DECANet：基于改进DeepLabv3+的图像语义分割方法

在图像的语义分割任务中，不同对象之间像素值存在差异，导致现有的网络模型在图像语义分割过程中丢失图像局部细节信息。针对上述问题，提出一种图像语义分割方法（DECANet）。首先，引入通道注意力网络模块，通过对所有通道的依赖关系进行建模提高网络的表达能力，选择性地学习并强化通道特征，提取有用信息，抑制无用信息。其次，利用改进的空洞空间金字塔池化（ASPP）结构，对提取到的图像卷积特征进行多尺度融合，减少图像细节信息丢失，且在权重参数不改变的情况下提取语义像素位置信息，加快模型的收敛速度。最后，DECANet在PASCAL VOC2012和Cityscapes数据集上的平均交并比分别达81.08%和76%，与现有的先进网络模型相比，检测性能更优，可以有效地捕获局部细节信息，减少图像语义像素分类错误。     

分组双注意力语义分割网络

深度学习和自注意力机制的应用,使语义分割网络的性能得到了大幅提升.针对目前自注意力机制将每个像素的所有通道看作一个向量进行计算的粗糙性,基于空间维度和通道维度提出了一种分组双注意力网络.首先,将特征层分成多组;然后,自适应过滤掉每组特征层的无效基组,从而捕获精确的上下文信息;最后,将多组加权后的信息进行融合,获得较强的上下文信息.实验结果表明,本网络在两个数据集上的分割性能均优于双注意力网络,在PASCAL VOC2012验证集上的分割精度为85.6％,在Cityscapes验证集上的分割精度为71.7％.     

基于类特征注意力机制融合的语义分割算法

针对DeepLabv3+模型对图像目标边缘分割不准确、不同类目标分割不一致等问题，提出一种基于类特征注意力机制融合的语义分割算法。该算法在DeepLabv3+模型编码端先设计一个类特征注意力模块增强类别间的相关性，更好地提取和处理不同类别的语义信息。然后采用多级并行的空间金字塔池化结构增强空间之间的相关性，更好地提取图像不同尺度的上下文信息。最后在解码端利用通道注意力模块的特性对多层融合特征重新校准，抑制冗余信息，加强显著特征来提高网络的表征能力。在Pascal Voc2012和Cityscapes数据集上对改进模型进行了有效性和泛化性实验，平均交并比分别达到了81.34%和76.27%，使图像边缘分割更细致，类别更清晰，显著优于本文对比算法。     

基于改进SSD的航拍飞机目标检测方法

针对航拍图像中对于小尺度的飞机目标出现漏检、错检的问题，在SSD(Single Shot MultiBox Detector)模型的基础上提出了一种改进SSD的航拍图像目标检测模型。首先，针对SSD模型中浅层特征图中缺乏语义、细节信息的问题，设计了一种特征融合机制，通过添加细节信息补充特征层和添加由递归反向路径获得的语义信息补充特征层来丰富浅层特征图的语义、细节信息。然后，针对SSD模型对通道以及空间信息的关注能力不足的问题，引入了结合通道和空间的混合注意力模块来提高模型整体的关注能力。最后，针对SSD模型中先验框与小尺度目标不匹配的问题，对先验框的比例进行了调整。使用自制的航拍图像数据集进行验证，结果表明改进后的模型检测精度为95.7%，相较于原模型提高了7.5%，检测速度达到30.8 FPS。     

基于DeepLabV3+与注意力机制相结合的图像语义分割

基于DeepLabV3+进行图像分割时,在特征提取阶段忽略了不同级别的特征图中存在的特征重要程度不同,丢失了大量的细节信息,致使分割效果不佳.针对该问题,提出了一种基于DeepLabV3+与注意力机制相结合的图像语义分割算法.在骨干网络Xception模型中提取两条低级特征作为解码器的输入特征,提高特征提取的准确性;采...     

基于卷积模块注意力机制深度学习模型的激光熔覆裂纹识别

为改进传统人工方法对熔覆区域裂纹检测耗时、准确率低的现状,提出了一种融合注意力模型的熔覆区裂纹自动识别方法,以便对裂纹进行标识和检测.基于U-net网络构造的熔覆裂纹语义分割网络存在对局部小特征提取能力不足的问题,而通过增加注意力模型(CBAM)层,提取特征空间和特征通道的权重信息,就可以对激光熔覆区微观裂纹进行实时的像素级标注和检测.实验结果表明:引入注意力模型的深度学习模型可使熔覆裂纹的识别和检测准确率提升2.7个百分点;融合注意力模型的网络在熔覆区域裂纹测试集上的准确率为79.8％.深度学习模型标注的准确度和速度均已超过人工标注,为激光熔覆裂纹的识别提供了有效方法.     

一种改进的高分辨率遥感图像语义分割模型

本文针对高分辨率遥感图像的特点,设计了一种端到端的语义分割网络结构模型,高分辨率遥感图像可得到两种图像数据,采用resnet网络对两种图像的特征分别进行提取,并在不同的特征层上进行数据融合,在网络结构的设计中引入了空间位置注意力模块和通道注意力模块,并对底层特征使用不同扩张率的空洞卷积神经网络进行多尺度融合,得到一种新的高分辨率遥感图像语义分割模型,通过对最终的预测性能分析,相比FCN、Unet、Segnet、DeeplabV3+等流行的语义分割模型,该模型在高分辨率遥感图像的预测中具有一定的优势。     

基于纹元森林和显著性先验的弱监督图像语义分割方法

弱监督语义分割任务常利用训练集中全体图像的超像素及其相似度建立图模型,使用图像级别标记的监督关系进行约束求解。全局建模缺少单幅图像结构信息,同时此类参数方法受到复杂度限制,无法使用大规模的弱监督训练数据。针对以上问题,该文提出一种基于纹元森林和显著性先验的弱监督图像语义分割方法。算法使用弱监督数据和图像显著性训练随机森林分类器用于语义纹元森林特征(Semantic Texton Forest, STF)的提取。测试时,先将图像进行过分割,然后提取超像素语义纹元特征,利用朴素贝叶斯法进行超像素标记的概率估计,最后在条件随机场(CRF)框架下结合图像显著性信息定义了新的能量函数表达式,将图像的标注(labeling)问题转换为能量最小化问题求解。在MSRC-21类数据库上进行了验证,完成了语义分割任务。结果表明,在并未对整个训练集建立图模型的情况下,仅利用单幅图像的显著性信息也可以得到较好的分割结果,同时非参模型有利于规模数据分析。     

一种面向室内场景的语义分割网络

现有RGB D语义分割方法难以充分地融合深度信息来实现对复杂场景的语义分割,为了能更精确地在室内场景RGB图中进行识别内部物体,提出一种基于通道注意力机制的非对称三分支结构型卷积网络语义分割模型。该方法能选择性地从RGB图和深度图像中收集特征。先构建了一个具有三个并行分支的体系结构,并添加了三个互补的注意模块。且运用了双向跨模块特征传播策略,不仅可以保留原始RGB图像和深度图像的特征,还能充分利用融合分支的深度特征。在两个室内场景数据集(NYUDv2数据集和SUN RGBD数据集)进行了对照实验和消融研究。结果表明,所提出的模型与目前最好的表现方法注意力互补网络(ACNet)对比下,像素精度、平均像素精度、平均交并比分别提高了09、13、17,在镜子、书本、箱子等小物体的语义分割交并比指标提高了72、96、112。验证了提出的模型在处理室内场景具更强的适用性。     

基于颜色特征判别的纸病图像分割研究

针对当前纸病检测中图像分割算法的精确性及抗干扰性问题,文中提出了一种基于颜色特征判别的纸病图像分割算法。首先建立RGB颜色空间模型,提取空间分量信息特征,然后分别对RGB图像的3个通道的像素值进行可靠性计算,最后通过逻辑"或"运算融合单通道的计算结果,得到分割图像。结果表明:该算法定位准确、抗干扰性强,能够精确分割纸病图像,满足纸病检测要求。     

Technology innovation and process integrations for sub-100nm gate patterning

This paper presents a brief overview of the Applied Centura(R)DPS(R)system,configured with silicon etch DPS Ⅱ chamber, with emphasis on discussing tuning capability for CD uniformity control. It also presents the studies of etch process chemistry and film integration impact for an overall successful gate patterning development. Discussions will focus on resolutions to key issues, such as CD uniformity, line-edge roughness, and multilayer film etching integration.     

White organic light-emitting devices based on fac tris（2- phenylpyridine） iridium sensitized 5,6,11,12-tetraphenylnap -hthacene

We have fabricated the white organic light-emitting devices （WOLEDs） based on 4,4＇ -bis（2,2 -diphenyl vinyl）-1,1＇ - biphenyl （DPVBi） and phosphorescence sensitized 5,6,11,12,-tetraphenylnaphthacene （rubrene）. The device structure is ITO/2T-NATA （20 nm）/NPBX （20 nm）/CBP： x%Ir（ppy）3：0.5% rubrene （8 nm）/NPBX （5 nm）/DPVBi （30 nm）/Alq（30 nm）/LiF（0.5 nm）/A1. In the devices, DPVBi acts as a blue light-emitting layer, the rubrene is sensitized by a phosphorescent material, fac tris （2-phenylpyridine） iridium [Ir（ppy）3], acts as a yellow light-emitting layer, and N,N＇ -bis- （1-naphthyl）- N,N＇ -diphenyl -1, 1＇ -biphenyl-4,4＇ -diamine （NPBX） acts as a hole transporting and exciton blocker layer, respectively. When the concentration of Ir （PPY）3 is 6wt%, the maximum luminance is 24960 cd/m^2 at an applied voltage of 15 V, and the maximum luminous efficiency is 5.17 cd/A at an applied voltage of 8 V.     

Complete approach to automatic identification and subpixel center location for ellipse feature

To meet the need of automatic image features extraction with high precision in visual inspection, a complete approach to automatic identification and sub-pixel center location for similar-ellipse feature is proposed. In the method, the feature area is identified automatically based on the edge attribute, and the sub-pixel center location is accomplished with the leastsquare algorithm. It shows that the method is valid, practical, and has high precision by experiment. Meanwhile this method can meet the need of instrumentation of visual inspection because of easy realization and without man-machine interaction.     

小角度扩展相关性近似算法分析

本论文提出一种在多天线MIMO信道相关性建模中小角度扩展近似理论算法,并应用于分析MIMO系统性能。分析中分别对三种不同角能量分布情况下的空间相关性研发快速近似计算法,并同时提出双模(Bi-Modal)角能量分布情况下的近似运算。通过分析这些新方法的近似效率,可以得到计算简单、复杂度低、而且符合实际的MIMO相关信道矩阵,对系统级的快速高效计算法的研究和系统级的评估以及误差分析具有重要的意义。     

Curved crystal spectrometer for the measurement of X-ray lines from laser-produced plasmas

In order to diagnose the laser-produced plasmas, a focusing curved crystal spectrometer has been developed for measuring the X-ray lines radiated from a laser-produced plasmas. The design is based on the fact that the ray emitted from a source located at one focus of an ellipse will converge on the other focus by the reflection of the elliptical surface. The focal length and the eccentricity of the ellipse are 1350 mm and 0.9586, respectively. The spectrometer can be used to measure the X- ray lines in the wavelength range of 0.2-0.37 nm, and a LiF crystal （200） （2d = 0.4027 nm） is used as dispersive element covering Bragg angle from 30° to 67.5°. The spectrometer was tested on Shengnang- Ⅱ which can deliver laser energy of 60-80 J/pulse and the laser wavelength is 0.35 μm. Photographs of spectra including the 1 s2p ^1P1-1s^2 ^1S0 resonance line（w）, the 1s2p ^3P2-1s^2 1S0 magnetic quadrupole line（x）, the 1s2p ^3P1-1 s^2 ^1S0 intercombination lines（y）, the 1 s2p ^3S~1-1 s^2 ^1S0 forbidden line（z） in helium-like Ti Ⅹ Ⅺ and the 1 s2s2p ^2P3/2-1 s622s ^2S1/2 line（q） in lithium-like Ti Ⅹ Ⅹhave been recorded with a X-ray CCD camera. The experimental result shows that the wavelength resolution（λ/△ 2） is above 1000 and the elliptical crystal spectrometer is suitable for X-ray spectroscopy.     

Preparation and Characterization of TaN ALD Precursors

High purity organic-tantalum precursors for thin film ALD TaN were synthesized and characterized.Vapor pressure and thermal stability of these precursors were studied.From the vapor pressure analysis,it was found that TBTEMT has a higher vapor pressure than any other published liquid TaN precursor,including TBTDET,TAITMATA,and IPTDET.Thermal stability of the alkyl groups on the precursors was investigated using a 1H NMR technique.The results indicated that the tertbutylimino group is the most stable group on TBTDET and TBTEMT as compared to the dialkylamido groups.Thermal stability of TaN precursors decreased in the following order:TBTDET ＞ PDMAT ＞ TBTEMT.In conclusion,precursor vapor pressure and thermal stability were tuned by making slight variations in the ligand sphere around the metal center.     

A Versatile Mixed-Signal Pin Approach for Cost-Effective Test of Automotive ICs

Integrated circuits (ICs) intended for increasingly sophisticated automotive applications bring unique test demands. Advanced ICs for applications such as highly integrated automatic braking system (ABS) and airbag controllers combine high voltage digital channels, significant VI demands and precise timing capability. Along with continued missioncritical reliability concerns, the trend toward higher voltage operation and increased device integration requires specialized test capabilities able to extend across the wide operating ranges found in automotive applications. Among these capabilities, automotive test requirements increasingly dictate a need for a cost-effective versatile mixed-signal pin electronics with very high data rates reaching up to 50MHz with a voltage swing of-2 V to +28 V.     

Electronic Structure of Semiconductor Nanocrystals

This paper reviews our recent development of the use of the large-scale pseudopotential method to calculate the electronic structure of semiconductor nanocrystals, such as quantum dots and wires, which often contain tens of thousands of atoms. The calculated size-dependent exciton energies and absorption spectra of quantum dots and wires are in good agreement with experiments. We show that the electronic structure of a nanocrystal can be tuned not only by its size,but also by its shape. Finally,we show that defect properties in quantum dots can be significantly different from those in bulk semiconductors.     

Critical Stage Rule-Based Real Time Dispatch（RTD）System in Highly-Mixed-Products （HMP） FAB

An improving utilization and efficiency of critical equipments in semiconductor wafer fabrication facilities are concerned. Semiconductor manufacturing FAB is one of the most complicated and cost sensitive environments. A good dispatching tool will make big difference in equipment utilization and FAB output as a whole. The equipment in this paper is In-Line DUV Scanner. There are many factors impacting utilization and output on this equipment group. In HMP environment one of the issues is changing of reticule in this area and idle counts due to load unbalance between equipments. Here we'll introduce a rule-based RTD system which aiming at decreasing the number of recipe change and idle counts among a group of scanner equipment in a high-mixed-products FAB.     

Optical vibration and deviation measurement of rotating machine parts

It is of interest to get appropriate information about the dynamic behaviour of rotating machinery parts in service. This paper presents an approach of optical vibration and deviation measurement of such parts. Essential of this method is an image derotator combined with a high speed camera or a laser doppler vibrometer （LDV）.