Search Results (458)

This paper presents the study of integrating a deep motion model into simple online and real-time tracking for video multi-object tracking. The tracking-by-detection paradigm faces significant challenges in handling nonlinear motion and occlusions. Although conventional Kalman-filter-based methods such as the SORT are efficient, they suffer from error accumulation because of their linear motion assumption. We propose KalmanFormer, a novel framework that enhances Kalman-filter-based tracking through adaptive motion modeling for video sequences. KalmanFormer consists of three key components. First, the inner-trajectory motion corrector, built upon the transformer architecture, refines Kalman filter predictions by learning nonlinear residuals from historical trajectories, thereby improving adaptability to complex motion patterns in videos. Second, the cross-trajectory attention module captures interobject motion correlations, significantly boosting object association under occlusions. Third, a pseudo-observation generator is integrated to provide neural-based predictions when detections are missing, stabilizing the Kalman filter update process. To validate our approach, we conduct comprehensive evaluations on the video benchmarks DanceTrack, MOT17, and MOT20 to demonstrate its effectiveness in handling complex motion and occlusion. The experimental results on the DanceTrack, MOT17, and MOT20 benchmarks demonstrate that KalmanFormer achieves competitive performance, with HOTA scores of 66.6 on MOT17 and 63.2 on MOT20, and strong identity preservation, IDF1: 82.0% and 80.1%, respectively. Full article

This study explores how the integration of generative artificial intelligence, multi-objective evolutionary optimization, and reinforcement learning can enable sustainable and cost-effective decision-making in supply chain strategy. Using real-world retail demand data enriched with synthetic sustainability attributes, we trained a Variational Autoencoder (VAE) to generate plausible future demand scenarios. These were used to seed a Non-Dominated Sorting Genetic Algorithm (NSGA-II) aimed at identifying Pareto-optimal sourcing strategies that balance delivery cost and CO₂ emissions. The resulting Pareto frontier revealed favorable trade-offs, enabling up to 50% emission reductions for only a 10–15% cost increase. We further deployed a deep Q-learning (DQN) agent to dynamically manage weekly shipments under a selected balanced strategy. The reinforcement learning policy achieved an additional 10% emission reduction by adaptively switching between green and conventional transport modes in response to demand and carbon pricing. Importantly, the agent also demonstrated resilience during simulated supply disruptions by rerouting decisions in real time. This research contributes a novel AI-based decision architecture that combines generative modeling, evolutionary search, and adaptive control to support sustainability in complex and uncertain supply chains. Full article

Ports with Mediterranean-like traffic profiles combine dense passenger, cargo, touristic, and local operations in confined waters where many small craft sail without AIS, increasing collision risk. Nature of such traffic in often unpredictable, due to often and sudden course corrections or changes. In such situations, it is possible that larger ships cannot manoeuvre to avoid collisions with small vessels. Hence, it is important to the port authority to develop a fast and adoptable mean to reduce collision risks. We present an end-to-end shore-based framework that detects and tracks vessels from fixed cameras (YOLOv9 + DeepSORT), estimates speed from monocular lateral video with an artificial neural network (ANN), and visualises collision risk in augmented reality (AR) for VTS/port operators. Validation in the Port of Split using laser rangefinder/GPS ground truth yields MAE 1.98 km/h and RMSE 2.18 km/h (0.605 m/s), with relative errors 2.83–21.97% across vessel classes. We discuss limitations (sample size, weather), failure modes, and deployment pathways. The application uses stationary port camera as an input. The core calculations are performed at user’s computer in the building. Mobile application uses wireless communication to show risk assessment at augmented reality smart phone. For training of ANN, we used The Split Port Ship Classification Dataset. Full article

The development of gravity flow sedimentology has improved our understanding of the physical properties of different types of gravity flow deposits, especially the advancement of various gravity flow models. Although studies of gravity flows have developed greatly, the linkage between different sub-facies and their reservoir properties is hindered by a lack of detailed sedimentary records. Here, integrated test data (including thin-section petrology, high-pressure mercury injection experiments, capillary pressure curve analysis, and scanning electron microscopy) are used to evaluate links between different types of gravity flows and their reservoir properties from the Late Triassic–Early Jurassic Anyao Formation, southeastern Paleo-Ordos Basin, China. The petrological and sedimentological data reveal two types of deep-water gravity flow deposits comprising sandy debris flow (SDF) and turbidity current (TC) deposits. Both are fine-grained lithic sandstones and form low-porosity and ultra-low permeability reservoirs. Secondary porosity, formed by the dissolution of framework grains, including feldspars and lithic fragments, dominates the pore types. This secondary porosity is widely developed in the Anyao Formation and formed by reaction with organic acids during burial (early mesodiagenesis). The associated mud rocks have reached the early mature stage of the oil window with Tmax of 442–448 °C. Compared with the turbidites, the sandy debris flows have higher framework grain content (87.9 vs. 84.8%), framework grain size (0.091 vs. 0.008 mm), porosity (6.97 vs. 3.44%), pore throat radius (0.102 vs. 0.025 μm), and permeability (0.025 vs. 0.005 mD) but are relatively poor in the sorting of framework grains and pore throat radii. The most important petrological factors affecting porosity and permeability of the SDF reservoirs are framework grain size and feldspar grain content, respectively, but those of the TC reservoirs are feldspar grain content and the maximum pore throat radius. Diagenetic dissolution of framework grains is the most important porosity-affecting factor for both SDF and TC reservoirs. Our multi-proxy study provides new insights into the links between gravity flow sub-facies and reservoir properties in the lacustrine deep-water environment. Full article

The Kolmogorov–Arnold network (KAN) is a regression model that is based on a representation of an arbitrary continuous multivariate function by a composition of functions of a single variable. Experimentally obtained datasets for regression models typically include uncertainties, which in some cases, cannot be neglected. The conventional way to account for the latter is to model confidence intervals of the systems’ outputs in addition to the expected values of the outputs. However, such information may be insufficient, and in some cases, researchers aim to obtain probability distributions of the outputs. The present paper proposes a method for estimating probability distributions of the outputs by constructing an ensemble of models. The suggested approach covers input-dependent probability distributions of the outputs and is capable of capturing the multi-modality, as well as the variation of the distribution type with the inputs. Although the method is applicable to any regression model, the present paper combines it with KANs, since their specific structure leads to the construction of computationally efficient models. The source codes are available online. Full article

The popularity of keeping ornamental fish has grown increasingly, as their vibrant presence can provide a calming influence. Accurately assessing the health of ornamental fish is important but challenging. For this, researchers have focused on developing fish tracking methods that provide trajectories for health assessment. However, issues such as mirror images, occlusion, and motion prediction errors can significantly reduce the accuracy of existing algorithms. To address these problems, we propose a novel ornamental fish tracking method based on deep learning techniques. We first utilize the You Only Look Once (YOLO) v5 deep convolutional neural network algorithm with Distance Intersection over Union–Non Maximum Suppression (DIoU-NMS) to handle occlusion problems. We then design an object removal algorithm to eliminate fish mirror image coordinates. Finally, we adopt an improved DeepSORT algorithm, replacing the original Kalman Filter with an advanced Noise Scale Adaptive (NSA) Kalman Filter to enhance tracking accuracy. In our experiment, we evaluated our method in three simulated real-world fish tank environments, comparing it with the YOLOv5 and YOLOv7 methods. The results show that our method can increase Multiple Object Tracking Accuracy (MOTA) by up to 13.3%, Higher Order Tracking Accuracy (HOTA) by up to 10.0%, and Identification F1 Score by up to 14.5%. These findings confirm that our object removal algorithm effectively improves Multiple Object Tracking Accuracy, which facilitates early disease detection, reduces mortality, and mitigates economic losses—an important consideration given many owners’ limited ability to recognize common diseases. Full article

Bruising in ‘Korla’ pears represents a prevalent phenomenon that leads to progressive fruit decay and substantial economic losses. The detection of early-stage bruising proves challenging due to the absence of visible external characteristics, and existing deep learning models have limitations in weak feature extraction under complex optical interference. To address the postharvest latent damage detection challenges in ‘Korla’ pears, this study proposes a collaborative detection framework integrating structured-illumination reflectance imaging (SIRI) with multi-order gated attention mechanisms. Initially, an SIRI optical system was constructed, employing 150 cycles·m⁻¹ spatial frequency modulation and a three-phase demodulation algorithm to extract subtle interference signal variations, thereby generating RT (Relative Transmission) images with significantly enhanced contrast in subsurface damage regions. To improve the detection accuracy of latent damage areas, the MOGA-UNet model was developed with three key innovations: 1. Integrate the lightweight VGG16 encoder structure into the feature extraction network to improve computational efficiency while retaining details. 2. Add a multi-order gated aggregation module at the end of the encoder to realize the fusion of features at different scales through a special convolution method. 3. Embed the channel attention mechanism in the decoding stage to dynamically enhance the weight of feature channels related to damage. Experimental results demonstrate that the proposed model achieves 94.38% mean Intersection over Union (mIoU) and 97.02% Dice coefficient on RT images, outperforming the baseline UNet model by 2.80% with superior segmentation accuracy and boundary localization capabilities compared with mainstream models. This approach provides an efficient and reliable technical solution for intelligent postharvest agricultural product sorting. Full article

Plastic debris is a pervasive and persistent threat to marine ecosystems. Microplastics (plastics < 5 mm) are increasing in a variety of marine habitats, including open water systems, shorelines, and benthic sediments. It remains unclear how microplastics distribute and accumulate in marine systems and the extent to which this pollutant is accessible to marine taxa. We examined subtidal benthic sediments and beach sediments in critical nearshore habitats for forage fish species—Pacific sand lance (Ammodytes personatus), Pacific herring (Clupea pallasi), and surf smelt (Hypomesus pretiosus)—to quantify microplastic concentrations in the spawning and deep-water habitats of these fish and better understand how microplastics accumulate and distribute in nearshore systems. In the San Juan Islands, we examined an offshore subtidal bedform in a high-flow channel and beach sites of protected and exposed shorelines. We also examined 12 beach sites proximate to urban areas in Puget Sound. Microplastics were found in all samples and at all sample sites. Microfibers were the most abundant, and flakes were present proximate to major shipyards and marinas. Microplastics were significantly elevated in Puget Sound compared to the San Juan Archipelago. Protected beaches had elevated concentrations relative to exposed beaches and subtidal sediments. Microplastics were in higher concentrations in sand and fine-grain sediments, poorly sorted sediments, and artificial sediments. Microplastics were also elevated at sites confirmed as spawning habitats for forage fish. The model results indicate that both current speed and proximate urban populations influence nearshore microplastic concentrations. Our research provides new insights into how microplastics are distributed, deposited, and retained in marine sediments and shorelines, as well as insight into potential exposure in benthic, demersal, and shoreline habitats. Further analyses are required to examine the relative influence of urban populations and shipping lanes and the effects of physical processes such as wave exposure, tidal currents, and shoreline geometry. Full article

Channeling in cementing causes interlayer interference, severely restricting oilfield recovery. Existing channeling plugging agents, such as cement and gels, often lead to reservoir damage or insufficient strength. Oil-soluble resin (OSR) particles show great potential in selective plugging of channeling fractures due to their excellent oil solubility, temperature/salt resistance, and high strength. However, their application is limited by the efficient filling and retention in deep fractures. This study innovatively combines the OSR particle plugging system with the mature rapid filtration loss plugging mechanism in drilling, systematically exploring the influence of particle size and sorting on their filtration, packing behavior, and plugging performance in channeling fractures. Through API filtration tests, visual fracture models, and high-temperature/high-pressure (100 °C, salinity 3.0 × 10⁵ mg/L) core flow experiments, it was found that well-sorted large particles preferentially bridge in fractures to form a high-porosity filter cake, enabling rapid water filtration from the resin plugging agent. This promotes efficient accumulation of OSR particles to form a long filter cake slug with a water content <20% while minimizing the invasion of fine particles into matrix pores. The slug thermally coalesces and solidifies into an integral body at reservoir temperature, achieving a plugging strength of 5–6 MPa for fractures. In contrast, poorly sorted particles or undersized particles form filter cakes with low porosity, resulting in slow water filtration, high water content (>50%) in the filter cake, insufficient fracture filling, and significantly reduced plugging strength (<1 MPa). Finally, a double-slug strategy is adopted: small-sized OSR for temporary plugging of the oil layer injection face combined with well-sorted large-sized OSR for main plugging of channeling fractures. This strategy achieves fluid diversion under low injection pressure (0.9 MPa), effectively protects reservoir permeability (recovery rate > 95% after backflow), and establishes high-strength selective plugging. This study clarifies the core role of particle size and sorting in regulating the OSR plugging effect based on rapid filtration loss, providing key insights for developing low-damage, high-performance channeling plugging agents and scientific gradation of particle-based plugging agents. Full article

Driven by the rapid development of e-commerce and intelligent logistics, the volume of express delivery services has surged, making the efficient and accurate identification of shipping information a core requirement for automatic sorting systems. However, traditional Optical Character Recognition (OCR) technology struggles to meet the accuracy and real-time demands of complex logistics scenarios due to challenges such as image distortion, uneven illumination, and field overlap. This paper proposes a three-level collaborative recognition method based on deep learning that facilitates structured information extraction through regional normalization, dual-path parallel extraction, and a dynamic matching mechanism. First, the geometric distortion associated with contour detection and the lightweight direction classification model has been improved. Second, by integrating the enhanced YOLOv5s for key area localization with the upgraded PaddleOCR for full-text character extraction, a dual-path parallel architecture for positioning and recognition has been constructed. Finally, a dynamic space–semantic joint matching module has been designed that incorporates anti-offset IoU metrics and hierarchical semantic regularization constraints, thereby enhancing matching robustness through density-adaptive weight adjustment. Experimental results indicate that the accuracy of this method on a self-constructed dataset is 89.5%, with an F1 score of 90.1%, representing a 24.2% improvement over traditional OCR methods. The dynamic matching mechanism elevates the average accuracy of YOLOv5s from 78.5% to 89.7%, surpassing the Faster R-CNN benchmark model while maintaining a real-time processing efficiency of 76 FPS. This study offers a lightweight and highly robust solution for the efficient extraction of order information in complex logistics scenarios, significantly advancing the intelligent upgrading of sorting systems. Full article

As an important pillar of the global economic system, the cotton industry faces critical challenges from non-fibrous impurities (e.g., leaves and debris) during processing, which severely degrade product quality, inflate costs, and reduce efficiency. Traditional detection methods suffer from insufficient accuracy and low efficiency, failing to meet practical production needs. While deep learning models excel in general object detection, their massive parameter counts render them ill-suited for real-time industrial applications. To address these issues, this study proposes Cotton-YOLO, an optimized yolov8 model. By leveraging principles of symmetry in model design and system setup, the study integrates the CBAM attention module—with its inherent dual-path (channel-spatial) symmetry—to enhance feature capture for tiny impurities and mitigate insufficient focus on key areas. The C2f_DSConv module, exploiting functional equivalence via quantization and shift operations, reduces model complexity by 12% (to 2.71 million parameters) without sacrificing accuracy. Considering angle and shape variations in complex scenarios, the loss function is upgraded to Wise-IoU for more accurate boundary box regression. Experimental results show that Cotton-YOLO achieves 86.5% precision, 80.7% recall, 89.6% mAP50, 50.1% mAP50–95, and 50.51 fps detection speed, representing a 3.5% speed increase over the original yolov8. This work demonstrates the effective application of symmetry concepts (in algorithmic structure and performance balance) to create a model that balances lightweight design and high efficiency, providing a practical solution for industrial impurity detection and key technical support for automated cotton sorting systems. Full article

Traditional collision risk warning methods primarily focus on vehicle-to-vehicle collisions, neglecting conflicts between vehicles and vulnerable road users (VRUs) such as pedestrians, while the difficulty in predicting pedestrian trajectories further limits the accuracy of collision warnings. To address this problem, this study proposes a vehicle-to-everything-based (V2X) multi-fusion vehicle–pedestrian collision warning method, aiming to enhance the traffic safety protection for VRUs. First, Unmanned Aerial Vehicle aerial imagery combined with the YOLOv7 and DeepSort algorithms is utilized to achieve target detection and tracking at unsignalized intersections, thereby constructing a vehicle–pedestrian interaction trajectory dataset. Subsequently, key foundational modules for collision warning are developed, including the vehicle trajectory module, the pedestrian trajectory module, and the risk detection module. The vehicle trajectory module is based on a kinematic model, while the pedestrian trajectory module adopts an Attention-based Social GAN (AS-GAN) model that integrates a generative adversarial network with a soft attention mechanism, enhancing prediction accuracy through a dual-discriminator strategy involving adversarial loss and displacement loss. The risk detection module applies an elliptical buffer zone algorithm to perform dynamic spatial collision determination. Finally, a collision warning framework based on the Monte Carlo (MC) method is developed. Multiple sampled pedestrian trajectories are generated by applying Gaussian perturbations to the predicted mean trajectory and combined with vehicle trajectories and collision determination results to identify potential collision targets. Furthermore, the driver perception–braking time (TTM) is incorporated to estimate the joint collision probability and assist in warning decision-making. Simulation results show that the proposed warning method achieves an accuracy of 94.5% at unsignalized intersections, outperforming traditional Time-to-Collision (TTC) and braking distance models, and effectively reducing missed and false warnings, thereby improving pedestrian traffic safety at unsignalized intersections. Full article

Stylolites are ubiquitous diagenetic products in carbonate rocks. They play a significant role in enhancing or reducing fluid flow in subsurface reservoirs. This study unravels the relationship between stylolite networks, carbonate microfacies, and the elemental geochemistry of Upper Cretaceous limestones of the Kometan Formation (shallow to moderately deep marine) in Northern Iraq. Stylolites exhibit diverse morphologies across mud- and grain-supported limestone facies. Statistical analyses of stylolite spacing, wavelength, amplitude, and their intersections and connectivity indicate that grain size, sorting, and mineral composition are key parameters that determine the geometrical properties of the stylolites and stylolite networks. Stylolites typically exhibit weak connectivity and considerable vertical spacing when hosted in packstone facies with moderate grain sorting. Conversely, mud-supported limestones, marked by poor sorting and high textural heterogeneity, host well-developed stylolite networks characterized by high amplitude and frequent intersections, indicating significant dissolution and deformation processes. Stylolites in mud-supported facies are closely spaced and present heightened amplitudes and intensified junctions, with suture and sharp-peak type. This study unveils that stylolites can potentially enhance porosity in the studied formation. Full article

The mushroom Stropharia rugoso-annulata is one of the most popular varieties in the international market because it is highly nutritious and has a delicious flavor. However, grading is still performed manually, leading to inconsistent grading standards and low efficiency. In this study, deep learning and computer vision techniques were used to develop an automated air-blown grading system for classifying this mushroom into three quality grades. The system consisted of a classification module and a grading module. In the classification module, the cap and stalk regions were extracted using the YOLOv8-seg algorithm, then post-processed using OpenCV based on quantitative grading indexes, forming the proposed SegGrade algorithm. In the grading module, an air-blown grading system with an automatic feeding unit was developed in combination with the SegGrade algorithm. The experimental results show that for 150 randomly selected mushrooms, the trained YOLOv8-seg algorithm achieved an accuracy of 99.5% in segmenting the cap and stalk regions, while the SegGrade algorithm achieved an accuracy of 94.67%. Furthermore, the system ultimately achieved an average grading accuracy of 80.66% and maintained the integrity of the mushrooms. This system can be further expanded according to production needs, improving sorting efficiency and meeting market demands. Full article

This study aimed to describe the training leading to the Zwift Academy (ZA) Finals of a world-class road cyclist who earned a professional contract after winning the contest. Four years of daily power meter data were analyzed (male, 25 years old, 68 kg, VO₂max: 85 mL·min⁻¹·kg⁻¹, and 20-min power: 6.37 W·kg⁻¹), focusing on load, volume, intensity, and strategies. Early training alternated between long, moderate-intensity sessions and shorter high-intensity sessions, with easy days in between. Gradually, the structure was progressively modified by increasing the duration of moderate-intensity (MIT) and high-intensity (HIT) and, subsequently, moving them to “high-volume days”, creating a sort of “all-in days” with low-intensity (LIT), MIT, and HIT. Moderate use of indoor training and a few double low-volume, low-intensity sessions were noted. These data provide a deep view of a 4-year preparation period of ZA, providing suggestions for talent identification and training, thereby highlighting the importance of gradual progression in MIT and HIT. Full article