Resolution Of Features Research Articles

A small object detection method with context information for high altitude images

Detection of small objects stands as a pivotal and difficult task because of their low resolution and lack of visualization features. Though achieving some promising results, recent detection methods utilize the context information insufficiently, leading to inadequate small object feature representation and increasing the misdetection and omission rates. We propose a method named Context Information Enhancement YOLO(CIE-YOLO) for small object detection. CIE-YOLO mainly includes a Context Reinforcement Module(CRM), a Channel Spatial Joint Attention(CSJA) module, and a Pixel Feature Enhancement Module(PFEM). The CRM module extracts and enhances the context information to mitigate the confusion between small objects and the background in the network. Then CSJA suppresses the background noise to highlight important small object features. Finally, PFEM reduces the small object feature losses in up-sampling via feature enhancement and pixel resolution enhancement. The effectiveness of the proposed CIE-YOLO in small object detection is demonstrated by extensive experiments.

Manufacturing Feature Recognition With a Sparse Voxel-Based Convolutional Neural Network

Abstract Automated manufacturing feature recognition is a crucial link between computer-aided design and manufacturing, facilitating process selection and other downstream tasks in computer-aided process planning. While various methods such as graph-based, rule-based, and neural networks have been proposed for automatic feature recognition, they suffer from poor scalability or computational inefficiency. Recently, voxel-based convolutional neural networks have shown promise in solving these challenges but incur a tradeoff between computational cost and feature resolution. This paper investigates a computationally efficient sparse voxel-based convolutional neural network for manufacturing feature recognition, specifically, an octree-based sparse voxel convolutional neural network. This model is trained on a large-scale manufacturing feature dataset, and its performance is compared to a voxel-based feature recognition model (FeatureNet). The results indicate that the octree-based model yields higher feature recognition accuracy (99.5% on the test dataset) with 44% lower graphics processing unit (GPU) memory consumption than a voxel-based model of comparable resolution. In addition, increasing the resolution of the octree-based model enables recognition of finer manufacturing features. These results indicate that a sparse voxel-based convolutional neural network is a computationally efficient deep learning model for manufacturing feature recognition to enable process planning automation. Moreover, the sparse voxel-based neural network demonstrated comparable performance to a boundary representation-based feature recognition neural network, achieving similar accuracy in single-feature recognition without having access to the exact 3D shape descriptors.

PJ-YOLO: Prior-Knowledge and Joint-Feature-Extraction Based YOLO for Infrared Ship Detection

Infrared ship images have low resolution and limited recognizable features, especially for small targets, leading to low accuracy and poor generalization of traditional detection methods. To address this, we design a prior knowledge auxiliary loss for leveraging the unique brightness distribution of infrared ship images, we construct a joint feature extraction module that sufficiently captures context awareness, channel differentiation, and global information, and then we propose a prior-knowledge- and joint-feature-extraction-based YOLO (PJ-YOLO) for use in detecting infrared ships. Additionally, a residual deformable attention module is designed to integrate multi-scale information, enhancing detail capture. Experimental results on the SFISD and InfiRray Ships datasets demonstrate that the proposed PJ-YOLO achieves state-of-the-art detection performance for infrared ship targets. In particular, PJ-YOLO achieves improvements of 1.6%, 5.0%, and 2.8% in mAP50, mAP75, and mAP50:95 on the SFISD dataset, respectively.

AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net.

The task of nucleus segmentation plays an important role in medical image analysis. However, due to the challenge of detecting small targets and complex boundaries in datasets, traditional methods often fail to achieve satisfactory results. Therefore, a novel nucleus segmentation method based on the U-Net architecture is proposed to overcome this issue. Firstly, we introduce a Weighted Feature Enhancement Unit (WFEU) in the encoder decoder fusion stage of U-Net. By assigning learnable weights to different feature maps, the network can adaptively enhance key features and suppress irrelevant or secondary features, thus maintaining high-precision segmentation performance in complex backgrounds. In addition, to further improve the performance of the network under different resolution features, we designed a Double-Stage Channel Optimization Module (DSCOM) in the first two layers of the model. This DSCOM effectively preserves high-resolution information and improves the segmentation accuracy of small targets and boundary regions through multi-level convolution operations and channel optimization. Finally, we proposed an Adaptive Fusion Loss Module (AFLM) that effectively balances different lossy targets by dynamically adjusting weights, thereby further improving the model's performance in segmentation region consistency and boundary accuracy while maintaining classification accuracy. The experimental results on 2018 Data Science Bowl demonstrate that, compared to state-of-the-art segmentation models, our method shows significant advantages in multiple key metrics. Specifically, our model achieved an IOU score of 0.8660 and a Dice score of 0.9216, with a model parameter size of only 7.81 M. These results illustrate that the method proposed in this paper not only excels in the segmentation of complex shapes and small targets but also significantly enhances overall performance at lower computational costs. This research offers new insights and references for model design in future medical image segmentation tasks.

Enhancing Model Accuracy of UAV-Based Biomass Estimation by Evaluating Effects of Image Resolution and Texture Feature Extraction Strategy

Enhancing Model Accuracy of UAV-Based Biomass Estimation by Evaluating Effects of Image Resolution and Texture Feature Extraction Strategy

Intuitionistic Fuzzy Set Guided Fast Fusion Transformer for Multi-Polarized Petrographic Image of Rock Thin Sections

The fusion of multi-polarized petrographic images of rock thin sections involves the fusion of feature information from microscopic images of rock thin sections illuminated under both plane-polarized and orthogonal-polarized light. During the fusion process of rock thin section images, the inherent high resolution and abundant feature information of the images pose substantial challenges in terms of computational complexity when dealing with massive datasets. In engineering applications, to ensure the quality of image fusion while meeting the practical requirements for high-speed processing, this paper proposes a novel fast fusion Transformer. The model leverages a soft matching algorithm based on intuitionistic fuzzy sets to merge redundant tokens, effectively mitigating the negative effects of asymmetric dependencies between tokens. The newly generated artificial tokens serve as brokers for the Query (Q), forming a novel lightweight fusion strategy. Both subjective visual observations and quantitative analyses demonstrate that the Transformer proposed in this paper is comparable to existing fusion methods in terms of performance while achieving a notable enhancement in its inference efficiency. This is made possible by the attention paradigm, which is equivalent to a generalized form of linear attention, and the newly designed loss function. The model has been experimented on with multiple datasets of different rock types and has exhibited robust generalization capabilities. It provides potential for future research in diverse geological conditions and broader application scenarios.

Multipath Projection Stereolithography for Three-Dimensional Printing Microfluidic Devices.

Although many lab-on-chip applications require inch-sized devices with microscale feature resolution, achieving this via current 3D printing methods remains challenging due to inherent trade-offs between print resolution, design complexity, and build sizes. Inspired by microscopes that can switch objectives to achieve multiscale imaging, we report a new optical printer coined multipath projection stereolithography (MPS) specifically designed for printing microfluidic devices. MPS is designed to switch between high-resolution (1× mode, ∼10 μm) and low-resolution (3× mode, ∼30 μm) optical paths to generate centimeter-sized constructs (3 × 6 cm) with a feature resolution of ∼10 μm. Illumination and projection systems were designed, resin formulations were optimized, and slicing software was integrated with hardware with the goal of ease of use. Using a test case of micromixers, we show that user-defined CAD models can be directly input to an automated slicing software to define printing of low-resolution features via the 3× mode with embedded microscale fins via 1× mode. A new computational model, validated using experimental results, was used to simulate various fin designs, and experiments were conducted to verify simulated mixing efficiencies. New 3D out-of-plane micromixer designs were simulated and tested. To show broad applications of MPS, multichambered chips and microfluidic devices with microtraps were also printed. Overall, MPS can be a new fabrication tool to rapidly print a range of lab-on-chip applications.

Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI.

AI-based breast cancer detection can improve the sensitivity and specificity of detection, especially for small lesions, which has clinical value in realizing early detection and treatment so as to reduce mortality. The two-stage detection network performs well; however, it adopts an imprecise ROI during classification, which can easily include surrounding tumor tissues. Additionally, fuzzy noise is a significant contributor to false positives. We adopted Faster RCNN as the architecture, introduced ROI aligning to minimize quantization errors and feature pyramid network (FPN) to extract different resolution features, added a bounding box quadratic regression feature map extraction network and three convolutional layers to reduce interference from tumor surrounding information, and extracted more accurate and deeper feature maps. Our approach outperformed Faster R-CNN, Mask R-CNN, and YOLOv9 in breast cancer detection across 485 internal cases. We achieved superior performance in mAP, sensitivity, and false positive rate ((0.752, 0.950, 0.133) vs. (0.711, 0.950, 0.200) vs. (0.718, 0.880, 0.120) vs. (0.658, 0.680, 405)), which represents a 38.5% reduction in false positives compared to manual detection. Additionally, in a public dataset of 220 cases, our model also demonstrated the best performance. It showed improved sensitivity and specificity, effectively assisting doctors in diagnosing cancer.

InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding.

Multi-task scene understanding aims to design models that can simultaneously predict several scene understanding tasks with one versatile model. Previous studies typically process multi-task features in a more local way, and thus cannot effectively learn spatially global and cross-task interactions, which hampers the models' ability to fully leverage the consistency of various tasks in multi-task learning. To tackle this problem, we propose an Inverted Pyramid multi-task Transformer, capable of modeling cross-task interaction among spatial features of different tasks in a global context. Specifically, we first utilize a transformer encoder to capture task-generic features for all tasks. And then, we design a transformer decoder to establish spatial and cross-task interaction globally, and a novel UP-Transformer block is devised to increase the resolutions of multi-task features gradually and establish cross-task interaction at different scales. Furthermore, two types of Cross-Scale Self-Attention modules, i.e., Fusion Attention and Selective Attention, are proposed to efficiently facilitate cross-task interaction across different feature scales. An Encoder Feature Aggregation strategy is further introduced to better model multi-scale information in the decoder. Comprehensive experiments on several 2D/3D multi-task benchmarks clearly demonstrate our proposal's effectiveness, establishing significant state-of-the-art performances.

The impact of cluster resolution feature selection on pattern recognition and classification for detecting Sudan dye adulteration in palm oil

The impact of cluster resolution feature selection on pattern recognition and classification for detecting Sudan dye adulteration in palm oil

Human key point detection method based on enhanced receptive field and transformer

The existing key point detection network models have complex structures, so it is difficult to deploy on edge devices. Meanwhile, the convolution is localized and limited by the size of convolution kernels, which cannot effectively capture long-range dependencies. To address this problem, this paper introduces a lightweight Convolutional Transformer network (LHFormer Net) for human pose estimation. Considering that the sampling area of convolution kernels for different dimensional feature maps is fixed and the contextual information is singular, the enhanced receptive field block is designed to extract richer feature information and reduce information loss in feature maps. Based on the global modeling features of Transformer encoder, convolutional position encoding and multi-head self-attention are used to capture the spatial constraint relationship between key points in the deep feature extraction. Finally, a lightweight deconvolution module is used to generate higher resolution features to achieve multi-resolution supervision, which can effectively solve the problem of scale variation in pose estimation, more accurately locate key points of small and medium-sized people, ad further improve the detection accuracy of the network. Compared with other networks, the experimental results on the open access datasets COCO2017 and MPII show that the proposed network achieves a good balance between model complexity and detection performance.

An Optimization Method for PCB Surface Defect Detection Model Based on Measurement of Defect Characteristics and Backbone Network Feature Information.

Printed Circuit Boards (PCBs) are essential components in electronic devices, making defect detection crucial. PCB surface defects are diverse, complex, low in feature resolution, and often resemble the background, leading to detection challenges. This paper proposes the YOLOv8_DSM algorithm for PCB surface defect detection, optimized based on the three major characteristics of defect targets and feature map visualization. First, to address the complexity and variety of defect shapes, we introduce CSPLayer_2DCNv3, which incorporates deformable convolution into the backbone network. This enhances adaptive defect feature extraction, effectively capturing diverse defect characteristics. Second, to handle low feature resolution and background resemblance, we design a Shallow-layer Low-semantic Feature Fusion Module (SLFFM). By visualizing the last four downsampling convolution layers of the YOLOv8 backbone, we incorporate feature information from the second downsampling layer into SLFFM. We apply feature map separation-based SPDConv for downsampling, providing PAN-FPN with rich, fine-grained shallow-layer features. Additionally, SLFFM employs the bi-level routing attention (BRA) mechanism as a feature aggregation module, mitigating defect-background similarity issues. Lastly, MPDIoU is used as the bounding box loss regression function, improving training efficiency by enhancing convergence speed and accuracy. Experimental results show that YOLOv8_DSM achieves a mAP (0.5:0.9) of 63.4%, representing a 5.14% improvement over the original model. The model's Frames Per Second (FPS) reaches 144.6. To meet practical engineering requirements, the designed PCB defect detection model is deployed in a PCB quality inspection system on a PC platform.

Mitigation of Stress Corrosion Cracking in Additively Manufactured Stainless Steel by Laser Shock Peening

Abstract Use of laser powder bed fusion (LPBF) stainless steel in corrosive environments is attractive due to material's high corrosion resistance and fine feature resolution, which is advantageous for fluidic applications. For this implementation to be optimized, LPBF stainless steel parts must have reduced susceptibility to stress corrosion cracking (SCC), a failure mode that is of high risk for stainless steels. Laser shock peening (LSP) surface processing has been used to improve SCC resistance in wrought metals and has also been used to improve other material properties of additively manufactured metals. However, LSP has yet to be investigated for the improvement of SCC behavior in LPBF stainless steel. This article demonstrates that not only does LSP improve time to crack initiation of LPBF 316L stainless steel in SCC testing but also improves SCC behavior differently when applied to different surfaces of the build. To explain these results, residual stress, texture, dislocation distribution, hardness, microstructure, and fracture surfaces are investigated, linking different hydrogen embrittlement mechanisms to each of the two build orientations as well as the peened and un-peened conditions. These results are supported by matching the observed crack morphologies to those simulated with dynamic crack modeling, thereby demonstrating the impact of residual stress and plastic versus brittle failure upon the observed outcome.

Vibrational State-Resolved Differential Cross Sections of the F + CH4 → HF + CH3 Reaction at the Collision Energies of 3.1-13.8 kcal/mol.

We report a high-resolution crossed molecular beam experiment investigating the reaction dynamics of the F + CH4 → HF + CH3 reaction across a broad range of collision energies (3.1-13.8 kcal/mol). By using time-sliced velocity map imaging within the crossed molecular beam apparatus, we obtain correlated angular distributions and branching ratios for various product pairs (CH3(ν), HF(ν')). The resolved reactive rainbow-like features that display a distinct bulge in the angular distribution in different channels reveal the formation of vibrationally ground and excited states of the methyl radical accompanied by different rovibrationally excited HF products. These findings suggest distinct reaction dynamics for channels leading to vibrationally excited methyl radicals compared to those forming ground-state methyl radicals.

Evaluation of Antivenom Therapy for Middle East Scorpion Envenomations.

Scorpion envenomation is a leading cause of envenomation in our region. Antivenom has been used successfully to treat the systemic manifestations of envenomations inflicted by toxic scorpions. Toxic scorpions common in our area include Leiurus quinquestriatus, Androctonus australis, and Buthus occitanus. This study describes the outcomes of children envenomated by these scorpions, and treated with SCORPIFAV, a polyvalent scorpion antivenom F(ab')2 (equine), used since 2016 at our institution. A retrospective chart review of all children admitted with symptoms and signs of scorpion envenomation to Soroka University Medical Center, between September 1, 2019, and December 1, 2020, who received antivenom SCORPIFAV. Our center has a protocol mandating antivenom therapy for all patients manifesting autonomic excitation, agitation, and anxiety, or more pronounced symptoms, following suspected scorpion envenomation. Three hundred patients were seen in the pediatric emergency department for scorpion envenomation during the study period, and 49 required antivenom (SCORPIFAV) as per departmental policy. Four of 49 developed allergic reactions during antivenom treatment: 2 manifested minor skin rashes treated with antihistamines only, and a further 2 required intramuscular adrenaline. There were no deaths in the study cohort and all patients recovered fully, with complete resolution of symptoms, signs, and laboratory features. Patients treated with antivenom exhibited rapid resolution of symptoms without severe hypersensitivity. We recommend broadened availability of antivenom at sites where it is needed.

Adaptive Granularity-Fused Keypoint Detection for 6D Pose Estimation of Space Targets

Estimating the 6D pose of a space target is an intricate task due to factors such as occlusions, changes in visual appearance, and background clutter. Accurate pose determination requires robust algorithms capable of handling these complexities while maintaining reliability under various environmental conditions. Conventional pose estimation for space targets unfolds in two stages: establishing 2D–3D correspondences using keypoint detection networks and 3D models, followed by pose estimation via the perspective-n-point algorithm. The accuracy of this process hinges critically on the initial keypoint detection, which is currently limited by predominantly singular-scale detection techniques and fails to exploit sufficient information. To tackle the aforementioned challenges, we propose an adaptive dual-stream aggregation network (ADSAN), which enables the learning of finer local representations and the acquisition of abundant spatial and semantic information by merging features from both inter-layer and intra-layer perspectives through a multi-grained approach, consolidating features within individual layers and amplifying the interaction of distinct resolution features between layers. Furthermore, our ADSAN implements the selective keypoint focus module (SKFM) algorithm to alleviate problems caused by partial occlusions and viewpoint alterations. This mechanism places greater emphasis on the most challenging keypoints, ensuring the network prioritizes and optimizes its learning around these critical points. Benefiting from the finer and more robust information of space objects extracted by the ADSAN and SKFM, our method surpasses the SOTA method PoET (5.8°, 8.1°/0.0351%, 0.0744%) by 0.5°, 0.9°, and 0.0084%, 0.0354%, achieving 5.3°, 7.2° in rotation angle errors and 0.0267%, 0.0390% in normalized translation errors on the Speed and SwissCube datasets, respectively.

Hematopoietic Stem Cell Transplantation for C1q Deficiency: A Study on Behalf of the EBMT Inborn Errors Working Party

C1q deficiency is a rare inborn error of immunity characterized by increased susceptibility to infections and autoimmune manifestations mimicking SLE, with an associated morbidity and mortality. Because C1q is synthesized by monocytes, to date, four patients treated with allogeneic HSCT have been reported, with a positive outcome in three. We conducted an international retrospective study to assess the outcome of HSCT in C1q deficiency. Eighteen patients, fourteen previously unreported, from eleven referral centres, were included. Two patients had two HSCTs, thus 20 HSCTs were performed in total, at a median age of 10 years (range 0.9—19). Indications for HSCT were autoimmune manifestations not controlled by ongoing treatment in seventeen, and early development of MALT lymphoma in one patient. Overall survival (OS) was 71% and event-free survival was 59% at two years (considering an event as acute GvHD ≥ grade III, disease recurrence and death). In eleven patients HSCT led to resolution of autoimmune features and discontinuation of immunosuppressive treatments (follow-up time range 3–84 months). Five patients died due to transplant-related complications. Patients with a severe autoimmune phenotype, defined as neurological and/or renal involvement, had the worst OS (40% vs 84%; p = 0.034). Reviewing data of 69 genetically confirmed C1q deficient patients, we found that anti-Ro antibodies are associated with neurologic involvement, and anti-RNP and anti-DNA antibodies with renal involvement. In conclusion, HSCT may be a valid curative option for C1q deficiency, but careful selection of patients, with an accurate assessment of risk and benefit, is mandatory.

Uncertainty-driven dynamic ensemble framework for rotating machinery fault diagnosis under time-varying working conditions

Multi-scale ensemble learning combines different scales of feature resolution, thereby improving fault diagnostic accuracy. However, the effectiveness of different information scales in characterizing fault features under time-varying speed conditions varies with speed. It is difficult for existing ensemble strategies to ensure the effectiveness of feature information when ensemble multi-scale feature information is involved. Accordingly, we propose an uncertainty-driven dynamic ensemble Bayesian convolutional neural network (DEBCNN) framework. The uncertainty of the results of different scale models was used to dynamically determine their weights in the ensemble framework, which reduced the influence of irrelevant features on the diagnostic results. By employing the proposed dynamic ensemble strategy, the ensemble framework can utilize fault feature information corresponding to different rotational speeds in the final diagnostic results. Experiments on motor and bearing datasets illustrate the superiority of this strategy over other techniques. This study provides useful insights for further research in the field of fault diagnosis of rotating machinery at time-varying speeds.

Development of printable bacterial nanocellulose bioinks for bioprinting applications

This research has developed a printable bioink formulated with bacterial nanocellulose (BNC) and sodium alginate. The bioink composition offers a unique combination of printability, mechanical strength, and high BNC content. A low-cost 3D bioprinting platform, with in-situ crosslinking capabilities, was designed and fabricated to facilitate the creation of complex constructs. Rheological analysis revealed shear-thinning behaviour, a critical property for efficient 3D bioprinting. The printed constructs exhibited exceptional resolution, printability, and self-supporting features at BNC loadings up to 72 wt.% in dried structures. The optimal ink composition was found, containing 7.8 wt.% BNC and 3 wt.% sodium alginate. These findings highlight the potential for this BNC-alginate bioink for bio-fabrication applications demanding both printability and high biomaterial content.Graphical

Image-Based Auto-Focus Microscope System with Visual Servo Control for Micro-Stereolithography.

Micro-stereolithography (μSL) is an advanced additive manufacturing technique that enables the fabrication of highly precise microstructures with fine feature resolution. One of the primary challenges in μSL is achieving and maintaining precise focus throughout the fabrication process. For the successful application of μSL, it is essential to maintain the sample surface within a focal depth of several microns. Despite the growing interest in auto-focus devices, limited attention has been directed towards auto-focus systems in image-based auto-focus microscope systems for precision μSL. To address this challenge, we propose an image-based auto-focus microscope system incorporating visual servo control. In the optical design, a transflective beam splitter is employed, allowing the laser beam to pass through for fabrication while reflecting the focused beam on the sample surface to the microscope and camera. Utilizing captured spot images and the Foucault knife-edge test, a deep learning-based laser spot image processing algorithm is developed to determine the focus position based on spot size and the number of spot pixels on both sides. Experimental results demonstrate that the proposed auto-focus system effectively determines the relative position of the focal point using the laser spot image and achieves auto-focusing through visual servo control.