Search Results (41)

This paper presents an effective method for generating blending meshes by leveraging geodesic curves on triangular meshes. Depending on whether the input meshes intersect, the blending regions are automatically initialized using either minimum-distance points or intersection curves, while allowing users to intuitively adjust boundary curves directly on the mesh. Each blending region is parameterized via geodesic linear interpolation, and a reparameterization strategy is employed to establish optimal correspondences between boundary curves, ensuring smooth, twist-free connections. The resulting blending mesh is merged with the input meshes through subdivision, trimming, and co-refinement along the boundaries. The proposed method is applicable to both intersecting and non-intersecting meshes and offers flexible control over the shape and curvature of the blending region through various user-defined parameters, such as boundary radius, scaling factor, and blending function parameters. Experimental results demonstrate that the method produces stable and smooth transitions even for complex geometries, highlighting its robustness and practical applicability in diverse domains including digital fabrication, mechanical design, and 3D object modeling. Full article

Automated violence detection in images presents a technical and scientific challenge that demands specialized methods to enhance classification systems. This study introduces an approach for automatically identifying relevant samples to improve the performance of neural network models, specifically DenseNet121, with a focus on violence classification in images. The proposed methodology begins with an initial training phase using a balanced dataset (DS1, 6000 images). Based on the model’s output scores ($ou{t}_N$), three confidence levels are defined: Safe ($ou{t}_N\ge 0.9+\sigma$ or $ou{t}_N\le 0.1-\sigma$), Border ($0.5-\sigma \le ou{t}_N\le 0.5+\sigma$), and Average ($0.4-\sigma \le ou{t}_N\le 0.6+\sigma$). These levels correspond to scenarios with low, moderate, and high prediction error probabilities, respectively, where $\sigma$ is an adjustable threshold. The Border subset exhibits symmetry around the decision boundary ($ou{t}_N=0.5$), capturing maximally uncertain samples, while the Safe regions reflect functional asymmetries in high-confidence predictions. Subsequently, these thresholds are applied to a second dataset (DS2, 5600 images) to extract specialized subsets for retraining ($D{S}_{Safe}$, $D{S}_{Border}$, and $D{S}_{Average}$). Finally, the model is evaluated using an independent test set ($D{S}_{test}$, 4400 images), ensuring complete data isolation. The experimental results demonstrate that the confidence-based subsets offer competitive performance despite using significantly fewer samples. The Average subset achieved an F1-Score of 0.89 and a g-mean of 0.93 using only 20% of the data, making it a promising alternative for efficient training. These findings highlight that strategic sample selection based on confidence thresholds enables effective training with reduced data, offering a practical balance between performance and efficiency when symmetric uncertainty modeling is exploited. Full article

In real-world visual recognition tasks, long-tailed distribution is a pervasive challenge, where the extreme class imbalance severely limits the representation learning capability of deep models. Although supervised learning has demonstrated certain potential in long-tailed visual recognition, these models’ gradient updates dominated by head classes often lead to insufficient representation of tail classes, resulting in ambiguous decision boundaries. While existing Supervised Contrastive Learning variants mitigate class bias through instance-level similarity comparison, they are still limited by biased negative sample selection and insufficient modeling of the feature space structure. To address this, we propose Rebalancing Supervised Contrastive Learning (Reb-SupCon), which constructs a balanced and discriminative feature space during model training to alleviate performance deviation. Our method consists of two key components: (1) a dynamic rebalancing factor that automatically adjusts sample contributions through differentiable weighting, thereby establishing class-balanced feature representations; (2) a prototype-aware enhancement module that further improves feature discriminability by explicitly constraining the geometric structure of the feature space through introduced feature prototypes, enabling locally discriminative feature reconstruction. This breaks through the limitations of conventional instance contrastive learning and helps the model to identify more reasonable decision boundaries. Experimental results show that this method demonstrates superior performance on mainstream long-tailed benchmark datasets, with ablation studies and feature visualizations validating the modules’ synergistic effects. Full article

Pneumothorax is a critical condition that requires rapid and accurate diagnosis from standard chest radiographs. Identifying and segmenting the location of the pneumothorax are essential for developing an effective treatment plan. nnUNet is a self-configuring, deep learning-based framework for medical image segmentation. Despite adjusting its parameters automatically through data-driven optimization strategies and offering robust feature extraction and segmentation capabilities across diverse datasets, our initial experiments revealed that nnUNet alone struggled to achieve consistently accurate segmentation for pneumothorax, particularly in challenging scenarios where subtle intensity variations and anatomical noise obscure the target regions. This study aims to enhance the accuracy and robustness of pneumothorax segmentation in low-contrast chest radiographs by integrating spatial prior information and attention mechanism into the nnUNet framework. In this study, we introduce the spatial prior contrast adapter (SPCA)-enhanced nnUNet by implementing two modules. First, we integrate an SPCA utilizing the MedSAM foundation model to incorporate spatial prior information of the lung region, effectively guiding the segmentation network to focus on anatomically relevant areas. In the meantime, a probabilistic atlas, which shows the probability of an area prone to pneumothorax, is generated based on the ground truth masks. Both the lung segmentation results and the probabilistic atlas are used as attention maps in nnUNet. Second, we combine the two attention maps as additional input into nnUNet and integrate an attention mechanism into standard nnUNet by using a convolutional block attention module (CBAM). We validate our method by experimenting on the dataset CANDID-PTX, a benchmark dataset representing 19,237 chest radiographs. By introducing spatial awareness and intensity adjustments, the model reduces false positives and improves the precision of boundary delineations, ultimately overcoming many of the limitations associated with low-contrast radiographs. Compared with standard nnUNet, SPCA-enhanced nnUNet achieves an average Dice coefficient of 0.81, which indicates an improvement of standard nnUNet by 15%. This study provides a novel approach toward enhancing the segmentation performance of pneumothorax with low contrast in chest X-ray radiographs. Full article

The flatness of the cut surface in enoki mushrooms (Flammulina filiformis Z.W. Ge, X.B. Liu & Zhu L. Yang) is a key factor in quality classification. However, conventional automatic cutting equipment struggles with deformation issues due to its inability to adjust the grasping force based on individual mushroom sizes. To address this, we propose an improved method that integrates visual feedback to dynamically adjust the execution end, enhancing cut precision. Our approach enhances YOLOv8n-seg with Star Net, SPPECAN (a reconstructed SPPF with efficient channel attention), and C2fDStar (C2f with Star Net and deformable convolution) to improve feature extraction while reducing computational complexity and feature loss. Additionally, we introduce a mask ownership judgment and merging optimization algorithm to correct positional offsets, internal disconnections, and boundary instabilities in grasping area predictions. Based on this, we optimize grasping parameters using an improved centroid-based region width measurement and establish a region width-to-PWM mapping model for the precise conversion from visual data to gripper control. Experiments in real-situation settings demonstrate the effectiveness of our method, achieving a mean average precision (mAP50:95) of 0.743 for grasping area segmentation, a 4.5% improvement over YOLOv8, with an average detection speed of 10.3 ms and a target width measurement error of only 0.14%. The proposed mapping relationship enables adaptive end-effector control, resulting in a 96% grasping success rate and a 98% qualified cutting surface rate. These results confirm the feasibility of our approach and provide a strong technical foundation for the intelligent automation of enoki mushroom cutting systems. Full article

Accurate and efficient tomato detection is one of the key techniques for intelligent automatic picking in the area of precision agriculture. However, under the facility scenario, existing detection algorithms still have challenging problems such as weak feature extraction ability for occlusion conditions and different fruit sizes, low accuracy on edge location, and heavy model parameters. To address these problems, this paper proposed D³-YOLOv10, a lightweight YOLOv10-based detection framework. Initially, a compact dynamic faster network (DyFasterNet) was developed, where multiple adaptive convolution kernels are aggregated to extract local effective features for fruit size adaption. Additionally, the deformable large kernel attention mechanism (D-LKA) was designed for the terminal phase of the neck network by adaptively adjusting the receptive field to focus on irregular tomato deformations and occlusions. Then, to further improve detection boundary accuracy and convergence, a dynamic FM-WIoU regression loss with a scaling factor was proposed. Finally, a knowledge distillation scheme using semantic frequency prompts was developed to optimize the model for lightweight deployment in practical applications. We evaluated the proposed framework using a self-made tomato dataset and designed a two-stage category balancing method based on diffusion models to address the sample class-imbalanced issue. The experimental results demonstrated that the D³-YOLOv10 model achieved an $mA{P}_{0.5}$ of 91.8%, with a substantial reduction of 54.0% in parameters and 64.9% in FLOPs, compared to the benchmark model. Meanwhile, the detection speed of 80.1 FPS more effectively meets the demand for real-time tomato detection. This study can effectively contribute to the advancement of smart agriculture research on the detection of fruit targets. Full article

The automatic and accurate segmentation of bladder tumors is a key step in assisting urologists in diagnosis and analysis. At present, existing Transformer-based methods have limited ability to restore local detail features and insufficient boundary segmentation capabilities. We propose FEBE-Net, which aims to effectively capture global and remote semantic features, preserve more local detail information, and provide clearer and more precise boundaries. Specifically, first, we use PVT v2 backbone to learn multi-scale global feature representations to adapt to changes in bladder tumor size and shape. Secondly, we propose a new feature exploration attention module (FEA) to fully explore the potential local detail information in the shallow features extracted by the PVT v2 backbone, eliminate noise, and supplement the missing fine-grained details for subsequent decoding stages. At the same time, we propose a new boundary enhancement and refinement module (BER), which generates high-quality boundary clues through boundary detection operators to help the decoder more effectively preserve the boundary features of bladder tumors and refine and adjust the final predicted feature map. Then, we propose a new efficient self-attention calibration decoder module (ESCD), which, with the help of boundary clues provided by the BER module, gradually and effectively recovers global contextual information and local detail information from high-level features after calibration enhancement and low-level features after exploration attention. Extensive experiments on the cystoscopy dataset BtAMU and five colonoscopy datasets have shown that FEBE-Net outperforms 11 state-of-the-art (SOTA) networks in segmentation performance, with higher accuracy, stronger robust stability, and generalization ability. Full article

The Microwave Radiation Imager (MWRI) onboard the FengYun satellite plays a crucial role in global change monitoring and numerical weather prediction. Estimating and correcting geolocation errors are important to retrieving accurate geophysical variables. However, the instantaneous field of view (IFOV) inter-channel deviation, which is mainly caused by the structure mounting error and measurement error of feedhorns, is less studied. In this present study, we constructed a general theoretical model to automatically estimate the IFOV inter-channel deviations suitable for conical-scanning instruments. The model can automatically detect the along-track and across-track vectors that pass through the land–sea boundary points and are perpendicular to the actual coastlines. Regarding the midpoints of the vectors as the brightness temperature (Tb) inflection points, the IFOV inter-channel deviation is the pixel offset or distance of the maximum gradients of the Tb near the inflection points for each channel relative to the 89-GHz V-pol channel. We tested the model’s operational performance using the FY-3G/MWRI-Rainfall Mission (MWRI-RM) observations. Considering that parameter uploading adjusted the IFOV inter-channel deviations, the model’s validity was verified by comparing the adjustments calculated by the model with the theoretical changes caused by parameter uploading. The result shows that the differences between them for all window channels are less than 100 m, indicating the model’s effectiveness in evaluating the IFOV inter-channel deviation for the MWRI-RM. Furthermore, the estimated on-orbit IFOV inter-channel deviations for the MWRI-RM show that all channel deviations are less than 1 km, meeting the instrument’s design requirement of 2 km. We believe this study will provide a foundation for IFOV inter-channel registration of passive microwave payloads and spatial matching of multiple payloads. Full article

Accurately obtaining the geological characteristic digital model of a coal seam and surrounding rock in front of a fully mechanized mining face is one of the key technologies for automatic and continuous coal mining operation to realize an intelligent unmanned working face. The research on how to establish accurate and reliable coal seam digital models is a hot topic and technical bottleneck in the field of intelligent coal mining. This paper puts forward a construction method and dynamic update mechanism for a digital model of coal seam autonomous cutting by a coal mining machine, and verifies its effectiveness in experiments. Based on the interpolation model of drilling data, a fine coal seam digital model was established according to the results of geological statistical inversion, which overcomes the shortcomings of an insufficient lateral resolution of lithology and physical properties in a traditional geological model and can accurately depict the distribution trend of coal seams. By utilizing the numerical derivation of surrounding rock mining and geological SLAM advanced exploration, the coal seam digital model was modified to achieve a dynamic updating and optimization of the model, providing an accurate geological information guarantee for intelligent unmanned coal mining. Based on the model, it is possible to obtain the boundary and inclination information of the coal seam profile, and provide strategies for adjusting the height of the coal mining machine drum at the current position, achieving precise control of the automatic height adjustment of the coal mining machine. Full article

Water is the basis for human survival and growth, and it holds great importance for ecological and environmental protection. The Hindu Kush Himalaya (HKH) is known as the “Water Tower of Asia”, where water influences changes in the global water cycle and ecosystem. It is thus very important to efficiently measure the status of water in this region and to monitor its changes; with the development of satellite-borne sensors, water surface extraction based on remote sensing images has become an important method through which to do so, and one of the most advanced and accurate methods for water surface extraction involves the use of deep learning networks. We designed a network based on the state-of-the-art Vision Transformer to automatically extract the water surface in the HKH region; however, in this region, terrain shadows are often misclassified as water surfaces during extraction due to their spectral similarity. Therefore, we adjusted the training dataset in different ways to improve the accuracy of water surface extraction and explored whether these methods help to reduce the interference of terrain shadows. Our experimental results show that, based on the designed network, adding terrain shadow samples can significantly enhance the accuracy of water surface extraction in high mountainous areas, such as the HKH region, while adding terrain data does not reduce the interference from terrain shadows. We obtained the water surface extraction results in the HKH region in 2021, with the network and training datasets containing both water surface and terrain shadows. By comparing these results with the data products of Global Surface Water, it was shown that our water surface extraction results are highly accurate and the extracted water surface boundaries are finer, which strongly confirmed the applicability and advantages of the proposed water surface extraction approach in a wide range of complex surface environments. Full article

In the process of coal mining, one of the main reasons for the high labor intensity of workers and the frequent occurrence of casualties is the low level of intelligence of coal mining equipment. As the core equipment in the process of coal mining, the intelligence level of shearers directly affects the safety production and mining efficiency of coal mines. Coal and rock recognition technology is the core technology used to realize the intelligentization of shearers, which is an urgent technical problem to be solved in the field of coal mining. In this paper, coal seam images, rock stratum images, and coal–rock mixed-layer images of a coal mining area are taken as the research object, and key technologies such as the construction of a sample image library, classification and recognition, and semantic segmentation are studied by using the relevant theoretical knowledge of artificial neural network models. Firstly, the BP neural network is used to classify and identify coal seam images, rock stratum images, and coal–rock mixed-layer images, so as to distinguish which of the current mining targets of a shearer is the coal seam, rock stratum, or coal–rock mixed layer. Because different mining objectives will lead to different working modes of a shearer, it is necessary to maintain normal power to cut coal when encountering a coal seam, to stop working when encountering rock stratum, and to cut coal along the boundary between a coal seam and rock stratum when encountering a coal–rock mixed stratum. Secondly, the DeepLabv3+ model is used to perform semantic segmentation experiments on the coal–rock mixed-layer images. The purpose is to find out the distribution of coal and rocks in the coal–rock mixed layer in the coal mining area, so as to provide technical support for the automatic adjustment height of the shearer. Finally, the research in this paper achieved a 97.16% recognition rate in the classification and recognition experiment of the coal seam images, rock stratum images, and coal–rock mixed-layer images and a 91.2% accuracy in the semantic segmentation experiment of the coal–rock mixed-layer images. The research results of the two experiments provide key technical support for improving the intelligence level of shearers. Full article

Accurate surface water mapping is crucial for rationalizing water resource utilization and maintaining ecosystem sustainability. However, the diverse shapes and scales of water bodies pose challenges in automatically extracting them from remote sensing images. Existing methods suffer from inaccurate lake boundary extraction, inconsistent results, and failure to detect small rivers. In this study, we propose a dual-stream parallel feature aggregation network to address these limitations. Our network effectively combines global information interaction from the Swin Transformer network with deep local information integration from Convolutional Neural Networks (CNNs). Moreover, we introduce a deformable convolution-based attention mechanism module (D-CBAM) that adaptively adjusts receptive field size and shape, highlights important channels in feature maps automatically, and enhances the expressive ability of our network. Additionally, we incorporate a Feature Pyramid Attention (FPA) module during the advanced coding stage for multi-scale feature learning to improve segmentation accuracy for small water bodies. To verify the effectiveness of our method, we chose the Yellow River Basin in China as the research area and used Sentinel-2 and Sentinel-1 satellite images as well as manually labelling samples to construct a dataset. On this dataset, our method achieves a 93.7% F1 score, which is a significant improvement compared with other methods. Finally, we use the proposed method to map the seasonal and permanent water bodies in the Yellow River Basin in 2021 and compare it with existing water bodies. The results show that our method has certain advantages in mapping large-scale water bodies, which not only ensures the overall integrity but also retains local details. Full article

Unattended intelligent cargo handling is an important means to improve the efficiency and safety of port cargo trans-shipment, where high-precision carton detection is an unquestioned prerequisite. Therefore, this paper introduces an adaptive image augmentation method for high-precision carton detection. First, the imaging parameters of the images are clustered into various scenarios, and the imaging parameters and perspectives are adaptively adjusted to achieve the automatic augmenting and balancing of the carton dataset in each scenario, which reduces the interference of the scenarios on the carton detection precision. Then, the carton boundary features are extracted and stochastically sampled to synthesize new images, thus enhancing the detection performance of the trained model for dense cargo boundaries. Moreover, the weight function of the hyperparameters of the trained model is constructed to achieve their preferential crossover during genetic evolution to ensure the training efficiency of the augmented dataset. Finally, an intelligent cargo handling platform is developed and field experiments are conducted. The outcomes of the experiments reveal that the method attains a detection precision of 0.828. This technique significantly enhances the detection precision by 18.1% and 4.4% when compared to the baseline and other methods, which provides a reliable guarantee for intelligent cargo handling processes. Full article

Moistube irrigation is an efficient method that accurately irrigates and fertilizes agricultural crops. Investigation into the mechanisms of infiltration behaviors under an adjusted working head (WKH) benefits a timely and artificially regulating moisture condition within root zones, as adapted to evapotranspiration. This study explores the laws of Moistube irrigated soil water movement under constant and adjusted working heads. Lysimeter experiments were conducted to measure Moistube irrigation cumulative infiltration, infiltration rate, and to observe wetting front area and water content distribution using digital image processing and time domain reflectometry, respectively. Treatments of constant heads (0, 1, and 2 m), increasing heads (0 to 1, 0 to 2 and 1 to 2 m) and deceasing heads (1 to 0, 2 to 0 and 2 to 1 m) were designed. The results show that (1) under constant heads, the cumulative infiltration increases linearly over time. The infiltration rate and cumulative infiltration are positively correlated with the pressure head. When WKH is increased or decreased, the infiltration rate and cumulative infiltration curves significantly change, followed by a gradual stabilization. The more the head is increased or decreased, the more evident this tendency will be. (2) When WKH is increased, the wetting front migration rate and the wetted soil moisture content marked increase; when WKH is decreased, the wetting front migration rate sharply decelerates, and the water content of the wetted soil slowly grows. They both tend to equilibrium with time. (3) By regarding the same cumulative infiltration of increased WKH and constant WKH treatments as a similar initial condition, we proposed a cumulative infiltration empirical model for Moistube irrigation under variable working head. Additionally, we treat the Moistube as a clayey porous medium and construct a HYDRUS-2D numerical model to predict the infiltration behaviors under variable WKH. The validity of the two models were well proven, with MRE and NRMSE close to 0 and NSE greater than 0.867, indicating good agreements with the experimental results. This model breaks through the limitation of constant boundary of traditional numerical model and applies variable head boundary to the boundary of the Moistube pipe, which can also effectively simulate the response mechanism of Moistube irrigation to variable WKH. The research results further confirmed the feasibility of manually adjusting the WKH to regulate the discharge of the Moistube pipe and soil moisture state. Based on the HYDRUS-2D numerical model simulation results and the root distribution and water demand of typical facility crops, the selection range of placement depth and the adjustable range of WKH of Moistube irrigation were proposed. The research results provide a theoretical reference for manual adjustment or automatic control of Moistube irrigation WKH to adapt to real-time crop water demand in agricultural production. Full article

Ascertaining the positions of geological boundaries serves as a cornerstone in the characterization of shale reservoirs. Existing methods heavily rely on labor-intensive manual well-to-well correlation, while automated techniques often suffer from limited efficiency and consistency due to their reliance on single well log data. To overcome these limitations, an innovative approach, termed DRAG, is introduced, which uses deep belief forest (DBF), principal component analysis (PCA), and an enhanced generative adversarial network (GAN) for automatic layering recognition in logging curves. The approach employed in this study involves the use of PCA for dimensionality reduction across multiple well log datasets, coupled with a sophisticated GAN to generate representative samples. The DBF algorithm is then applied for stratification, incorporating a confidence screening mechanism to improve computational efficiency. In order to improve both accuracy and stability, a coordinate system is introduced that adjusts for stratification variations among neighboring wells around the target well. Experimental comparisons demonstrate the superior performance of the proposed algorithm in reducing stratification fluctuations and improving precision. Full article