’s needs. Approximately 54.8% of participants attended more than one workshop. Upon program completion, exit surveys indicated that participants reported a moderate level of hopefulness about their ability to shape the future. Respondents reported overall satisfaction with the workshop series. We conclude with reflections on our process and recommendations for ways to support aging Black women using Afrofuturism and the arts. Full article
Show Figures

Figure 1

19 pages, 6871 KiB  
Article
Determining the Vibration Parameters for Coffee Harvesting Through the Vibration of Fruit-Bearing Branches: Field Trials and Validation
by Shengwu Zhou, Yingjie Yu, Wei Su, Hedong Wang, Bo Yuan and Yu Que
Agriculture 2025, 15(10), 1036; https://doi.org/10.3390/agriculture15101036 - 11 May 2025
Viewed by 544
Abstract
In order to explore the optimal vibration parameters for the selective harvesting of coffee fruits, a high-velocity dynamic photography monitoring system was developed to analyze the vibration-assisted harvesting process. This system identified the optimal vibration position on coffee branches and facilitated theoretical energy [...] Read more.
In order to explore the optimal vibration parameters for the selective harvesting of coffee fruits, a high-velocity dynamic photography monitoring system was developed to analyze the vibration-assisted harvesting process. This system identified the optimal vibration position on coffee branches and facilitated theoretical energy transfer analysis, obtaining a mathematical formula for calculating the total kinetic energy of coffee branches. A single-factor experiment was conducted with the vibration position as the experimental factor and the total kinetic energy of coffee branches as the response variable. The results showed that the total kinetic energy of the branches was the highest at Vibration Position 2 (the position between the third and the fourth Y-shaped bud tips on the branch). Therefore, Vibration Position 2 was determined as the optimal vibration position. Further analysis established a mathematical model linking coffee cherry motion parameters to theoretical detachment force. A factorial experiment was conducted with vibration frequency and amplitude as test factors, using detachment rates of green, semi-ripe, and ripe cherries as indicators. The results showed that at 55 Hz and 10.10 mm amplitude, the detachment rate of ripe cherries was highest (83.33%), while green and semi-ripe cherries detached at 16.67% and 33.33%, respectively. A field validation experiment, with Vibration Position 2, 55 Hz frequency, 10.10 mm amplitude, and 1 s vibration duration, yielded actual detachment rates of 15.86%, 35.17%, and 89.50% for green, semi-ripe, and ripe cherries, respectively. The error margins compared with the theoretical values were all below 10%. These results confirm the feasibility of optimizing vibration harvesting parameters through high-velocity photography dynamic analysis. Full article
(This article belongs to the Special Issue Agricultural Machinery and Technology for Fruit Orchard Management)
Show Figures

Figure 1

18 pages, 8552 KiB  
Article
PID-NET: A Novel Parallel Image-Dehazing Network
by Wei Liu, Yi Zhou, Dehua Zhang and Yi Qin
Electronics 2025, 14(10), 1906; https://doi.org/10.3390/electronics14101906 - 8 May 2025
Viewed by 562
Abstract
Image dehazing is a critical task in image restoration, aiming to retrieve clear images from hazy scenes. This process is vital for various applications, including machine recognition, security monitoring, and aerial photography. Current dehazing algorithms often encounter challenges in multi-scale feature extraction, detail [...] Read more.
Image dehazing is a critical task in image restoration, aiming to retrieve clear images from hazy scenes. This process is vital for various applications, including machine recognition, security monitoring, and aerial photography. Current dehazing algorithms often encounter challenges in multi-scale feature extraction, detail preservation, effective haze removal, and maintaining color fidelity. To address these limitations, this paper introduces a novel Parallel Image-Dehazing Network (PID-Net). PID-Net uniquely combines a Convolutional Neural Network (CNN) for precise local feature extraction and a Vision Transformer (ViT) to capture global contextual information, overcoming the shortcomings of methods relying solely on either local or global features. A multi-scale CNN branch effectively extracts diverse local details through varying receptive fields, thereby enhancing the restoration of fine textures and details. To optimize the ViT component, a lightweight attention mechanism with CNN compensation is integrated, maintaining performance while minimizing the parameter count. Furthermore, a Redundant Feature Filtering Module is incorporated to filter out noise and haze-related artifacts, promoting the learning of subtle details. Our extensive experiments on public datasets demonstrated PID-Net’s significant superiority over state-of-the-art dehazing algorithms in both quantitative metrics and visual quality. Full article
Show Figures

Figure 1

14 pages, 3761 KiB  
Article
Different Influences of Soil and Climatic Factors on Shrubs and Herbaceous Plants in the Shrub-Encroached Grasslands of the Mongolian Plateau
by Yue Liu, Lei Dong, Jinrong Li, Shuaizhi Lu, Liqing Yi, Huimin Li, Shaoqi Chai and Jian Wang
Forests 2025, 16(4), 696; https://doi.org/10.3390/f16040696 - 17 Apr 2025
Viewed by 449
Abstract
Factors such as climate change, fire, and overgrazing have been commonly considered the main causes of the global expansion of shrub invasion in grasslands over the past 160 years. Nevertheless, the influence of soil substrates on the progression of shrub encroachment has been [...] Read more.
Factors such as climate change, fire, and overgrazing have been commonly considered the main causes of the global expansion of shrub invasion in grasslands over the past 160 years. Nevertheless, the influence of soil substrates on the progression of shrub encroachment has been insufficiently examined. This study examines the fundamental characteristics of the shrub-encroached desert steppe communities of Caragana tibetica in the Mongolian Plateau. Combining field surveys (field surveys and drone aerial photography) and laboratory experiments, using Spearman’s rank correlation analysis and structural equation modeling (SEM), this research systematically explores the impact of varying degrees of soil sandification on the survival of shrubs and herbaceous plants within these grassland communities. The findings indicate the following: (1) In the eight shrub-encroached grassland plots, the soil exhibited a significantly higher sand content compared to silt and clay, with the sand content generally exceeding 64%. (2) The coverage of shrub species is predominantly influenced by soil factors, particularly the soil sand content. (The path coefficient is 0.56, with p < 0.01). In contrast, herbaceous plants are more strongly influenced by climatic factors. (The path coefficient is 0.83, with p < 0.001). This study examines the response patterns of Caragana tibetica communities to edaphic and climatic factors, highlighting the pivotal role of soil sandification in the initiation and succession of shrub encroachment. The findings furnish a theoretical framework for forecasting future trends in grassland shrub encroachment and provide empirical evidence for the conservation and sustainable management of shrub-encroached grasslands. Full article
(This article belongs to the Section Forest Ecology and Management)
Show Figures

Figure 1

23 pages, 10647 KiB  
Article
Study on Local High-Velocity-Impact Characteristics of Carbon Fiber Composite Laminates Based on Experimental Image Sequences
by Shuguang Yao, Minxin Zhou and Jie Xing
Materials 2025, 18(8), 1833; https://doi.org/10.3390/ma18081833 - 16 Apr 2025
Cited by 1 | Viewed by 377
Abstract
For the complex operating environment of rail vehicles impacted by foreign objects, this study carried out experiments on carbon fiber composite laminates impacted by projectiles of three different materials in the gas gun apparatus. High-speed photography was used to capture the impact dynamic [...] Read more.
For the complex operating environment of rail vehicles impacted by foreign objects, this study carried out experiments on carbon fiber composite laminates impacted by projectiles of three different materials in the gas gun apparatus. High-speed photography was used to capture the impact dynamic process, with subsequent analysis of image sequences enabling the quantification of both projectile energy characteristics and laminate mechanical responses. The key findings reveal that (1) the impact force demonstrates a nonlinear relationship with the energy input, exhibiting diminishing growth rates at higher energy levels, while deformable aluminum projectiles yield significantly lower average impact forces; (2) crack propagation follows a characteristic pattern of initial expansion with the impact energy reaching maxima of 88.40 mm (concrete), 41.48 mm (steel), and 80.35 mm (aluminum), and then decreasing, followed by stabilization post-perforation; (3) the penetration depth showed an accelerating nonlinear growth trend with progressively higher rates of increases as the impact energy rose, and its variation trend exhibited a correlation with the crack length. The results provide quantitative insights into carbon fiber laminates’ damage mechanisms, which offer practical implications for the composite structure design in transportation systems subjected to foreign object impacts. Full article
(This article belongs to the Section Advanced Composites)
Show Figures

Figure 1

16 pages, 5727 KiB  
Article
ED-Swin Transformer: A Cassava Disease Classification Model Integrated with UAV Images
by Jing Zhang, Hao Zhou, Kunyu Liu and Yuguang Xu
Sensors 2025, 25(8), 2432; https://doi.org/10.3390/s25082432 - 12 Apr 2025
Cited by 1 | Viewed by 725
Abstract
The outbreak of cassava diseases poses a serious threat to agricultural economic security and food production systems in tropical regions. Traditional manual monitoring methods are limited by efficiency bottlenecks and insufficient spatial coverage. Although low-altitude drone technology offers advantages such as high resolution [...] Read more.
The outbreak of cassava diseases poses a serious threat to agricultural economic security and food production systems in tropical regions. Traditional manual monitoring methods are limited by efficiency bottlenecks and insufficient spatial coverage. Although low-altitude drone technology offers advantages such as high resolution and strong timeliness, it faces dual challenges in the field of disease identification, such as complex background interference and irregular disease morphology. To address these issues, this study proposes an intelligent classification method for cassava diseases based on drone imagery and an ED-Swin Transformer. Firstly, we introduced the EMAGE (Efficient Multi-Scale Attention with Grouping and Expansion) module, which integrates the global distribution features and local texture details of diseased leaves in drone imagery through a multi-scale grouped attention mechanism, effectively mitigating the interference of complex background noise on feature extraction. Secondly, the DASPP (Deformable Atrous Spatial Pyramid Pooling) module was designed to use deformable atrous convolution to adaptively match the irregular boundaries of diseased areas, enhancing the model’s robustness to morphological variations caused by angles and occlusions in low-altitude drone photography. The results show that the ED-Swin Transformer model achieved excellent performance across five evaluation metrics, with scores of 94.32%, 94.56%, 98.56%, 89.22%, and 96.52%, representing improvements of 1.28%, 2.32%, 0.38%, 3.12%, and 1.4%, respectively. These experiments demonstrate the superior performance of the ED-Swin Transformer model in cassava classification networks. Full article
Show Figures

Figure 1

35 pages, 7003 KiB  
Article
Federated LeViT-ResUNet for Scalable and Privacy-Preserving Agricultural Monitoring Using Drone and Internet of Things Data
by Mohammad Aldossary, Jaber Almutairi and Ibrahim Alzamil
Agronomy 2025, 15(4), 928; https://doi.org/10.3390/agronomy15040928 - 10 Apr 2025
Cited by 1 | Viewed by 821
Abstract
Precision agriculture is necessary for dealing with problems like pest outbreaks, a lack of water, and declining crop health. Manual inspections and broad-spectrum pesticide application are inefficient, time-consuming, and dangerous. New drone photography and IoT sensors offer quick, high-resolution, multimodal agricultural data collecting. [...] Read more.
Precision agriculture is necessary for dealing with problems like pest outbreaks, a lack of water, and declining crop health. Manual inspections and broad-spectrum pesticide application are inefficient, time-consuming, and dangerous. New drone photography and IoT sensors offer quick, high-resolution, multimodal agricultural data collecting. Regional diversity, data heterogeneity, and privacy problems make it hard to conclude these data. This study proposes a lightweight, hybrid deep learning architecture called federated LeViT-ResUNet that combines the spatial efficiency of LeViT transformers with ResUNet’s exact pixel-level segmentation to address these issues. The system uses multispectral drone footage and IoT sensor data to identify real-time insect hotspots, crop health, and yield prediction. The dynamic relevance and sparsity-based feature selector (DRS-FS) improves feature ranking and reduces redundancy. Spectral normalization, spatial–temporal alignment, and dimensionality reduction provide reliable input representation. Unlike centralized models, our platform trains over-dispersed client datasets using federated learning to preserve privacy and capture regional trends. A huge, open-access agricultural dataset from varied environmental circumstances was used for simulation experiments. The suggested approach improves on conventional models like ResNet, DenseNet, and the vision transformer with a 98.9% classification accuracy and 99.3% AUC. The LeViT-ResUNet system is scalable and sustainable for privacy-preserving precision agriculture because of its high generalization, low latency, and communication efficiency. This study lays the groundwork for real-time, intelligent agricultural monitoring systems in diverse, resource-constrained farming situations. Full article
(This article belongs to the Section Precision and Digital Agriculture)
Show Figures

Figure 1

Back to TopTop