最优字典选择多频段雷达信号宽带融合

多频段雷达带宽融合外推是一种提升雷达带宽、解决小目标高分辨成像的有效手段。然而,现有多频段融合算法仍面临运算慢、精度低等问题。为此,该文提出基于最优字典选择正交匹配追踪的多频段融合外推雷达超分辨距离成像方法。首先,对多频段信号进行参数化建模,提出基于蛇优化的信号相参配准方法,实现多频段信号高精度相位对齐;然后,利用几何绕射模型,提出基于最优字典选择正交匹配追踪的多频段信号模型估计方法,实现多频段信号融合外推,估计未知频段频谱,获取大带宽信号;最后,通过仿真和实测数据,验证了该方法的可行性。该方法在保障高精度的前提下,通过简化模型粗估计与完整模型精估计结合,有效降低了运算量,实现了快速精确多频段融合外推处理。

基于空间分辨法分析时间低相干光自聚焦效应

时间低相干光由于其瞬时宽带的物理特性,在激光惯性约束聚变中得到了广泛的关注.然而其复杂的时间尖峰结构或将诱导非线性自聚焦效应的放大.同时,传统的非线性自聚焦特征数值的测试方法中,多数材料的表面损伤先于体内自聚焦成丝损伤发生,这为对比不同激光的非线性效应带来巨大影响.本文利用短焦距透镜对熔石英进行紧聚焦,通过调节入射激光能量,在避免前表面损伤的前提下,诱导熔石英产生自聚焦成丝损伤.随后通过理论计算对光束在样品体内传输过程的光斑变化进行空间分辨处理,并得到对应细分位置的非线性数值.最终将各个位置对应的非线性相位变化值进行积分,得到前表面无损条件下材料的非线性自聚焦特征数值.测试结果表明时间低相干光的非线性自聚焦效应比传统单模脉冲激光更强.本文不仅设计了一套更加精确的对比不同激光非线性效应的测试方法,同时也探明了时间相干性对于非线性自聚焦效应的影响机制,为高功率时间低相干激光器的设计提供理论依据和参考.

面向司法文书的抽取-生成式自动摘要模型

为解决抽取式摘要核心信息拼接生硬,生成式摘要源文本过长易忽略重要信息等问题,对抽取式摘要和生成式摘要的结合进行研究。通过分析抽取式摘要可提取出文本关键信息且缩短源文本长度特性;生成式摘要可降低序列间信息损失,增加文本关联的优势。提出一种面向司法文书的抽取-生成式自动摘要模型,融合模型优势,避免单一模型存在的关键文本信息重复及重组段落语法不准的问题,保障法律文书抽取的切实完整性。在大规模公开法律领域裁判文书数据集上的实验结果表明,该模型获得较高ROUGE得分,表明了该模型提升了摘要质量。

基于一致性感知特征融合的高动态范围成像方法

高动态范围成像(High Dynamic Range Imaging,HDRI)技术是指通过融合多张低动态范围(Low Dynamic Range,LDR)图像拓展图像动态范围、完整图像内容的方法,其为解决由于相机传感器动态范围有限而导致所拍摄图像内容丢失的问题提供了实际的解决方案.通过数十年的研究,众多有效的HDRI方法已被提出,并在无物体运动、内容曝光良好的静态场景中取得接近最优的性能.然而,现实场景中物体移动和相机偏移无法避免,直接使用传统HDRI方法会在融合后的HDR图像中产生严重的重影和伪影.这使得仅包含简单融合过程的HDRI方法并不适用于实际应用,现实场景中的HDRI任务仍然具有一定挑战.因此,针对动态场景下的HDRI研究迅速发展.近期的方法集中在借助深度卷积神经网络(Convolutional Neural Network,CNN)的力量以期实现更好的性能.在这些基于CNN的方法中,特征融合对于恢复图像完整内容、消除图像伪影方面起着至关重要的作用.传统的特征融合方法通过借助跳跃连接或注意力模块,首先将LDR图像的特征进行拼接,并通过堆叠的卷积操作逐渐关注不同的局部特征.然而,此类方案通常忽略了LDR图像序列之间丰富的上下文依赖关系,且未充分利用特征之间的纹理一致性.为解决这一问题,本文提出了一种全新的一致性感知特征融合(Coherence-Aware Feature Aggregation,CAFA)方案,该方案在卷积过程中对输入特征中位于不同空间位置但具有相同上下文信息的特征信息进行采样,从而显式地将上下文一致性纳入特征融合中.基于CAFA,本文进一步提出了一种结合CAFA的动态场景下一致性感知高动态范围成像网络CAHDRNet.为更好地嵌合CAFA方案,本文通过设计三个额外的可学习模块来构建CAHDRNet.首先,使用基于在ImageNet上预训练的VGG-19构建可学习特征提取器,并在模型训练期间不断更新该特征提取器的参数.这种设计可实现LDR图像的联合特征学习,为CAFA中的上下文一致性评估奠定了坚实基础.接着,应用所提出的CAFA模块,通过在图像特征中采样具有相同上下文的信息进行特征融合.最后,本文提出使用一种多尺度残差补全模块来处理融合后的特征,利用不同扩张率进行特征学习,以实现更强大的特征表示并在图像缺失区域中进行可信细节填充.同时,设计一个软注意力模块来学习不同图像区域的重要性,以便在跳跃连接期间获得与参考图像互补的所需特征.多种实验验证了CAHDRNet的有效性并证实其优于现有最先进的方法.具体而言,本文所提出的CAHDRNet在Kalantari数据集上HDR-VDP-2和PSNR-L等指标相较于次好方法AHDRNet分别提升了1.61和0.68.

基于改进MobileNetV2神经网络的视网膜OCT图像多分类

光学相干断层成像(optical coherence tomography,OCT)是一种具有无接触、高分辨率等特点的新型眼科医学诊断方法,现在已经作为医生临床诊断眼科疾病的重要参考物,但人工分类疾病费时费力,视网膜病变的早期发现和临床诊断至关重要.为了解决该类问题,本文提出了一种基于改进MobileNetV2神经网络对视网膜OCT图像多分类识别方法.此方法利用特征融合技术处理图像并设计增加注意力机制改进网络模型,二者在极大程度上提高OCT图像的分类准确率.与原有算法相比,分类效果具有明显提升,本文模型的分类准确率、召回值、精确度、F1值分别达到98.3%、98.44%、98.94%、98.69%,已经超越人工分类的准确率.此类方法不仅在实际诊断中加快诊断流程、降低医生负担、提高诊断质量,同时也为眼科医疗研究提供新的方向.

基于AS-OCT图像的核性白内障多级排序分类算法研究

目的探讨基于眼前节光学相干断层扫描(AS-OCT)图像的核性白内障智能辅助分级算法对白内障分级的诊断价值。方法采用诊断试验研究方法,收集2020年11月至2021年9月间同济大学附属第十人民医院电子病例系统中核性白内障患者939例1608眼的AS-OCT图像资料,所有资料均符合临床阅片清晰度要求。其中男398例664眼,女541例944眼,年龄18~94岁,平均年龄(65.7±18.6)岁。由3名经验丰富的临床医生基于晶状体混浊分类系统(LOCSⅢ分级系统),对所收集的AS-OCT图像进行1~6级人工标注。构建一种基于多级排序的全局-局部白内障分级算法,该算法包含5个基本的二元分类全局-局部网络(GL-Net),每个GL-Net聚合白内障核区域、原始图像等多尺度信息进行核性白内障分级。基于消融实验和模型对比试验,采用准确率、精确率、灵敏度、F1指标及Kappa系数对模型性能进行评价,且所有结果均通过五折交叉验证。结果模型在核性白内障数据集上的准确率、精确率、灵敏度、F1、Kappa分别为87.81%、88.88%、88.33%、88.51%、85.22%。消融实验结果表明,ResNet18结合局部特征和全局特征进行多级排序分类,模型在准确率、精确率、灵敏度、F1、Kappa指标上均有提升。与ResNet34、VGG16、Ranking-CNN、MRF-Net模型比较,本研究模型各性能指标均有提升。结论基于深度学习的AS-OCT核性白内障图像多级排序分类算法对白内障分级具有较高的准确度,有望辅助提高眼科医生对核性白内障的诊断精度以及效率。

Multi-Focus Image Fusion Based on Wavelet Transformation

In the fusion of image,how to measure the local character and clarity is called activity measurement. According to the problem,the traditional measurement is decided only by the high-frequency detail coefficients, which will make the energy expression insufficient to reflect the local clarity. Therefore,in this paper,a novel construction method for activity measurement is proposed. Firstly,it uses the wavelet decomposition for the fusion resource image, and then utilizes the high and low frequency wavelet coefficients synthetically. Meantime,it takes the normalized variance as the weight of high-frequency energy. Secondly,it calculates the measurement by the weighted energy,which can be used to measure the local character. Finally,the fusion coefficients can be got. In order to illustrate the superiority of this new method,three kinds of assessing indicators are provided. The experiment results show that,comparing with the traditional methods,this new method weakens the fuzzy and promotes the indicator value. Therefore,it has much more advantages for practical application.

DETECTION ON MICRO-DOPPLER EFFECT BASED ON LASER COHERENT RADAR

A laser coherent detection system of 1550 nm wavelength was presented, and experimen- tal research on detecting micro-Doppler effect in a dynamic target was developed. In the study, the return signal in the time domain is decomposed into a set of components in different wavelet scales by multi-resolution wavelet analysis, and the components are associated with the vibrational motions in a target. Then micro-Doppler signatures are extracted by applying the reconstruction. During the course of the final data processing frequency analysis and time-frequency analysis are applied to analyze the vibrationM signals and estimate the motion parameters successfully. The experimental results indicate that the system can effectively detect micro-Doppler information in a moving target, and the tiny vibrational signatures also can be acquired effectively by wavelet multi-resolution analy- sis and time-frequency analysis.

The spatial-temporal evolution of coherent structures in log law region of turbulent boundary layer

The spatial-temporal evolution of coherent structures （CS） is significant for turbulence control and drag re- duction. Among the CS, low and high speed streak structures show typical burst phenomena. The analysis was based on a time series of three-dimensional and three-component （3D-3C） velocity fields of the flat plate turbulent boundary layer （TBL） measured by a Tomographic and Time-resolved PIV （Tomo TRPIV） system. Using multi-resolution wavelet transform and conditional sampling method, we extracted the intrinsic topologies and found that the streak structures appear in bar-like patterns. Furthermore, we seized locations and velocity information of transient CS, and then calculated the propagation velocity of CS based on spatial-temporal cross-correlation scanning. This laid a foundation for further studies on relevant dynamics properties.

Multimodal Medical Image Registration and Fusion for Quality Enhancement

For the last two decades,physicians and clinical experts have used a single imaging modality to identify the normal and abnormal structure of the human body.However,most of the time,medical experts are unable to accurately analyze and examine the information from a single imaging modality due to the limited information.To overcome this problem,a multimodal approach is adopted to increase the qualitative and quantitative medical information which helps the doctors to easily diagnose diseases in their early stages.In the proposed method,a Multi-resolution Rigid Registration(MRR)technique is used for multimodal image registration while Discrete Wavelet Transform(DWT)along with Principal Component Averaging(PCAv)is utilized for image fusion.The proposed MRR method provides more accurate results as compared with Single Rigid Registration(SRR),while the proposed DWT-PCAv fusion process adds-on more constructive information with less computational time.The proposed method is tested on CT and MRI brain imaging modalities of the HARVARD dataset.The fusion results of the proposed method are compared with the existing fusion techniques.The quality assessment metrics such as Mutual Information(MI),Normalize Crosscorrelation(NCC)and Feature Mutual Information(FMI)are computed for statistical comparison of the proposed method.The proposed methodology provides more accurate results,better image quality and valuable information for medical diagnoses.

Reproducibility of macular perfusion parameters in non-proliferative diabetic retinopathy patients by two different OCTA sweep modes

·AIM:To assess the reproducibility of macular perfusion parameters in non-proliferative diabetic retinopathy(NPDR)patients measured by different examiners and two different sweep modes of optical coherence tomography angiography(OCTA).·METHODS:Ninety-eight(98 eyes)patients with NPDR were included in this study.All participates were performed three times using Cirrus OCTA with Angiography 3×3 mm^(2)and 6×6 mm^(2)sweep mode by two examiners.The macular foveal avascular zone(FAZ)and vessel density(VD)in the superficial retinal layer(SRL)were measured.The reproducibility of the measurements was evaluated with intraclass correlation coefficients(ICC)and coefficient of variation(CoV).·RESULTS:The intra-mode ICCs of Angiography 3×3 mm^(2)and 6×6 mm^(2)sweep mode were 0.957 to 0.959 and 0.964 to 0.977,respectively;and the inter-mode ICCs were 0.962 to 0.970.The intra-examiner ICCs of macular perfusion parameters were>0.950;and the inter-examiner ICCs were0.928 to 0.969.All CoVs were<1.0%.·CONCLUSION:Cirrus OCTA can measure macular perfusion parameters in NPDR patients with excellent reproducibility.The measurements of FAZ and VD in the SRL determined by Angiography 3×3 mm^(2)and 6×6 mm^(2)sweep mode are highly consistent and both sweep modes are suitable for macular perfusion parameters measurement.

Analysis of color distortion and optimum fusion for remote sensing images using the statistical property of wavelet decomposition

IHS （Intensity, Hue and Saturation） transform is one of the most commonly used tusion algonthm. But the matching error causes spectral distortion and degradation in processing of image fusion with IHS method. A study on IHS fusion indicates that the color distortion can＇t be avoided. Meanwhile, the statistical property of wavelet coefficient with wavelet decomposition reflects those significant features, such as edges, lines and regions. So, a united optimal fusion method, which uses the statistical property and IHS transform on pixel and feature levels, is proposed. That is, the high frequency of intensity component Ⅰ is fused on feature level with multi-resolution wavelet in IHS space. And the low frequency of intensity component Ⅰ is fused on pixel level with optimal weight coefficients. Spectral information and spatial resolution are two performance indexes of optimal weight coefficients. Experiment results with QuickBird data of Shanghai show that it is a practical and effective method.

Theoretical Hypothesis of a Double Barrier Regarding the D-D Interaction in a Pd Lattice： A Possible Explanation of Cold Fusion Experiment Failures

During the past 15 years, disputable experimental evidence has built up for LERN （low energy nuclear reaction） phenomena in specialized heavy hydrogen systems. Actually, it can not be said that a new branch of science is beginning. In spite of experimental contributions, the real problem is that the theoretical statements of LERN are unknown. In this work, the authors analyze the deuteron-deuteron reactions within palladium lattice by means of the coherence theory of nuclear and condensed matter and, using this general theoretical framework accepted from ＂cold fusion scientists＂, it will be shown the low occurrence probability of fusion phenomena. In fact, in the coherence approach, the D-D potential exhibits double barrier features and, in this way, the D-D fusion is hampered.

地震属性融合技术在砂岩型铀矿断层识别中的研究与应用

砂岩型铀矿由于其埋藏深度浅,浅层地震信息易受到噪音的影响,在使用相干体技术来进行断层的解释时,其属性剖面常呈现出多解性,给小断层的识别带来了一定的困难。为改善这一问题,结合谱分解技术高分辨率和抗噪性的优点,采用主成分分析法来对这两种地震属性进行融合,以改善单一地震属性对断层的分辨能力,经正演模拟及实际工区试算,融合后的地震属性剖面断层线清晰、断点干脆,取得了较好的应用效果。

眼底病变OCT图像的轻量化识别算法

为了准确、方便地识别多类型眼底病变,提出光学相干断层扫描技术(OCT)图像的轻量化分类模型MB-CNN.降低卷积核的使用个数,调节每个阶段卷积块的使用比例,设计轻量化主干网络L-Resnet,通过加深网络深度增强对深层语义信息的提取.使用深度可分离卷积设计多尺度卷积块MultiBlock,利用MultiBloc深度挖掘病灶区域的特征,使用不同的卷积核提取不同尺寸病变的特征,提高网络对病变OCT图像的识别能力.构建特征融合模块FFM,融合浅层信息和深层信息,充分提取病变特征的纹理和语义信息,提高对小目标病变的识别能力.实验结果显示,MB-CNN在UCSD、 Duke和NEH3个数据集上的总体分类精度分别达到97.2%、 99.92%和94.37%,模型参数量明显降低,所提模型能够针对眼底的多种病变进行分类.

Multi-resolution Analysis of Density Fluctuation of Coherent Structures About Supersonic Flow over VG

The density field around a vortex generator （VG） in supersonic flow is studied with a nanoparticle-based planar laser scattering （NPLS） method. Based on the calibration, i.e., the density distribution of the supersonic flow around a wedge, the density field of a supersonic VG is measured. According to movement characteristics of coherent structure in VG’s flow fields and the basic concepts of wavelet, the density fluctuating signals and multi-resolution characteristics of density field images are studied. The multi-resolution characteristics of density fluctuation can be analyzed with wavelet transformation of NPLS images. The wavelet approximate coefficients of density fluctuating signals exhibit their characteristics at different scales, and the corresponding detail coefficients show the difference of diverse layer smooth approximation in some way. Based on 2D wavelet decomposition and reconstruction of density field images, the approximate and detail signals at different scales are studied, and the coherent structures at different scales are extracted and analyzed.

基于机会发射的无源雷达系统发展评述

基于机会发射无源雷达系统采用的是一种古老而特殊的雷达体制 ,由于其具有潜在的隐蔽和反隐身等特性 ,近年来倍受媒体关注。专家们认为它将成为今后 10～ 2 0年内雷达系统的一个重要发展方向。本文分三个阶段对这一系统的发展作了阐述 ,并评述了各个阶段的技术特征 。

甜点及其融合属性在深水储层研究中的应用

在当今世界深水勘探油气勘探热潮中,深水储层的研究和预测更受注目。利用多种地震属性的结合能够最大限度地提高储层预测的精度。甜点属性是利用三维地震资料识别砂体的一种新技术。甜点值是反射强度与均方根频率的比值,能有效地预测深海沉积中的孤立砂体。研究发现,甜点结合地震相波形分类、相干体技术可以预测储层的沉积类型、砂体展布特征;甜点和相干的融合属性可以清晰确定岩性类型和分布范围。

ICF中光束平滑及靶面辐照均匀性技术评述

由于激光的高强度 ,它成为惯性约束聚变的首选驱动器。但为实现聚变靶丸的均匀压缩 ,必须提高激光的辐照均匀性。分析了惯性约束聚变中实现激光光束平滑和靶面均匀辐照的几种主要技术方案的原理和方法 ,得出各技术手段的性能特点及适用条件。

一种新的全色与多光谱图像融合变分模型

图像融合是提供包含各输入图像互补信息的单幅图像的有力工具.本文提出了一种新的用于全色和多光谱图像融合的变分模型.在Socolinsky对比度模型的基础上构造了一个改进的能量泛函最小化问题,以寻找最接近全色图像梯度的解.为了提高多光谱图像的空间分辨率,并尽可能地保持其原有的光谱信息,还将光谱一致项、波段间相关项和对比度增强项引入融合模型.在IKONOS和QuickBird数据集上测试了该模型的性能.实验结果表明该模型可以生成同时具有高空间质量和高光谱质量的融合图像.