基于Multi-WHFPN与SimAM注意力机制的版面分割

作为OCR的预处理工作,版面分割技术越来越受到学术界和工业界重视。针对版面分割中遇到的检测速度慢、目标区域边界不准确以及细小目标易遗漏等问题,提出了YOLOv7-MSY模型。此模型首先借鉴残差连接思想,提出了Multi-WHFPN网络结构。它采用可训练的权重参数,突出特征融合过程中特征重要性,并添加了小目标检测头,从而提升对小目标的检测性能;其次,引入SimAM注意力机制,可以在不增加额外参数的基础上在3D维度评估特征权重,以增强重要特征,抑制无效特征;最后,使用YEIOU来代替原模型中的定位损失函数,提升了模型的收敛速度与回归精度。在江苏省档案馆提供的数据集上进行实验对比,YOLOv7-MSY对目标区域边界检测更加敏感,对细小目标的检测效果更好。YOLOv7-MSY的mAP@.5达到了0.871,相较于原YOLOv7模型提高了7.84%。该模型的版面分割的效果优于其他类型的版面分割算法,具有良好的泛化性能,并且版面分割速度处于较高水平。

Multi-Atlas Based Methods in Brain MR Image Segmentation

Brain region-of-interesting (ROI) segmentation is an important prerequisite step for many computeraid brain disease analyses.However,the human brain has the complicated anatomical structure.Meanwhile,the brain MR images often suffer from the low intensity contrast around the boundary of ROIs,large inter-subject variance and large inner-subject variance.To address these issues,many multi-atlas based segmentation methods are proposed for brain ROI segmentation in the last decade.In this paper,multi-atlas based methods for brain MR image segmentation were reviewed regarding several registration toolboxes which are widely used in the multi-atlas methods,conventional methods for label fusion,datasets that have been used for evaluating the multiatlas methods,as well as the applications of multi-atlas based segmentation in clinical researches.We propose that incorporating the anatomical prior into the end-to-end deep learning architectures for brain ROI segmentation is an important direction in the future.

Multi-segment and Multi-ply Overlapping Process of Multi Coupled Activities Based on Valid Information Evolution

Complex product development will inevitably face the design planning of the multi-coupled activities, and overlapping these activities could potentially reduce product development time, but there is a risk of the additional cost. Although the downstream task information dependence to the upstream task is already considered in the current researches, but the design process overall iteration caused by the information interdependence between activities is hardly discussed; especially the impact on the design process＇ overall iteration from the valid information accumulation process. Secondly, most studies only focus on the single overlapping process of two activities, rarely take multi-segment and multi-ply overlapping process of multi coupled activities into account; especially the inherent link between product development time and cost which originates from the overlapping process of multi coupled activities. For the purpose of solving the above problems, as to the insufficiency of the accumulated valid information in overlapping process, the function of the valid information evolution （VIE） degree is constructed. Stochastic process theory is used to describe the design information exchange and the valid information accumulation in the overlapping segment, and then the planning models of the single overlapping segment are built. On these bases, by analyzing overlapping processes and overlapping features of multi-coupling activities, multi-segment and multi-ply overlapping planning models are built; by sorting overlapping processes and analyzing the construction of these planning models, two conclusions are obtained： （1） As to multi-segment and multi-ply overlapping of multi coupled activities, the total decrement of the task set development time is the sum of the time decrement caused by basic overlapping segments, and minus the sum of the time increment caused by multiple overlapping segments; （2） the total increment of development cost is the sum of the cost increment caused by all overlapping process. And then, based on overlapping degree analysis of these planning models, by the V1E degree function, the four lemmas theory proofs are represented, and two propositions are finally proved： （1） The multi-ply overlapping of the multi coupled activities will weaken the basic overlapping effect on the development cycle time reduction （2） Overlapping the multi coupled activities will decrease product development cycle, but increase product development cost. And there is trade-off between development time and cost. And so, two methods are given to slacken and eliminate multi-ply overlapping effects. At last, an example about a vehicle upper subsystem design illustrates the application of the proposed models; compared with a sequential execution pattern, the decreasing of development cycle （22%） and the increasing of development cost （3%） show the validity of the method in the example The proposed research not only lays a theoretical foundation for correctly planning complex product development process, but also provides specific and effective operation methods for overlapping multi coupled activities.

Multi-resolution image segmentation based on Gaussian mixture model

Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassification. A new segmentation method, called multi-resolution Ganssian mixture model method, is proposed. First, an image pyramid is constructed and son-father link relationship is built between each level of pyramid. Then the mixture model segmentation method is applied to the top level. The segmentation result on the top level is passed top-down to the bottom level according to the son-father link relationship between levels. The proposed method considers not only local but also global information of image, it overcomes the effect of noise and can obtain better segmentation result. Experimental result demonstrates its effectiveness.

DDoS Defense Algorithm Based on Multi-Segment Timeout Technology

Through the analysis to the DDoS（distributed denial of service） attack, it will conclude that at different time segments, the arrive rate of normal SYN （Synchronization） package are similar, while the abnormal packages are different with the normal ones. Toward this situation a DDoS defense algorithm based on multi-segment timeout technology is presented, more than one timeout segment are set to control the net flow. Experiment results show that in the case of little flow, multi-segment timeout has the ability dynamic defense, so the system performance is improved and the system has high response rate.

A Local Contrast Fusion Based 3D Otsu Algorithm for Multilevel Image Segmentation

To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level thresholding processes. In this paper, to improve the quality of segmented images, a simple and effective multilevel thresholding method is introduced. The proposed approach focuses on preserving edge detail by computing the 3 D Otsu along the fusion phenomena. The advantages of the presented scheme include higher quality outcomes, better preservation of tiny details and boundaries and reduced execution time with rising threshold levels. The fusion approach depends upon the differences between pixel intensity values within a small local space of an image;it aims to improve localized information after the thresholding process. The fusion of images based on local contrast can improve image segmentation performance by minimizing the loss of local contrast, loss of details and gray-level distributions. Results show that the proposed method yields more promising segmentation results when compared to conventional1 D Otsu, 2 D Otsu and 3 D Otsu methods, as evident from the objective and subjective evaluations.

High-power and high optical conversion efficiency diode-end-pumped laser with multi-segmented Nd：YAG/Nd：YVO-4

A novel flat-flat resonator consisting of two crystals（Nd：YAG ＋ Nd：YVO4） is established for power scaling in a diode-end-pumped solid-state laser. We systematically compare laser characteristics between multi-segmented（Nd：YAG ＋ Nd：YVO4） and conventional composite（Nd：YAG ＋ Nd：YAG） crystals to demonstrate the feasibility of spectral line matching for output power scale-up in end-pumped lasers. A maximum continuous-wave output power of 79.2 W is reported at 1064 nm, with Mx2= 4.82, My2= 5.48, and a pumping power of 136 W in the multi-segmented crystals（Nd：YAG ＋ Nd：YVO4）. Compared to conventional composite crystals（Nd：YAG ＋ Nd：YAG）, the optical-optical conversion efficiency of multi-segmented crystals（Nd：YAG ＋ Nd：YVO4） from 808 nm to 1064 nm is enhanced from 30% to 58.8%,while the laser output sensitivity as affected by the diode-laser temperature is reduced from 55% to 9%.

Creation of Multiple Subwavelength Focal Spot Segments Using Phase Modulated Radially Polarized Multi Gaussian Beam

Based on the vector diffraction theory, the effect of complex phase filters on intensity distribution of a radially polarized multi Gaussian beam in the focal region of high NA lens is theoretically investigated. It is observed that a properly designed multi belt complex phase filter can generate subwavelength novel focal patterns including splitting of focal spots and generation of multiple focal spot segments such as eight, six and four focal spots along the optical axis are obtained. We expect that such an investigation is useful for optical manipulation and material processing, multiple high refractive index particle trapping technologies.

Building Detection and Counting in Convoluted Areas Using Multiclass Datasets with Unmanned Aerial Vehicles (UAVs) Imagery

This paper studies the effect of breaking single-class building data into multi-class building data for semantic segmentation under end-to-end architecture such as UNet, UNet++, DeepLabV3, and DeepLabv3+. Although, the already existing semantic segmentation methods for building detection work on the imagery of developed world, where the buildings are highly structured and there is a clearly distinguishable space present between the building instances, the same methods do not work as effectively on the developing world where there is often no clear differentiable spaces between instances of building thus reducing the number of detected instances. Hence as a noble approach, we have added building contours as new class along with building segmentation data, and detected the building contours and the inner building regions, hence giving the precise number of buildings existing in the input imagery especially in the convoluted areas where the boundary between the buildings are often hard to determine even for human eyes. Breaking down the building data into multi-class data increased the building detection precision and recall. This is useful in building detection where building instances are convoluted and are difficult for bare instance segmentation to detect all the instances.

A Semi-Vectorial Hybrid Morphological Segmentation of Multicomponent Images Based on Multithreshold Analysis of Multidimensional Compact Histogram

In this work, we propose an original approach of semi-vectorial hybrid morphological segmentation for multicomponent images or multidimensional data by analyzing compact multidimensional histograms based on different orders. Its principle consists first of segment marginally each component of the multicomponent image into different numbers of classes fixed at K. The segmentation of each component of the image uses a scalar segmentation strategy by histogram analysis;we mainly count the methods by searching for peaks or modes of the histogram and those based on a multi-thresholding of the histogram. It is the latter that we have used in this paper, it relies particularly on the multi-thresholding method of OTSU. Then, in the case where i) each component of the image admits exactly K classes, K vector thresholds are constructed by an optimal pairing of which each component of the vector thresholds are those resulting from the marginal segmentations. In addition, the multidimensional compact histogram of the multicomponent image is computed and the attribute tuples or ‘colors’ of the histogram are ordered relative to the threshold vectors to produce (K + 1) intervals in the partial order giving rise to a segmentation of the multidimensional histogram into K classes. The remaining colors of the histogram are assigned to the closest class relative to their center of gravity. ii) In the contrary case, a vectorial spatial matching between the classes of the scalar components of the image is produced to obtain an over-segmentation, then an interclass fusion is performed to obtain a maximum of K classes. Indeed, the relevance of our segmentation method has been highlighted in relation to other methods, such as K-means, using unsupervised and supervised quantitative segmentation evaluation criteria. So the robustness of our method relatively to noise has been tested.

A Multi-Agent Approach to Arabic Handwritten Text Segmentation

The segmentation of individual words into characters is a vital process in handwritten character recognition systems. In this paper, a novel approach is proposed to segment handwritten Arabic text (words). We consider the “Naskh” font style. The segmentation algorithm employs seven agents in order to detect regions where segmentation is illegal. Feature points (end points) are extracted from the remaining regions of the word-image. Initially, the middle of every two successive end points is considered as a candidate segmentation point based on a set of rules. The experimental results are very promising as we achieved a success rate of 86%.

一种多段机翼水面起降地效无人机气动特性

为改善水面起降性能和气动性能,基于船身式机身、多段机翼和T尾融合设计思路,提出并设计了一种新型仿生式多段机翼地效无人机方案,采用N-S方程和K-Ω-SST湍流模型,详细研究了该型无人机在不同状态下的压力云图、压力系数及升阻特性。仿真结果表明,地效作用随离水高度的增加而减小,离水高度与平均几何弦长之比(高度弦长比H/c)接近1时,地效作用较为显著,无人机在离水高度0.2 m时,升力系数、升阻比分别提升21.91%和40.37%,阻力系数降低15.22%;对提出的多段机翼布局,地效飞行主要影响下表面压力系数和压力云图,下表面压力系数展向上由内向外正压增幅逐渐减小,弦向上前后缘附近压力系数较小,结合压力云图分析,地效对升力增幅的影响主要集中在中段和内段机翼下方区域;地效飞行可明显提高升力线斜率(H/c为1时提高了8.89%),迎角增加时升力系数增幅和阻力系数降幅均逐渐变大,升阻比增幅(H/c为1)在迎角2°后均达到26%以上;通过验证机的多轮水面起降和有、无地效飞行试验,证明设计方案具有优秀的气动性能和飞行性能,可为水质检测、水面地效运输、搜救侦察等提供应用平台。

底部填芯多节段预制拼装空心桥墩抗震性能试验研究

为提高预应力连接预制节段拼装桥墩的抗震性能及施工便捷性,设计了一种底部填芯多节段预制拼装空心桥墩并进行了抗震试验研究。提出了该新型预制节段拼装桥墩填芯高度设计方法,设计了底部填芯预制节段拼装桥墩缩尺模型并开展了拟静力试验测试。基于试验结果分析了该新型桥墩在水平循环往复作用下的裂缝发展过程、失效模式、滞回性能、延性性能、耗能能力及桥墩接缝的开口大小等抗震性能。研究结果表明:所发展的底部填芯多节段预制拼装空心桥墩的失效模式为底部节段混凝土局部压溃,但范围较小,所提填芯高度的设计方法可行,可以使桥墩实现预期失效模式。该新型桥墩具有较小的残余位移、优异的耗能能力与延性性能,这表明此桥墩具有优异的抗震性能。

MCFNet:融合上下文信息的多尺度视网膜动静脉分类网络

针对由于血管类间具有强相似性造成的动静脉错误分类问题,提出了一种新的融合上下文信息的多尺度视网膜动静脉分类网络(multi-scale retinal artery and vein classification network,MCFNet),该网络使用多尺度特征(multi-scale feature,MSF)提取模块及高效的全局上下文信息融合(efficient global contextual information aggregation,EGCA)模块结合U型分割网络进行动静脉分类,抑制了倾向于背景的特征并增强了血管的边缘、交点和末端特征,解决了段内动静脉错误分类问题。此外,在U型网络的解码器部分加入3层深度监督,使浅层信息得到充分训练,避免梯度消失,优化训练过程。在2个公开的眼底图像数据集(DRIVE-AV,LES-AV)上,与3种现有网络进行方法对比,该模型的F1评分分别提高了2.86、1.92、0.81个百分点,灵敏度分别提高了4.27、2.43、1.21个百分点,结果表明所提出的模型能够很好地解决动静脉分类错误的问题。

基于CNN和Transformer并行编码的腹部多器官图像分割

针对现有方法在腹部中小器官图像分割性能方面存在的不足,提出一种基于局部和全局并行编码的网络模型用于腹部多器官图像分割.首先,设计一种提取多尺度特征信息的局部编码分支;其次,全局特征编码分支采用分块Transformer,通过块内Transformer和块间Transformer的组合,既捕获了全局的长距离依赖信息又降低了计算量;再次,设计特征融合模块,以融合来自两条编码分支的上下文信息;最后,设计解码模块,实现全局信息与局部上下文信息的交互,更好地补偿解码阶段的信息损失.在Synapse多器官CT数据集上进行实验,与目前9种先进方法相比,在平均Dice相似系数(DSC)和Hausdorff距离(HD)指标上都达到了最佳性能,分别为83.10%和17.80 mm.

用于实时语义分割的丰富语义提取器网络

目的由于推理速度限制,网络深度较浅,实时语义分割网络提取的语义特征信息不足。此外,较浅的网络深度也限制了特征提取网络的能力,降低了其鲁棒性和适应能力。为此,方法提出一种用于实时语义分割的丰富语义提取器网络。首先针对语义特征信息提取不足的问题,引入丰富语义提取器,丰富语义提取器包括多尺度全局语义提取模块和语义融合模块。其次,利用多尺度全局语义提取模块可以提取丰富的多尺度全局语义,扩大网络的有效感受野,同时语义融合模块将多尺度局部语义与多尺度全局语义高效融合,使网络拥有更全面更丰富的语义信息。最后针对细节分支和语义分支的特点设计空间重构聚合模块,建模细节特征的上下文信息,增强特征表示,使2个分支高效聚合。结果在Cityscapes和ADE20K数据集上进行全面实验,所提出的RSENet分别以76帧/s和67帧/s的推理速度达到了75.6%和35.7%的MIoU。结论实验结果表明,在复杂场景语义信息的提取方面,本文所提出的网络能够深入挖掘并准确捕捉图像中语义信息。同时,在精度与速度的平衡方面也展现出了卓越的性能,不仅能够实现高精度的语义分割,而且推理速度非常快。这种高效的图像分割能力使得网络在实际应用场景中具有极高的实用性和可操作性。

基于激光雷达点云的动态驾驶场景多任务分割网络

在自动驾驶场景理解任务中进行准确的可行驶区域以及动静态物体分割对于后续的局部运动规划和运动控制至关重要。然而当前基于激光雷达点云的通用语义分割方法并不能在车端边缘计算设备上实现实时且鲁棒的预测,且不能预测当前时刻的物体运动状态。为解决该问题本文提出一种可行驶区域及动静态物体多任务分割网络MultiSegNet。该网络利用激光雷达输出的深度图及处理后得到的残差图像作为编码空间特征和运动特征的表征输入到网络用于特征学习,从而避免直接处理无序高密度点云。针对深度图在不同方向视角内目标分布数量差异较大的特点,本文提出了变分辨率分组输入策略。该方法能在降低网络计算量的同时提高网络的分割精度。为适配不同尺度目标所需要的卷积感受野尺寸本文提出了深度值引导的分层空洞卷积模块。同时本文为有效关联并融合不同时域下物体的空间位置和姿态信息提出了时空运动特征增强网络。为验证所提出MultiSegNet的有效性,本文在大规模点云驾驶场景数据集SemanticKITTI及nuScenes上进行验证。结果表明:可行驶区域、静态物体和动态物体的分割IoU分别达到98%、97%和70%,性能优于主流网络,且在边缘计算设备上实现实时推理。

融合多尺度特征和注意力机制的超声甲状腺结节分割

针对目前超声影像下甲状腺结节分割不够精准的问题,提出一种融合多尺度特征和注意力机制的超声甲状腺结节分割方法。该模型编码设计了多感受野通道选择模块,通过核心选择注意力对多个不同感受野的特征进行自适应加权组合,使包含目标的感受野通道占据主导。同时,设计自适应全局上下文模块自适应地提取瓶颈层多个尺度的全局上下文特征,以实现对瓶颈层高级语义的有效编码。此外,设计双注意力引导模块增强编解码器对等层之间的特征融合,以减少上采样过程中的信息损失。在公开的超声甲状腺结节数据集上进行实验,结果表明,文中所提方法优于其他对比网络,能更加精准地分割出甲状腺结节,有效提升了甲状腺结节的分割性能。