Search Results (25,431)

Underwater image enhancement is crucial for fields like marine exploration, underwater photography, and environmental monitoring, as underwater images often suffer from reduced visibility, color distortion, and contrast loss due to light absorption and scattering. Despite recent progress, existing methods struggle to generalize across diverse underwater conditions, such as varying turbidity levels and lighting. This paper proposes a novel hybrid UNet–Transformer architecture based on MaxViT blocks, which effectively combines local feature extraction with global contextual modeling to address challenges including low contrast, color distortion, and detail degradation. Extensive experiments on two benchmark datasets, UIEB and EUVP, demonstrate the superior performance of our method. On UIEB, our model achieves a PSNR of 22.91, SSIM of 0.9020, and CCF of 37.93—surpassing prior methods such as URSCT-SESR and PhISH-Net. On EUVP, it attains a PSNR of 26.12 and PCQI of 1.1203, outperforming several state-of-the-art baselines in both visual fidelity and perceptual quality. These results validate the effectiveness and robustness of our approach under complex underwater degradation, offering a reliable solution for real-world underwater image enhancement tasks. Full article

To address the central cracking problem in continuous casting slabs of 38CrMoAl steel, high-temperature tensile tests were performed using a Gleeble-3800 thermal simulator to characterize the hot ductility of the steel within the temperature range of 600–1200 °C. The phase transformation behavior was computationally analyzed via the Thermo-Calc software, while the microstructure, fracture morphology, and precipitate characteristics were systematically investigated using a metallographic microscope (MM), a field-emission scanning electron microscope (FE-SEM), and transmission electron microscopy (TEM). Additionally, the effects of different holding times and cooling rates on the microstructure and precipitates of 38CrMoAl steel were also studied. The results show that the third brittle temperature region of 38CrMoAl steel is 645–1009 °C, and the fracture mechanisms can be classified into three types: (I) in the α single-phase region, the thickness of intergranular proeutectoid ferrite increases with rising temperature, leading to reduced hot ductility; (II) in the γ single-phase region, the average size of precipitates increases while the number density decreases with increasing temperature, thereby improving hot ductility; and (III) in the α + γ two-phase region, the precipitation of proeutectoid ferrite promotes crack propagation and the dense distribution of precipitates at grain boundaries causes stress concentration, further deteriorating hot ductility. Heat treatment experiments indicate that the microstructures of the specimen transformed under water cooling, air cooling, and furnace cooling conditions as follows: martensite + proeutectoid ferrite → bainite + ferrite → ferrite. The average size of precipitates first decreased, then increased, and finally decreased again with increasing holding time, while the number density exhibited the opposite trend. Therefore, when the holding time was the same, reducing the cooling rate could increase the average size of the precipitates and decrease their number density, thereby improving the hot ductility of 38CrMoAl steel. Full article

Water deficiency and low water use efficiency severely constrain wheat yield in dryland regions. This study aimed to identify suitable tillage methods and straw management to improve dry matter production, grain yield, and water use efficiency of wheat in the dryland winter wheat–summer bean (hereafter referred to as wheat-soybean) double-cropping system. A long-term located field experiment (onset in October 2009) with two tillage methods—plowing (PT) and rotary tillage (RT)—and two straw management—no straw mulching (NS) and straw mulching (SM)—was conducted at a typical dryland in China. The wheat yield and yield component, dry matter accumulation and translocation characteristics, and water use efficiency were investigated from 2014 to 2018. Straw management significantly affected wheat yield and yield components, while tillage methods had no significant effect. Furthermore, the interaction of tillage methods and straw management significantly affected yield and yield components except for the spike number. RTSM significantly increased the spike number, grains per spike, 1000-grain weight, harvest index, and grain yield by 12.5%, 8.4%, 6.0%, 3.4%, and 13.4%, respectively, compared to PTNS. Likewise, RTSM significantly increased the aforementioned indicators by 14.8%, 10.1%, 7.5%, 3.6%, and 20.5%, compared to RTNS. Mechanistic analysis revealed that, compared to NS, SM not only significantly enhanced pre-anthesis and post-anthesis dry matter accumulation, and pre-anthesis dry matter tanslocation to grain, but also significantly improved pre-sowing water storage, water consumption during wheat growth, water use efficiency, and water-saving for produced per kg grain yield, with the greatest improvements obtained under RT than PT. Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) analysis confirmed RTSM’s yield superiority was mainly ascribed to straw-induced improvements in dry matter and water productivity. In a word, rotary tillage with straw mulching could be recommended as a suitable practice for high-yield wheat production in a dryland wheat-soybean double-cropping system. Full article

Millisecond lasers, with their high processing efficiency and large power, are widely used in manufacturing fields such as aerospace. This study aims to investigate the effects of different processing parameters on the micro-hole processing of 316 heat-resistant steel using millisecond lasers. Through the control variable method, the study examines the impact of pulse energy, pulse count, and pulse width on the quality of micro-holes, including the entrance diameter, exit diameter, and taper. Furthermore, combined with orthogonal experiments and COMSOL Multiphysics 6.2 simulations, the study explores the influence of pulse width on the formation of blind holes. The experimental results show that when the pulse energy is 2.2 J, the taper is minimal (2.2°), while the taper reaches its peak (2.4°) at 2.4 J pulse energy. As the pulse count increases to 55–60 pulses, the exit diameter stabilizes, and the taper decreases to 1.8°. Blind holes begin to form when the pulse width exceeds 1.2 ms. When the pulse width is 1.2 ms, pulse energy is 2.4 J, and pulse count is 50, the entrance diameter of the blind hole reaches its maximum, indicating that longer pulse widths result in more significant energy reflection and thermal accumulation effects. COMSOL simulations reveal that high-energy pulses cause intense melt ejection, while longer pulse widths exacerbate thermal accumulation at the micro-hole entrance, leading to blind hole formation. This study provides important process references for laser processing of through-holes and blind holes in heat-resistant steel. Full article

Due to the complex spatial structure, dense tree distribution, and narrow passages in orchard environments, traditional path planning algorithms often struggle with large path deviations, frequent turning, and reduced navigational safety. In order to overcome these challenges, this paper proposes a hybrid path planning algorithm based on improved D* Lite for narrow forest orchard environments. The proposed approach enhances path feasibility and improves the robustness of the navigation system. The algorithm begins by constructing a 2D grid map reflecting the orchard layout and inflates the tree regions to create safety buffers for reliable path planning. For global path planning, an enhanced D* Lite algorithm is used with a cost function that jointly considers centerline proximity, turning angle smoothness, and directional consistency. This guides the path to remain close to the orchard row centerline, improving structural adaptability and path rationality. Narrow passages along the initial path are detected, and local replanning is performed using a Hybrid A* algorithm that accounts for the kinematic constraints of a differential tracked robot. This generates curvature-continuous and directionally stable segments that replace the original narrow-path portions. Finally, a gradient descent method is applied to smooth the overall path, improving trajectory continuity and execution stability. Field experiments in representative orchard environments demonstrate that the proposed hybrid algorithm significantly outperforms traditional D* Lite and KD* Lite-B methods in terms of path accuracy and navigational safety. The average deviation from the centerline is only 0.06 m, representing reductions of 75.55% and 38.27% compared to traditional D* Lite and KD* Lite-B, respectively, thereby enabling high-precision centerline tracking. Moreover, the number of hazardous nodes, defined as path points near obstacles, was reduced to five, marking decreases of 92.86% and 68.75%, respectively, and substantially enhancing navigation safety. These results confirm the method’s strong applicability in complex, constrained orchard environments and its potential as a foundation for efficient, safe, and fully autonomous agricultural robot operation. Full article

Automated cherry harvesting presents a significant opportunity to overcome the high costs and inefficiencies of manual labor in modern agriculture. However, robotic harvesting in dense canopies requires sophisticated path planning to navigate cluttered branches and selectively pick target fruits. This paper introduces a complete robotic harvesting solution centered on a novel path-planning algorithm: the Multi-Strategy Integrated RRT for Continuous Harvesting Path (MSI-RRTCHP) algorithm. Our system first employs a machine vision system to identify and locate mature cherries, distinguishing them from unripe fruits, leaves, and branches, which are treated as obstacles. Based on this visual data, the MSI-RRTCHP algorithm generates an optimal picking trajectory. Its core innovation is a synergistic strategy that enables intelligent navigation by combining probability-guided exploration, goal-oriented sampling, and adaptive step size adjustments based on the obstacle’s density. To optimize the picking sequence for multiple targets, we introduce an enhanced traversal algorithm ($\sigma$-TSP) that accounts for obstacle interference. Field experiments demonstrate that our integrated system achieved a 90% picking success rate. Compared with established algorithms, the MSI-RRTCHP algorithm reduced the path length by up to 25.47% and the planning time by up to 39.06%. This work provides a practical and efficient framework for robotic cherry harvesting, showcasing a significant step toward intelligent agricultural automation. Full article

To enhance road-testing safety for autonomous driving robotic vehicles (ADRVs), collision avoidance with sudden obstacles is essential during testing processes. This paper proposes an upper-level collision avoidance strategy integrating model predictive control (MPC) and improved artificial potential field (APF). The kinematic model of the driving robot is established, and a vehicle dynamics model considering road curvature is used as the foundation for vehicle control. The improved APF constraints are constructed. The boundary constraint uses a three-circle vehicle shape suitable for roads with arbitrary curvatures. A unified obstacle potential field constraint is designed for static/dynamic obstacles to generate collision-free trajectories. An auxiliary attractive potential field is designed to ensure stable trajectory recovery after obstacle avoidance completion. A multi-objective MPC framework coupled with artificial potential fields is designed to achieve obstacle avoidance and trajectory tracking while ensuring accuracy, comfort, and environmental constraints. Results from Carsim-Simulink and semi-physical experiments validate that the proposed strategy effectively avoids various obstacles under different road conditions while maintaining reference trajectory tracking. Full article

Improving outdoor thermal comfort is a critical objective in urban design, particularly in densely built urban environments. Elevated semi-open spaces—outdoor areas located beneath raised building structures—have been recognized for enhancing pedestrian comfort by improving airflow and shading. However, previous studies primarily focused on warm or temperate climates, leaving a significant research gap regarding their thermal performance in cold climate zones characterized by extreme seasonal variations. Specifically, few studies have investigated how these spaces perform under conditions typical of northern Chinese cities like Xi’an, which is explicitly classified within the Cold Climate Zone according to China’s national standard GB 50176-2016 and experiences both severe summer heat and cold winter conditions. To address this gap, we conducted field measurements and numerical simulations using the ENVI-met model (v5.0) to systematically evaluate the microclimatic performance of elevated ground-floor spaces in Xi’an. Key microclimatic parameters—including air temperature, mean radiant temperature, relative humidity, and wind velocity—were assessed during representative summer and winter conditions. Our findings indicate that the height of the elevated structure significantly affects outdoor thermal comfort, identifying an optimal elevated height range of 3.6–4.3 m to effectively balance summer cooling and winter sheltering needs. These results provide valuable design guidance for architects and planners aiming to enhance outdoor thermal environments in cold climate regions facing distinct seasonal extremes. Full article

In the field of interferometric fiber-optic sensing, the phase-shifting technique is well known as a highly efficient method for retrieving the phase signal from the interference light intensity. The rectangular-pulse binary phase modulation (RPBPM) method is a typical phase-shifting method with the advantages of high efficiency, low complexity, and easy array multiplexing. Exploring the impact of the parameters on the performance is of great significance for guiding its application in practical systems. In this study, the influence of the sampling interval and modulation depth deviation involved in the method is analyzed in detail. Through a comparative simulation analysis with the traditional heterodyne and phase-generated carrier methods, the superiority of the RPBPM method is effectively validated. Meanwhile, an improved method based on the ellipse fitting of the Lissajous figure is proposed to compensate for the error and improve the signal-to-noise-and-distortion ratio (SINAD) from 26.3 dB to 37.1 dB in a specific experiment. Finally, the experimental results guided by the above method show excellent performance in a practical vibration system. Full article

Omnidirectional mobile robots have gained extensive application across diverse fields due to their exceptional maneuverability and adaptability in confined spaces. However, structural and systemic uncertainties significantly compromise motion accuracy. To enhance motion control precision, this paper proposes a sliding mode control (SMC) method integrated with a radial basis function (RBF) neural network. The approach aggregates model uncertainties, nonlinear dynamics, and unknown disturbances into a composite disturbance term. An RBF neural network is employed to approximate this disturbance, with compensation embedded within the SMC framework. An online adaptive law for neural network optimization is derived using the Lyapunov stability theorem, thereby improving the disturbance rejection capability. Comparative simulations and experiments validate the proposed method against modern control strategies. Results demonstrate superior tracking performance and robustness, significantly enhancing trajectory tracking accuracy for the MY3 wheeled omnidirectional mobile robot. Full article

In modern agriculture, tractors play a crucial role in powering tools and implements. Proper operation of agricultural tractors in mechanized field operations can support sustainable agriculture and reduce emissions of pollutants such as carbon dioxide (CO₂). This has been a recurring concern associated with agricultural intensification for food production. This study aimed to evaluate the optimization of tractor gears and engine speed during crop operations to minimize CO₂ emissions and promote sustainability. The experiment was conducted using a strip plot design with subdivided sections and six replications, following a double factorial structure. The first factor evaluated was the type of agricultural implement (disc harrow, subsoiler, or sprayer), while the second factor was the engine speed setting (nominal or reduced). Operational and energy performance metrics were analyzed, including fuel consumption and CO₂ emissions, travel speed, effective working time, wheel slippage, and working depth. Optimized gear selection and engine speeds resulted in a 20 to 40% reduction in fuel consumption and CO₂ emissions. However, other evaluated parameters remain unaffected by the reduced engine speed, regardless of the implement used, ensuring the operation’s quality. Thus, optimizing operator training or configuring machines allows for environmental impact reduction, making agricultural practices more sustainable. Full article

This research advances the integration of terrestrial laser scanning (TLS) in heritage documentation, targeting the development of holistic and practical guidance for practitioners to adopt the technology effectively. Acknowledging the pivotal role of TLS in capturing detailed and accurate representations of cultural heritage, the study emerges against a backdrop of technological progression and the evolving needs of heritage conservation. Through a comprehensive literature review, critical case studies of heritage sites in the U.S., expert interviews, and the development of a TLS for Heritage Documentation Best Practice Guide (the guide), the paper addresses the existing gaps in streamlined practices in the domain of TLS’s applications in heritage documentation. While recognizing and building upon foundational efforts such as international guidelines developed over the past decades, this study contributes a practice-oriented perspective grounded in field experience and case-based analysis. The developed guide seeks to equip practitioners with structured methods and practical tools to optimize the use of TLS, ultimately enhancing the quality and accessibility of heritage documentation. It also sets a foundation for integrating TLS datasets with other technologies, such as Building Information Modeling (BIM), virtual reality (VR), and augmented reality (AR) for heritage preservation, tourism, education, and interpretation, ultimately enhancing access to and engagement with cultural heritage sites. The paper also critically situates this guidance within the evolving theoretical discourse on digital heritage practices, highlighting its alignment with and divergence from existing methodologies. Full article

Graph anomaly detection aims at identifying rare, unusual entities in attributed networks with respect to their patterns or structures that deviate significantly from the majority within a graph. Over the years, extensive efforts in this field have been dedicated to the powerful capability of attributed networks to model real-world systems. Given the scarcity of labeled anomalies, current research primarily emphasizes model design via unsupervised learning. Graph autoencoders have been widely utilized for such purposes, leveraging the outstanding capabilities of Graph Neural Networks to model graph structured data. However, most existing graph autoencoder-based anomaly detectors do not exploit the nodes’ local subgraph information, limiting their ability to comprehensively understand the network for better representation learning. Moreover, these methods place greater emphasis on the attribute reconstruction process while neglecting the structure reconstruction aspect. This paper proposes an enhanced graph autoencoder framework for graph anomaly detection tasks that incorporates a subgraph extraction and aggregation preprocessing stage to utilize the nodes’ local topological information for enhanced embedding generation and to induce an additional node–subgraph view through model learning. A graph structure learning-based decoder is introduced as the structure decoder for better relationship learning. Finally, during the anomaly scoring stage, a node neighborhood selection technique is applied to enhance the detection performance. The effectiveness of the proposed framework is demonstrated through comprehensive experiments conducted on six commonly used real-world datasets. Full article

Straw removal is a method used to reduce cadmium (Cd) concentration in contaminated farmland. Experiments in Hunan Province tested different stubble heights (0, 15, 30, 45 cm) in three Cd-polluted paddy fields with different contamination levels. The results showed that lower stubble heights resulted in larger straw biomass and more Cd removed from the field, while the residual biomass and Cd returned to the field decreased accordingly. At stubble heights of 0, 15, 30, and 45 cm, the removed straw biomass accounted for 100%, 69.19%, 48.84%, and 28.17% of the total straw biomass, respectively. The corresponding Cd removal amounts were 12.89, 7.18, 4.18, and 1.83 g ha⁻¹, which constituted 100%, 54.06%, 29.85%, and 12.54% of the total Cd accumulation in straw for the season, respectively. According to the fitted curve, the biomass of returned and removed straw was equal at a stubble height of 31 cm, while at 23 cm, the Cd return and removal amounts were balanced. Rice varieties Huanghuazhan and Nongxiang 42 had better Cd removal but risked grain Cd exceeding limits. Since Cd concentration in straw determines removal efficiency, varieties with high straw Cd accumulation and low grain Cd are more suitable for remediation, rather than high-Cd-accumulating types. Full article

Object detection in remote sensing imagery is critical in environmental monitoring, urban planning, and land resource management. However, the task remains challenging due to significant scale variations, arbitrary object orientations, and complex background clutter. To address these issues, we propose a novel orientation module (SOAM Block) that jointly models object scale and directional features while exploiting geometric symmetry inherent in many remote sensing targets. The SOAM Block is constructed upon a lightweight and efficient Adaptive Multi-Scale (AMS) Module, which utilizes a symmetric arrangement of parallel depth-wise convolutional branches with varied kernel sizes to extract fine-grained multi-scale features without dilation, thereby preserving local context and enhancing scale adaptability. In addition, a Strip-based Context Attention (SCA) mechanism is introduced to model long-range spatial dependencies, leveraging horizontal and vertical 1D strip convolutions in a directionally symmetric fashion. This design captures spatial correlations between distant regions and reinforces semantic consistency in cluttered scenes. Importantly, this work is the first to explicitly analyze the coupling between object scale and orientation in remote sensing imagery. The proposed method addresses the limitations of fixed receptive fields in capturing symmetric directional cues of large-scale objects. Extensive experiments are conducted on two widely used benchmarks—DOTA and HRSC2016—both of which exhibit significant scale variations and orientation diversity. Results demonstrate that our approach achieves superior detection accuracy with fewer parameters and lower computational overhead compared to state-of-the-art methods. The proposed SOAM Block thus offers a robust, scalable, and symmetry-aware solution for high-precision object detection in complex aerial scenes. Full article