期刊文献+
共找到3,293篇文章
< 1 2 165 >
每页显示 20 50 100
Influence of the Multi-segment Micro-crack and Groups of Kinked Micro-cracks on the Plastic Behavior of a Macro-crack
1
作者 Hongda Yang Jiding Zhang +1 位作者 Wentao Ma Xiaoyu Jiang 《Acta Mechanica Solida Sinica》 2025年第6期970-979,共10页
Combining the continuously distributed dislocation technique(DDT)and the von Mises yield criterion,new double-crack and multi-crack models were established.The influences of multi-segment kinked micro-cracks and group... Combining the continuously distributed dislocation technique(DDT)and the von Mises yield criterion,new double-crack and multi-crack models were established.The influences of multi-segment kinked micro-cracks and groups of kinked micro-cracks on the plastic behavior of the macro-crack were investigated.The results show that a smaller kinking angle of the micro-crack enhances its influence on the plastic deformation of the macro-crack,potentially leading to plastic zone fusion.Meanwhile,micro-cracks with smaller kinking angles exert a stronger attracting force on macro-crack growth,facilitating convergence between them.Furthermore,annularly distributed micro-crack groups demonstrate a more pronounced attraction on macro-crack propagation compared to linearly distributed micro-crack groups.The double-crack and multi-crack models established in this paper offer a theoretical framework for analyzing the plastic fracture behavior of metallic materials containing complex kinked cracks. 展开更多
关键词 Distributed dislocation technique multi-segment micro-crack Groups of kinked micro-cracks Plastic zone
原文传递
Three-dimensional numerical analysis on combustion performance and flow of hybrid rocket motor with multi-segmented grain 被引量:6
2
作者 Hui TIAN Yu DUAN Hao ZHU 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2020年第4期1181-1191,共11页
This paper presents the combustion characteristics in hybrid rocket motors with multisegmented grain through three-dimensional numerical simulations.Multi-segmented grain is composed of several thin grains with two or... This paper presents the combustion characteristics in hybrid rocket motors with multisegmented grain through three-dimensional numerical simulations.Multi-segmented grain is composed of several thin grains with two or more ports.The numerical model consists of Navier-Stokes equations with turbulence,solid fuel pyrolysis,chemical reactions,a fluid–solid coupling model and a regression rate model.The simulations adopt 90%Hydrogen Peroxide(HP)and PolyEthylene(PE)as the propellant combination.The effects of the rotation,port number,fuel grain segment number and mid-chamber length on the flow field and combustion performances are analyzed.The results indicate that the multi-segmented grain configuration can strengthen the flow field,and the regression rate and combustion efficiency are enhanced.Take the cases with two grain segments and three ports for example,the regression rate is increased by 32.4%-45.1%and the combustion efficiency increases by 6%-8.6%in different rotation angles. 展开更多
关键词 Combustion efficiency Hybrid rocket motor multi-segmented grain Regression rate Rotation angle
原文传递
Multi-segment and Multi-ply Overlapping Process of Multi Coupled Activities Based on Valid Information Evolution 被引量:1
3
作者 WANG Zhiliang WANG Yunxia QIU Shenghai 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2013年第1期176-188,共13页
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 addi... 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. 展开更多
关键词 multi coupled activities valid information evolution multi-segment multi-ply overlapping development time and cost trade-ofl iteration
在线阅读 下载PDF
Enhancement of thermal rectification by asymmetry engineering of thermal conductivity and geometric structure for multi-segment thermal rectifier 被引量:1
4
作者 杜甫烨 张望 +1 位作者 王惠琼 郑金成 《Chinese Physics B》 SCIE EI CAS CSCD 2023年第6期34-43,共10页
Thermal rectification is an exotic thermal transport phenomenon,an analog to electrical rectification,in which heat flux along one direction is larger than that in the other direction and is of significant interest in... Thermal rectification is an exotic thermal transport phenomenon,an analog to electrical rectification,in which heat flux along one direction is larger than that in the other direction and is of significant interest in electronic device applications.However,achieving high thermal rectification efficiency or rectification ratio is still a scientific challenge.In this work,we performed a systematic simulation of thermal rectification by considering both efforts of thermal conductivity asymmetry and geometrical asymmetry in a multi-segment thermal rectifier.It is found that the high asymmetry of thermal conductivity and the asymmetry of the geometric structure of multi-segment thermal rectifiers can significantly enhance the thermal rectification,and the combination of both thermal conductivity asymmetry and geometrical asymmetry can further improve thermal rectification efficiency.This work suggests a possible way for improving thermal rectification devices by asymmetry engineering. 展开更多
关键词 thermal conductivity SIMULATION thermal rectification multi-segment thermal rectifier
原文传递
DDoS Defense Algorithm Based on Multi-Segment Timeout Technology 被引量:1
5
作者 DU Ruizhong YANG Xiaohui MA Xiaoxue HE Xinfeng 《Wuhan University Journal of Natural Sciences》 CAS 2006年第6期1823-1826,共4页
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 pac... 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. 展开更多
关键词 DDoS(distributed denial of service) multi-segments timeout dynamic defense net flow analysis
在线阅读 下载PDF
A two-parameter multiple shooting method and its application to the natural vibrations of non-prismatic multi-segment beams
6
作者 R.HOŁUBOWSKI K.JARCZEWSKA 《Applied Mathematics and Mechanics(English Edition)》 SCIE EI CSCD 2023年第12期2243-2252,共10页
This paper presents an enhanced version of the standard shooting method that enables problems with two unknown parameters to be solved.A novel approach is applied to the analysis of the natural vibrations of Euler-Ber... This paper presents an enhanced version of the standard shooting method that enables problems with two unknown parameters to be solved.A novel approach is applied to the analysis of the natural vibrations of Euler-Bernoulli beams.The proposed algorithm,named as two-parameter multiple shooting method,is a new powerful numerical tool for calculating the natural frequencies and modes of multi-segment prismatic and non-prismatic beams with different boundary conditions.The impact of the axial force and additional point masses is also taken into account.Due to the fact that the method is based directly on the fourth-order ordinary differential equation,the structures do not have to be divided into many small elements to obtain an accurate enough solution,even though the geometry is very complex.To verify the proposed method,three different examples are considered,i.e.,a three-segment non-prismatic beam,a prismatic column subject to non-uniformly distributed compressive loads,and a two-segment beam with an additional point mass.Numerical analyses are carried out with the software MATHEMATICA.The results are compared with the solutions computed by the commercial finite element program SOFiSTiK.Good agreement is achieved,which confirms the correctness and high effectiveness of the formulated algorithm. 展开更多
关键词 two-parameter multiple shooting method two-point boundary value problem natural vibration non-prismatic beam multi-segment beam
在线阅读 下载PDF
High-power and high optical conversion efficiency diode-end-pumped laser with multi-segmented Nd:YAG/Nd:YVO-4
7
作者 Meng-Yao Wu Peng-Fei Qu +3 位作者 Shi-Yu Wang SEl Zhen Guo De-Fang Cai Bing-Bin Li 《Chinese Physics B》 SCIE EI CAS CSCD 2018年第9期306-310,共5页
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-seg... 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%. 展开更多
关键词 diode-pumped solid-state laser multi-segmented crystals(Nd:YAG Nd:YVO4) spectral line matching diode-laser temperature
原文传递
Multi-segmented nanowires for vortex magnetic domain wall racetrack memory
8
作者 M Al Bahri M Al Hinaai T Al Harthy 《Chinese Physics B》 SCIE EI CAS CSCD 2023年第12期582-588,共7页
A vortex domain wall's(VW) magnetic racetrack memory's high performance depends on VW structural stability,high speed, low power consumption and high storage density. In this study, these critical parameters w... A vortex domain wall's(VW) magnetic racetrack memory's high performance depends on VW structural stability,high speed, low power consumption and high storage density. In this study, these critical parameters were investigated in magnetic multi-segmented nanowires using micromagnetic simulation. Thus, an offset magnetic nanowire with a junction at the center was proposed for this purpose. This junction was implemented by shifting one portion of the magnetic nanowire horizontally in the x-direction(l) and vertically(d) in the y-direction. The VW structure became stable by manipulating magnetic properties, such as magnetic saturation(M_(4)) and magnetic anisotropy energy(K_(u)). In this case, increasing the values of M_(4) ≥ 800 kA/m keeps the VW structure stable during its dynamics and pinning and depinning in offset nanowires,which contributes to maintenance of the storage memory's lifetime for a longer period. It was also found that the VW moved with a speed of 500 m/s, which is desirable for VW racetrack memory devices. Moreover, it was revealed that the VW velocity could be controlled by adjusting the offset area dimensions(l and d), which helps to drive the VW by using low current densities and reducing the thermal-magnetic spin fluctuations. Further, the depinning current density of the VW(J_(d)) over the offset area increases as d increases and l decreases. In addition, magnetic properties, such as the M_(4) and K_(u),can affect the depinning process of the VW through the offset area. For high storage density, magnetic nanowires(multisegmented) with four junctions were designed. In total, six states were found with high VW stability, which means three bits per cell. Herein, we observed that the depinning current density(J_(d)) for moving the VW from one state to another was highly influenced by the offset area geometry(l and d) and the material's magnetic properties, such as the M_(4) and K_(u). 展开更多
关键词 micromagnetic simulation vortex domain wall racetrack memory multi-segmented magnetic nanowire spin transfer torque
原文传递
Double tractors swing microendoscopic discectomy technique for multi-segmental lumbar disc herniation
9
作者 张春霖 《外科研究与新技术》 2011年第2期104-104,共1页
Objective To evaluate the effect of double tractors swing microendoscopic discectomy technique in multisegmental lumbar disc herniation.Methods From December 2006 to November 2009,153 patients with multisegmental lumb... Objective To evaluate the effect of double tractors swing microendoscopic discectomy technique in multisegmental lumbar disc herniation.Methods From December 2006 to November 2009,153 patients with multisegmental lumbar disc herniation 展开更多
关键词 Double tractors swing microendoscopic discectomy technique for multi-segmental lumbar disc herniation
暂未订购
Optimizing the cleanliness in multi-segment disk amplifiers based on vector flow schemes 被引量:1
10
作者 Zhiyuan Ren Jianqiang Zhu +1 位作者 Zhigang Liu Xiaowei Yang 《High Power Laser Science and Engineering》 SCIE CAS CSCD 2018年第1期1-6,共6页
The objective of maintaining the cleanliness of the multi-segment disk amplifier in Shenguang-II(SG-II) is to reduce laser-induced damage for optics. The flow field of clean gas, which is used for the transportation o... The objective of maintaining the cleanliness of the multi-segment disk amplifier in Shenguang-II(SG-II) is to reduce laser-induced damage for optics. The flow field of clean gas, which is used for the transportation of contaminant particles,is a key factor affecting the cleanliness level in the multi-segment disk amplifier. We developed a gas–solid coupling and three-dimensional flow numerical simulation model. The three-dimensional and two-phase flow model is verified by the flow-field smog experiment and the particle concentration measurement experiment with the 130-disk amplifier in SG-II. By optimizing the boundary conditions with the same flow rate, the multi-inlet vector flow scheme can not only effectively reduce the purging time, but also prevent the reverse diffusion of contaminant particles in the multi-segment disk amplifier and the deposition of contaminant particles on the surface of the Nd:glass. 展开更多
关键词 CLEANLINESS computational fluid dynamics flow field multi-segment disk amplifier vector flow
原文传递
Multi-segment linear gradient optimization strategy based on resolution map in HPLC
11
作者 Andreas Seidel-Morgenstern 《Science China Chemistry》 SCIE EI CAS 2006年第4期315-325,共11页
Based on the mechanism of chromatographic retention (the relationship between the retention of solute and the mobile phase conditions) and method of resolution map, several methods of optimizing multi-segment linear g... Based on the mechanism of chromatographic retention (the relationship between the retention of solute and the mobile phase conditions) and method of resolution map, several methods of optimizing multi-segment linear gradient elution conditions were proposed according to the different separation requirements of various samples. These methods were verified using literature data. Moreover, the advantages and disadvantages of these methods were compared. It was proved that the third method is a fast optimization method which is capable of separating all the components with relatively high resolution. 展开更多
关键词 optimization multi-segment LINEAR gradient RESOLUTION map LIQUID chromatography.
原文传递
A 14-bit wide temperature range differential SAR ADC with an on-chip multi-segment BGR
12
作者 乔宁 高见头 +3 位作者 赵凯 杨波 刘忠立 于芳 《Journal of Semiconductors》 EI CAS CSCD 北大核心 2011年第8期80-86,共7页
A 14-bit low power self-timed differential successive approximation(SAR) ADC with an on-chip multisegment bandgap reference(BGR) is described.An on-chip multi-segment BGR,which has a temperature coefficient of 1.3... A 14-bit low power self-timed differential successive approximation(SAR) ADC with an on-chip multisegment bandgap reference(BGR) is described.An on-chip multi-segment BGR,which has a temperature coefficient of 1.3 ppm/℃and a thermal drift of about 100μV over the temperature range of -40 to 120℃is implemented to provide a high precision reference voltage for the SAR ADC.The Gray code form is utilized instead of binary form mode control to reduce substrate noise and enhance the linearity of the whole system.Self-timed bit-cycling is adopted to enhance the time efficiency.The 14-bit ADC was fabricated in a TSMC 0.13μm CMOS process. With the on-chip BGR,the SAR ADC achieves an SNDR of 81.2 dB(13.2 ENOB) and an SFDR of 85.2 dB with a conversion rate of 2 MS/s at room temperature and can keep an ENOB of more than 12 bits at a conversion rate of 2 MS/s over the temperature range from -40 to 120℃. 展开更多
关键词 differential successive approximation ADC self-timed bit-cycling gray code on-chip multi-segment BGR
原文传递
基于自适应多阈值的复杂场景激光图像目标分割方法研究
13
作者 周珂 王睿志 +2 位作者 韩继贤 蒋玉华 向兵 《激光杂志》 北大核心 2026年第2期130-135,共6页
传统方法无法适应复杂场景的变化,分割效果不佳,为此提出基于自适应多阈值的复杂场景激光图像目标分割方法。对复杂场景激光图像进行去除噪声处理,通过区域生长将图像划分为多个子区域,然后对每个子区域利用遗传算法获得对应阈值,实现... 传统方法无法适应复杂场景的变化,分割效果不佳,为此提出基于自适应多阈值的复杂场景激光图像目标分割方法。对复杂场景激光图像进行去除噪声处理,通过区域生长将图像划分为多个子区域,然后对每个子区域利用遗传算法获得对应阈值,实现图像自适应多阈值分割,通过合并相似区域和采用形态学操作有效消除过分割现象和图像中的孔洞、毛刺,提高分割结果的清晰度和平滑度,确保分割效果。结果表明:采用所提方法进行复杂场景激光图像目标分割,分割后F1值更高,可达到0.96,结构相似指数更小,为-0.23,能有效提高复杂场景激光图像目标分割效果。 展开更多
关键词 视觉传达 复杂场景激光图像 预处理 遗传算法 多阈值分割
原文传递
边缘检测下模糊红外图像多目标分割方法
14
作者 汪志敏 《激光杂志》 北大核心 2026年第2期118-123,共6页
针对红外图像容易受到环境干扰,导致模糊度过高、对比度过低,影响图像分割效果的问题,研究边缘检测下模糊红外图像多目标分割方法。选取截断约束最小二乘法,利用升余弦函数截断处理复原滤波器,通过在空间域内执行卷积运算,复原模糊红外... 针对红外图像容易受到环境干扰,导致模糊度过高、对比度过低,影响图像分割效果的问题,研究边缘检测下模糊红外图像多目标分割方法。选取截断约束最小二乘法,利用升余弦函数截断处理复原滤波器,通过在空间域内执行卷积运算,复原模糊红外图像。利用Canny边缘检测算法,通过对红外图像平滑滤波处理、计算红外图像的梯度幅值与方向、非极大值抑制红外图像的梯度幅值以及双阈值连接红外图像边缘的过程,检测去模糊复原后红外图像的边缘。依据Otsu准则,构建红外边缘图像的直线截距直方图,依据截距阈值划分截距直方图,利用最佳直线阈值将红外图像划分为目标区域与背景区域。实验结果表明,该方法能够实现红外图像的多目标分割,在噪声干扰等情况下,红外图像分割结果的边缘保持度均高于0.7。 展开更多
关键词 边缘检测 模糊红外图像 多目标 分割方法 复原滤波器 OTSU准则
原文传递
基于关键路径点的深度强化学习复合路径规划
15
作者 孙超 王江 +2 位作者 穆朝絮 邢良平 孙长银 《中国科学:信息科学》 北大核心 2026年第2期394-408,共15页
本文提出了一种结合Voronoi图和深度强化学习的机器人路径规划方法.在全局规划方面,通过Voronoi图构建“安全区域”,利用A*算法和关键路径点提取算法优化路径点,为局部规划提供目标.局部规划采用融合阶段关键点与均衡回放策略的RainbowD... 本文提出了一种结合Voronoi图和深度强化学习的机器人路径规划方法.在全局规划方面,通过Voronoi图构建“安全区域”,利用A*算法和关键路径点提取算法优化路径点,为局部规划提供目标.局部规划采用融合阶段关键点与均衡回放策略的RainbowDQN(stage-key&weight-balanced replay Rainbow deep Q-network,SW-RDQN)算法,通过3项关键设计提升复杂动态环境下的导航适应性:首先,采用多阶段路径分割策略对全局路径进行划分与剪枝,提取并保留关键路径点信息;其次,结合轨迹落点预测与环境势场设计奖励函数,引导智能体学习更安全有效的避障行为;最后,采用基于奖励与TD误差动态加权的优先经验回放,通过偏移与对数归一化提升关键经验采样概率,从而提高训练效率.状态输入融合了卷积和多层感知机提取信息,取若干场景帧送入长短期记忆网络模型,最后由稠密层做出决策,提升了机器人对动态环境的感知和响应能力.该方法有效提升了机器人在动态环境中的路径规划精度与鲁棒性. 展开更多
关键词 多阶段路径分割 VORONOI图 SW-RDQN 落点预测 场景避障导航
原文传递
道路场景下基于多尺度特征融合的语义分割网络
16
作者 徐晓苏 李东蒲 孟焱迪 《中国惯性技术学报》 北大核心 2026年第1期44-51,共8页
针对道路场景下高效图像语义分割的需求,提出一种基于Transformer的多尺度特征融合网络,旨在解决传统卷积神经网络难以有效捕捉图像的长程依赖关系及早期Transformer架构计算冗余且局部感知受限的问题。在编码阶段,采用基于MiT-B1的混合... 针对道路场景下高效图像语义分割的需求,提出一种基于Transformer的多尺度特征融合网络,旨在解决传统卷积神经网络难以有效捕捉图像的长程依赖关系及早期Transformer架构计算冗余且局部感知受限的问题。在编码阶段,采用基于MiT-B1的混合Transformer骨干网络,通过重叠图像块嵌入技术,保持特征的空间连续性,并结合高效自注意力机制降低计算开销。在解码阶段,设计了多尺度特征融合方案,利用通道空间注意力机制增强模型对关键目标的上下文捕捉能力;同时,提出一种轻量级改进残差卷积单元(RCU)提升多尺度特征的转换效率,有效弥补了跨层特征的语义差异。实验结果表明,在保持15.61 M轻量化参数规模的同时,所提算法在Cityscapes、ADE20K和COCO-Stuff数据集上的MIoU精度指标较基准模型分别提升了1.03%、1.36%和2.19%。此外,真实道路场景下的样机实验进一步证明,所提算法能够提供高精度的语义分割结果,满足自动驾驶系统的应用需求。 展开更多
关键词 语义分割 多尺度特征融合 残差卷积单元 混合Transformer编码器
在线阅读 下载PDF
用于土地覆盖分割的多路径多尺度注意力网络
17
作者 李燕 樊新宇 陈芹 《计算机工程与科学》 北大核心 2026年第1期108-118,共11页
近年来,Transformer及其变种在图像识别领域已取得显著进展,但其在像素级分割任务中仍面临挑战,主要原因在于它们对局部偏差的处理不够显式和有效。对此,提出了一种名为DMANet的多路径多尺度注意力网络。该网络在编码阶段结合了卷积神... 近年来,Transformer及其变种在图像识别领域已取得显著进展,但其在像素级分割任务中仍面临挑战,主要原因在于它们对局部偏差的处理不够显式和有效。对此,提出了一种名为DMANet的多路径多尺度注意力网络。该网络在编码阶段结合了卷积神经网络和Transformer的优势,能够同时捕获图像的精细局部信息和广泛的全局上下文信息,有效地提升特征提取能力。提出的交互式双分支结构加强了对特征的整合能力,提高网络模型在密集预测任务中的性能。在解码阶段实施跨层特征融合,增强DMANet对复杂目标的识别能力。通过在Potsdam,GID-15和L8 SPARCS数据集上进行测试,DMANet展示了其在复杂土地覆盖分割任务中的优异性能及广泛适用性。 展开更多
关键词 Transformer结构 语义分割 多路径多尺度 卷积神经网络 土地覆盖
在线阅读 下载PDF
基于级联注意力的结肠息肉图像分割算法研究
18
作者 周孟然 陆鹏 《重庆工商大学学报(自然科学版)》 2026年第1期1-10,共10页
目的针对现有Transformer模型在息肉图像分割中存在注意力分散以及作为编码器提取的多级特征在融合时易产生信息丢失导致的分割精度不高的问题,提出一种新的分割模型PVT-CAMNet。方法在该模型中,使用金字塔式Transformer(Pyramid Vision... 目的针对现有Transformer模型在息肉图像分割中存在注意力分散以及作为编码器提取的多级特征在融合时易产生信息丢失导致的分割精度不高的问题,提出一种新的分割模型PVT-CAMNet。方法在该模型中,使用金字塔式Transformer(Pyramid Vision Transformer,PVT)作为编码器,接着设计了多尺度特征注意力提取模块(Multi-scale Feature Attention Extraction,MFAE)和层间注意力聚合模块(Inter-layer Attention Aggregation,IA)。其中,PVT通过其自注意力机制保证了模型的泛化能力,MFAE使用不同大小的滤波器多尺度提取特征,旨在缓解注意力分散问题;IA交互融合不同层级特征,有效解决多级特征融合产生的信息丢失问题;最后引入全局上下文模块(Global Context,GC)使模型更好地理解特征图之间的像素依赖关系。结果在Kvasir、CVC-ClinicDB、CVC-ColonDB和ETIS数据集上进行了评估,相较于最优基线模型,mDice、mIoU分别提高了1.76%、0.81%、1.51%、1.74%、3.15%、2.65%和1.73%、3.84%。结论PVT-CAMNet的学习性能和泛化性能均优于其他先进方法,在息肉图像分割上具有一定的应用价值。 展开更多
关键词 息肉图像分割 多尺度注意力提取 层间注意力聚合 全局上下文
在线阅读 下载PDF
基于特征融合及多尺度上下文提取的实时语义分割
19
作者 刘伯红 刘磊 《重庆邮电大学学报(自然科学版)》 北大核心 2026年第1期167-176,共10页
针对实时语义分割算法常用的双分支结构存在空间分支和上下文分支特征融合不充分、多尺度上下文信息提取不全面等问题,提出基于特征融合及多尺度上下文提取的实时语义分割网络。设计空间-多尺度双向注意力融合模块,使用空间注意力机制... 针对实时语义分割算法常用的双分支结构存在空间分支和上下文分支特征融合不充分、多尺度上下文信息提取不全面等问题,提出基于特征融合及多尺度上下文提取的实时语义分割网络。设计空间-多尺度双向注意力融合模块,使用空间注意力机制和多尺度特征融合模块实现双分支交互融合,促进空间特征以及语义特征在双分支上的流动;在上下文分支末端设计了串联聚合金字塔池化模块,更精确地捕捉细节信息;聚合空间分支不同阶段特征,增强模型对图像特征的全面理解能力,促进深层特征与浅层特征的深度融合;使用多尺度注意力特征融合模块引导空间分支和上下文分支融合。实验结果表明,构建的网络在Cityscapes数据集上平均交并比(mean intersection over union,MIoU)达到78.0%,推理速度为104.5 Frame/s;在CamVid数据集上,MIoU达到75.9%,推理速度为224.6 Frame/s。 展开更多
关键词 实时语义分割 特征融合 注意力机制 多尺度上下文提取
在线阅读 下载PDF
基于金字塔注意力与双路径融合的皮肤病变图像分割
20
作者 宋存利 傅景鑫 +2 位作者 王依 张雪松 时维国 《计算机系统应用》 2026年第1期178-187,共10页
在皮肤病变图像分割任务中,U-Net在处理皮肤镜图像时存在多尺度适应性不足、跨层特征融合低效及计算冗余导致边缘信息丢失等问题.本文提出层次化金字塔注意力网络HPANet(hierarchical pyramid attention network),通过金字塔注意力模块... 在皮肤病变图像分割任务中,U-Net在处理皮肤镜图像时存在多尺度适应性不足、跨层特征融合低效及计算冗余导致边缘信息丢失等问题.本文提出层次化金字塔注意力网络HPANet(hierarchical pyramid attention network),通过金字塔注意力模块和双路径特征融合机制,实现了多尺度特征捕获和跨层特征传递的双重优化.其中,双路径自适应融合模块结合CNN与Transformer双分支特征,通过通道注意力与压缩空间注意力增强互补特征的信息交互,并利用双线性交互与残差连接缓解特征稀释问题.金字塔注意力模块结合分层多核卷积、深度可分离下采样及分块空间通道注意力机制,显著提升多尺度病变特征捕获能力.实验结果表明,本架构在ISIC 2017、ISIC 2018数据集中的表现均超越主流模型,证实其在病变边界保留与小病灶检测方面的双重优势. 展开更多
关键词 金字塔注意力 多尺度特征融合 医学图像分割 深度学习
在线阅读 下载PDF
上一页 1 2 165 下一页 到第
使用帮助 返回顶部