调参随机共振在超高频微弱信号检测中的应用

针对经典随机共振（SR）理论只适用于小参数,在提取高频微弱信号失效而无法使用的问题,提出一种调参随机共振检测高频率微弱信号的方法。首先,推导出双稳系统中阻尼系数与信号频率的关系,并以Kramers逃逸速率为分析手段,讨论阻尼系数变化对系统发生随机共振的影响;然后,分析了系统形状参数对系统产生随机共振现象的影响,通过联合调整阻尼系数和系统参数实现了大频率微弱信号的检测,并讨论了不同采样频率与调参系统输出频谱特性的影响,验证了该方法在低采样率下仍具有较强的稳定性;最后,以通用软件无线电设备（USRP）接收的无线电带噪信号作为系统的输入进行仿真。实验结果表明,利用该调参随机共振策略能够稳定有效地检测出强噪声背景下的超高频微弱信号,信号频率可达到MHz、GHz,拓展了随机共振原理的微弱信号检测的应用领域。     

Effects of underdamped step-varying second-order stochastic resonance for weak signal detection

Stochastic resonance (SR) has been proved to be an effective approach for weak signal detection. In this paper, an underdamped step-varying second-order SR (USSSR) method is proposed to further improve the output signal-to-noise ratio (SNR). In the method, by selecting a proper underdamped damping factor and a proper calculation step, the weak periodic signal, the noise and the potential can be matched with each other in the regime of second-order SR to generate an optimal dynamical system. The proposed method has three distinct merits as: 1) secondary filtering effect produces a low-noise output waveform; 2) good band-pass filtering effect attenuates the multiscale noise that locates in high- and (or) low-frequency domains; and 3) good anti-noise capability in detecting weak signal being submerged in heavy background noise. Numerical analysis and application verification are performed to confirm the effectiveness and efficiency of the proposed method in comparison with a traditional SR method.     

Enhancement of Infrared Images Using Super Resolution Techniques Based on Big Data Processing

This paper presents a super-resolution (SR) technique for enhancement of infrared (IR) images. The suggested technique relies on the image acquisition model, which benefits from the sparse representations of low-resolution (LR) and high-resolution (HR) patches of the IR images. It uses bicubic interpolation and minimum mean square error (MMSE) estimation in the prediction of the HR image with a scheme that can be interpreted as a feed-forward neural network. The suggested algorithm to overcome the problem of having only LR images due to hardware limitations is represented with a big data processing model. The performance of the suggested technique is compared with that of the standard regularized image interpolation technique as well as an adaptive block-by-block least-squares (LS) interpolation technique from the peak signal-to-noise ratio (PSNR) perspective. Numerical results reveal the superiority of the proposed SR technique.

     

Precision constrained stochastic resonance in a feedforward neural network

Stochastic resonance (SR) is a phenomenon in which the response of a nonlinear system to a subthreshold information-bearing signal is optimized by the presence of noise. By considering a nonlinear system (network of leaky integrate-and-fire (LIF) neurons) that captures the functional dynamics of neuronal firing, we demonstrate that sensory neurons could, in principle harness SR to optimize the detection and transmission of weak stimuli. We have previously characterized this effect by use of signal-to-noise ratio (SNR). Here in addition to SNR, we apply an entropy-based measure (Fisher information) and compare the two measures of quantifying SR. We also discuss the performance of these two SR measures in a full precision floating point model simulated in Java and in a precision limited integer model simulated on a field programmable gate array (FPGA). We report in this study that stochastic resonance which is mainly associated with floating point implementations is possible in both a single LIF neuron and a network of LIF neurons implemented on lower resolution integer based digital hardware. We also report that such a network can improve the SNR and Fisher information of the output over a single LIF neuron.     

使用VGG能量损失的单图像超分辨率重建

单幅图像的超分辨率重建（single image super-resolution,简称SR）是一项重要的图像合成任务.目前,在基于神经网络的SR任务中,常用的损失函数包括基于内容的重构损失和基于生成对抗网络（generative adversarial network,简称GAN）的对抗损失.但是,基于传统的GAN的超分辨率重建模型（SRGAN）在判别器接收高分辨率图像作为输入时,输出判别信号不稳定.为了缓解这个问题,在SRGAN以及常用的VGG重构损失框架上,设计了一个稳定的基于能量的辅助对抗损失,称为VGG能量损失.该能量损失使用重构损失中的VGG编码部分,针对VGG编码设计相应的解码器,构建一个U-Net自编码结构VGG-UAE,利用VGG-UAE的重构损失表示能量,并使用该能量函数为生成器提供梯度;基于追踪能量函数的思想,VGG-UAE使生成器生成的高分辨率样本追踪真实数据的能量流.实验部分验证了使用VGG能量损失将比使用传统的GAN损失可以生成更有效的高分辨率图像.     

基于自适应块组割先验的噪声图像超分辨率重建

要增强噪声图像的分辨率,传统的串联方式依次进行去噪与超分辨率重建两个步骤,但去噪算法去除噪声的同时也损失了部分细节信息,影响了后续超分辨率重建的质量.为了使低分辨率噪声图像中所有细节信息都能参与超分辨率重建,本文以非局部中心化稀疏表示（Nonlocally centralized sparse representation,NCSR）模型为基础,提出了基于自适应块组割（Patch-group-cuts,PGCuts）先验的噪声图像超分辨率重建方法,同时实现去噪和超分辨率重建功能.块组割先验基于新颖的三维邻域系统和块组模型,能够达到图像去噪、边缘平滑和边缘清晰等效果.重建时以边缘强度为参考对块组割先验进行自适应约束,由于块组割在平滑区域约束力较低,采用分区域融合的方式进一步抑制噪声.本文对合成的低分辨率噪声图像和真实的低分辨率噪声图像进行了重建实验,实验表明,基于自适应块组割先验的噪声图像超分辨率重建算法,在丰富细节的同时能抑制噪声的干扰,不但具有较高的峰值信噪比和结构相似度等客观评价值,而且在非光滑区域具有很好的主观重建效果.     

2023年第1期目次

超分辨率(SR)是一类重要的数字图像处理技术,其根据一个观测者得到的低分辨率(LR)图像重 建并输出一个相应的高分辨率(HR)图像,从而提高现代数字图像的分辨率。SR 在数字图像压缩与传输、医学 成像、遥感成像、视频感知与监控等学科中的研究与应用价值巨大。随着深度学习的快速发展,结合最新的深 度学习方法,可以为 SR 问题提供创新性的解决方案。首先回顾 SR 的背景意义、发展过程以及将深度学习应 用于 SR 的技术价值。其次简要介绍传统 SR 算法的基本方法、分类和优缺点;按照不同的实现技术和网络类 型对基于深度学习的 SR 方法进行了分类介绍,重点分析对比了卷积神经网络(CNN)、残差网络(ResNet)和生成 对抗网络(GAN)在 SR 中的应用。然后介绍主要评价指标和解决策略,并对不同的 SR 算法在标准数据集中的 性能表现进行对比。最后总结基于深度学习的 SR 算法,并对未来发展趋势进行展望。     

A New Recurrent Neural Network for Solving Convex Quadratic Programming Problems With an Application to the $k$-Winners-Take-All Problem

In this paper, a new recurrent neural network is proposed for solving convex quadratic programming (QP) problems. Compared with existing neural networks, the proposed one features global convergence property under weak conditions, low structural complexity, and no calculation of matrix inverse. It serves as a competitive alternative in the neural network family for solving linear or quadratic programming problems. In addition, it is found that by some variable substitution, the proposed network turns out to be an existing model for solving minimax problems. In this sense, it can be also viewed as a special case of the minimax neural network. Based on this scheme, a k-winners-take-all (k-WTA) network with O(n) complexity is designed, which is characterized by simple structure, global convergence, and capability to deal with some ill cases. Numerical simulations are provided to validate the theoretical results obtained. More importantly, the network design method proposed in this paper has great potential to inspire other competitive inventions along the same line.     

周期势增强随机共振机械故障特征提取方法

针对机械设备早期故障特征难以提取的问题,提出一种周期势函数增强随机共振的机械故障特征提取方法。该方法利用周期势函数的无限稳态结构和抗粒子运动饱和特性,并整合频移尺度变换,能够克服经典双稳态随机共振方法的饱和问题,有利于高速高精机械设备旋转部件早期故障微弱特征的增强与提取。对仿真和电机轴承实验分别用提出方法、经典双稳态随机共振方法和集成经验模式分解方法进行故障特征提取,结果表明提出方法优于集成经验模式分解方法,而且比经典双稳态随机共振方法有更好的增强效果,能够增强和提取微弱故障特征,实现高速高精机械设备电机轴承的故障诊断。     

Dual-scale cascaded adaptive stochastic resonance for rotary machine health monitoring

Effective extraction of weak signals submerged in strong noise that are indicative of structural defects has remained a major challenge in fault diagnosis for rotary machines. Unlike traditional techniques that focus on noise filtering and reduction, stochastic resonance (SR) takes a noise-assisted approach to detecting weak signals. This paper presents a new adaptive method for weak signal detection, termed Dual-scale Cascaded Adaptive Stochastic Resonance (DuSCASR), which can quantify the frequency content of a weak signal without prior knowledge. Simulations and experiments have confirmed the effectiveness of the method in bearing fault diagnosis at the incipient stage, with high precision and robustness.     

图神经网络回归的人脸超分辨率重建

人脸超分辨率（super-resolution,SR）即将输入模糊的低分辨率（low-resolution,LR）人脸图像通过一系列算法处理得到较为清晰的高分辨率（high-resolution,HR）人脸图像的过程．相比自然图像,不同人脸图像的相同位置通常具有相似的结构．本文针对人脸图像的局部结构一致性特点,提出一种新的基于图结构的人脸超分辨率神经网络回归方法．将输入低分辨率图像表示为图结构,进而为图结构中每一个结点的局部表示训练一个浅层神经网络进行超分辨率回归．相比基于规则矩形网格的方法,图结构在描述一个像素的局部信息时,不仅考虑到图像坐标的相关性,同时关注了纹理的相似性,能更好表达图像局部特征．训练过程中,利用已收敛的相邻结点的神经网络参数初始化当前结点的神经网络参数,不仅加快神经网络的收敛速度,而且提高了预测精度．与包括深度卷积神经网络在内的基于学习的超分辨率最新算法比较实验表明,本文提出的算法取得了更高的准确率．本文提出的图神经网络（Graph Neural Networks,GNN）并不局限于解决人脸超分辨率问题,它还可以用于处理其它具有不规则拓扑结构的数据,解决不同的问题．     

A super resolution approach for spectral unmixing of remote sensing images

It is well known that coarse spatial resolution is an important factor for the occurrence of mixed pixels in remote sensing images, and conventional approaches for spectral unmixing adopt various techniques on spectral dimension only in a fixed spatial resolution. In this article, a super resolution (SR) approach for spectral unmixing is proposed, based on the assumption that increasing the spatial resolution helps to retrieve the composition of a pixel. Firstly, a remote sensing image is downscaled into an SR image using example-based kernel ridge regression (EBKRR). Secondly, the SR image is classified using supervised hard classification, and then the class map is decomposed into thematic class layers. Thirdly, the thematic class layers are upscaled into the original spatial resolution with an averaging operation, and the abundance maps are finally derived. In two simulated data-based experiments and one ground data-based experiment, this approach was compared with linear spectral mixture analysis (LSMA) and artificial neural network (ANN)-based spectral unmixing methods. The accuracy assessment indicated that the SR approach outperformed LSMA and ANN under measurements of mean absolute error and absolute bias in the three experiments.     

基于残差神经网络的图像超分辨率改进算法

为更有效地提升图像的超分辨率（SR）效果,提出了一种多阶段级联残差卷积神经网络模型。首先,该模型采用了两阶段超分辨率图像重建方法先重建2倍超分辨率图像,再重建4倍超分辨率图像;其次,第一阶段与第二阶段皆使用残差层和跳层结构预测出高分辨率空间的纹理信息,由反卷积层分别重建出2倍与4倍大小的超分辨率图像;最后,以两阶段的结果分别构建多任务损失函数,利用第一阶段的损失指导第二阶段的损失,从而提高网络的训练速度,加强网络学习中的监督指导。实验结果表明,与bilinear算法、bicubic算法、基于卷积神经网络的图像超分辨率（SRCNN）算法和加速的超分辨率卷积神经网络（FSRCNN）算法相比,所提模型能更好地重建出图像的细节和纹理,避免了经过迭代之后造成的图像过度平滑,获得更高的峰值信噪比（PSNR）和平均结构相似度（MSSIM）。     

基于级联双稳随机共振的微弱信号检测方法研究

微弱信号采集、检测与提取是航天测控领域研究的热点之一,学者们不断探索与研究微弱信号检测的新理论、新方法,以期能更快速、更准确地从大噪声背景中检测出微弱信号;文章介绍了随机共振的基本原理,分析了基于随机共振的微弱信号检测和故障诊断的工程实例,进一步指出了随机共振技术在微弱信号的增强放大和检测中的独特优势,为微弱信号的分析和噪声控制提供了一个新的处理思路。     

基于DCT变换和零次学习的刑侦图像超分辨率

图像超分辨率在视频侦查领域有重要作用.基于卷积神经网络的超分辨率算法通常在训练时输入人工合成的低分辨率图像,学习高、低分辨率图像的映射,很难应用于视频侦查领域.真实低分辨率图像退化过程复杂未知,且大都经过压缩算法的处理,存在人工压缩痕迹,导致超分辨率图像出现假纹理.针对真实场景下的低分辨率图像提出一种基于离散余弦变换(...     

Bridging the Gap: Query by Semantic Example

A combination of query-by-visual-example (QBVE) and semantic retrieval (SR), denoted as query-by-semantic-example (QBSE), is proposed. Images are labeled with respect to a vocabulary of visual concepts, as is usual in SR. Each image is then represented by a vector, referred to as a semantic multinomial, of posterior concept probabilities. Retrieval is based on the query-by-example paradigm: the user provides a query image, for which 1) a semantic multinomial is computed and 2) matched to those in the database. QBSE is shown to have two main properties of interest, one mostly practical and the other philosophical. From a practical standpoint, because it inherits the generalization ability of SR inside the space of known visual concepts (referred to as the semantic space) but performs much better outside of it, QBSE produces retrieval systems that are more accurate than what was previously possible. Philosophically, because it allows a direct comparison of visual and semantic representations under a common query paradigm, QBSE enables the design of experiments that explicitly test the value of semantic representations for image retrieval. An implementation of QBSE under the minimum probability of error (MPE) retrieval framework, previously applied with success to both QBVE and SR, is proposed, and used to demonstrate the two properties. In particular, an extensive objective comparison of QBSE with QBVE is presented, showing that the former significantly outperforms the latter both inside and outside the semantic space. By carefully controlling the structure of the semantic space, it is also shown that this improvement can only be attributed to the semantic nature of the representation on which QBSE is based.     

基于深度学习的心脏磁共振影像超分辨率前沿进展

心脏为人体血液流动提供动力,是人体血液循环系统的重要组成部分。受人口老龄化影响,心脏病诊疗已成为重大公共健康话题。非侵入式活体心脏成像对心脏疾病的检测、诊断与治疗意义重大。然而,受活体心跳影响,成像扫描时间与心脏影像分辨率成为难以调和的矛盾。为缓和这一矛盾,基于快速扫描获得的低分辨率影像重建出心脏高分辨率影像的超分辨率（super-resolution,SR）重建技术成为研究热点。深度学习技术在医学影像处理领域中展现出强大生命力,基于深度学习的SR技术因其强大的学习能力与数据驱动性,在心脏影像SR重建领域中表现出明显优于传统方法的性能。目前领域内前沿成果较多,但缺少对领域现状进行总结、对未来发展进行展望的综述性文献。因此,本文对领域内现状进行梳理总结,挑选出代表性方法,分析方法特性,总结文献中心脏影像数据来源与规模,给出常用的评价指标,以及模型得出的性能评价结论。分析发现,基于深度学习的心脏SR重建技术取得了较大进展,但在运动伪影抑制、模型简化程度与时间性能方面仍有进步空间。此外,现有模型基本完全依靠网络强大的表达能力,鲜有临床先验知识的引入。最后,模型间性能对比相对较少,且领域内缺少代表性的可用于评价不同心脏SR重建模型性能的数据集。基于深度学习的心脏影像SR技术仍有较大发展空间。     

跨尺度耦合的连续比例因子图像超分辨率

目的 虽然深度学习技术已大幅提高了图像超分辨率的性能,但是现有方法大多仅考虑了特定的整数比例因子,不能灵活地实现连续比例因子的超分辨率。现有方法通常为每个比例因子训练一次模型,导致耗费很长的训练时间和占用过多的模型存储空间。针对以上问题,本文提出了一种基于跨尺度耦合网络的连续比例因子超分辨率方法。方法 提出一个用于替代传统上采样层的跨尺度耦合上采样模块,用于实现连续比例因子上采样。其次,提出一个跨尺度卷积层,可以在多个尺度上并行提取特征,通过动态地激活和聚合不同尺度的特征来挖掘跨尺度上下文信息,有效提升连续比例因子超分辨率任务的性能。结果 在3个数据集上与最新的超分辨率方法进行比较,在连续比例因子任务中,相比于性能第2的对比算法Meta-SR(meta super-resolution),峰值信噪比提升达0.13 dB,而参数量减少了73%。在整数比例因子任务中,相比于参数量相近的轻量网络SRFBN(super-resolution feedback network),峰值信噪比提升达0.24 dB。同时,提出的算法能够生成视觉效果更加逼真、纹理更加清晰的结果。消融实验证明了所提算法中各个模块的有效性。结论 本文提出的连续比例因子超分辨率模型,仅需要一次训练,就可以在任意比例因子上获得优秀的超分辨率结果。此外,跨尺度耦合上采样模块可以用于替代常用的亚像素层或反卷积层,在实现连续比例因子上采样的同时,保持模型性能。     

Image super resolution based on residual dense CNN and guided filters

Convolutional neural networks (CNNs) have recently made impressive results for image super-resolution (SR). Our goal is to introduce a new image SR framework rely on a CNN. In this paper, the input image is decomposed into luminance channel and chromatic channels. A designed network based on a residual dense network is introduced to extract the hierarchical features from luminance part. The bicubic interpolation is simply used to upscale low resolution (LR) chromatic channels. However, this step degrades the chromatic channels. To tackle this issue, the SR reconstructed luminance channel is applied as the reference image in guided filters to promote the interpolated chromatic channels. Guided filters technique has ability to retain sharp edges and fine details from the reference image and carry them to the target images. Extensive experiments on several commonly used image SR testing datasets demonstrate that our framework has the ability to extract features and outperforms existing well-known techniques for image SR by LR image into the high resolution (HR) image efficiently.

     

Single-frame super resolution of remote-sensing images by convolutional neural networks

Super resolution (SR) refers to generation of a high-resolution (HR) image from a decimated, blurred, low-resolution (LR) image set, which can be either a single-frame or multi-frame that contains a collection of images acquired from slightly different views of the same observation area. In this study, two convolutional neural network (CNN)-based deep learning techniques are adapted in single-frame SR to increase the resolution of remote sensing (RS) images by a factor of 2, 3, and 4. In order to both preserve the colour information and speed up the algorithm, first an intensity hue saturation (IHS) transform is utilized and the SR techniques are only applied to the intensity channel of the images. Colour information is then restored with an inverse IHS transformation. We demonstrate the results of the proposed method on RS images acquired from Satellites Pour l’Observation de la Terre (SPOT) or Earth-observing satellites and Pleiades satellites with different spatial resolution. First synthetic LR images are created by downsampling, then structural similarity (SSIM) Index, peak signal-to-noise ratio (PSNR), Spectral Angle Mapper (SAM) and Erreur Relative Globale Adimensionnelle de Synthese (ERGAS) values are calculated for a quantitative evaluation of the methods. Finally, the method, with better performance results, is tested within a real scenario, that is, with original LR images as the input. The obtained HR images demonstrated visible qualitative enhancements.