蒙特卡罗估计改进Hausdorff距离的景象匹配方法

针对可见光与红外图像差异较大导致的匹配困难的实际问题,提出了一种基于蒙特卡罗估计改进Hausdorff距离（MCM-HD）的景象匹配方法。该方法在MCHD的基础上,使用蒙特卡罗方法来估计改进的Hausdorff距离（M-HD）,并定义了MCM-HD,即采用随机抽样的特征点子集来计算M-HD,从而有效地减少了计算量。为了提高匹配精度,采用分层MCM-HD与Nprod相结合的方法,在求出距离最小k个点之后采用Nprod相似性度量得出最终匹配位置。与MCHD算法相比,该算法有效提高了匹配精度,同时缩短了匹配时间。     

加权量子搜索算法及其相位匹配条件研究

目前的Grover算法在无序数据库中搜索多个目标时,得到不同目标的几率是相等的,不考虑各个目标重要程度的差异;并且当目标数超过数据库记录总数的四分之一时,搜索到目标的几率迅速下降,当目标数超过记录总数的一半时,算法失效.针对这两个问题,首先提出一种基于加权目标的搜索算法.根据各子目标的重要程度,为每个子目标赋予一个权系数,应用这些权系数将多个子目标表示成一个量子叠加态,这样可使得到每个子目标的几率等于其自身的权系数;其次,提出自适应相位匹配条件,该条件中两次相位旋转的方向相反,大小根据目标量子叠加态和系统初始状态的内积决定.当该内积大于等于((3-√5)/8)^1/2时,至多只需两步搜索,即可以恒等于1的几率得到搜索目标.实验表明,算法及其相位匹配条件是有效的.     

An Improved Human-Body-Segmentation Algorithm with Attention-Based Feature Fusion and a Refined Stereo-Matching Scheme Working at the Sub-Pixel Level for the Anthropometric System

This paper proposes an improved human-body-segmentation algorithm with attention-based feature fusion and a refined corner-based feature-point design with sub-pixel stereo matching for the anthropometric system. In the human-body-segmentation algorithm, four CBAMs are embedded in the four middle convolution layers of the backbone network (ResNet101) of PSPNet to achieve better feature fusion in space and channels, so as to improve accuracy. The common convolution in the residual blocks of ResNet101 is substituted by group convolution to reduce model parameters and computational cost, thereby optimizing efficiency. For the stereo-matching scheme, a corner-based feature point is designed to obtain the feature-point coordinates at sub-pixel level, so that precision is refined. A regional constraint is applied according to the characteristic of the checkerboard corner points, thereby reducing complexity. Experimental results demonstrated that the anthropometric system with the proposed CBAM-based human-body-segmentation algorithm and corner-based stereo-matching scheme can significantly outperform the state-of-the-art system in accuracy. It can also meet the national standards GB/T 2664-2017, GA 258-2009 and GB/T 2665-2017; and the textile industry standards FZ/T 73029-2019, FZ/T 73017-2014, FZ/T 73059-2017 and FZ/T 73022-2019.     

Effects of Fatty Alcohols with Different Chain Lengths on the Performance of Low pH Biomass-Based Foams for Radioactive Decontamination

Compared with polymers and nanoparticles, fatty alcohols can not only increase the stability of foam, but also maintain better foamability at pH < 2, which is beneficial to reduce waste liquid and increase decontamination efficiency for radioactive surface pollution. However, different fatty alcohols have different hydrophobic chain lengths. The effects of fatty alcohols with different chain lengths on the performance of decontamination foam were studied at pH < 2, to assist in the selection of suitable fatty alcohols as foam stabilizers. Combined with betaine surfactant and phytic acid, biomass-based foams were synthesized using fatty alcohols with different chain lengths. When the hydrophobic tail groups of the fatty alcohol and the surfactant were the same, the foam showed the best performance, including the lowest surface tension, the highest liquid film strength, the greatest sag-resistance and the best stability. However, when the hydrophobic tail groups were different, the space between adjacent surface active molecules was increased by thermal motion of the excess terminal tail segments (a tail-wagging effect), and the adsorption density reduced on the gas-liquid interface, leading to increased surface tension and decreased liquid film strength, sag-resistance and stability. The use of decontamination foam stabilized by fatty alcohols with the same hydrophobic group as the surfactant was found to increase the decontamination rate of radioactive uranium pollution from 64 to over 90% on a vertical surface.     

远距离运动目标三维测量中图像匹配的研究

采用两个摄像机光轴平行的双目立体视觉测量系统,检测远距离运动物体的三维物体轮廓.阐述了该三维轮廓测量系统中的两个关键技术:提取出合适的图像特征;建立特征间的对应关系.将同一空间物理点在不同图像中的映象点对应起来,由此得到相应的视差图像,实现立体匹配,恢复出物体的三维轮廓.仿真实验结果表明,该三维轮廓测量方法容易实现、对硬件要求不高、精度较高和具有较高稳定性,能够满足远距离运动物体姿态和速度测量的要求.     

基于视觉的空间粒子弱刚性运动约束

在对流场进行的激光测量中,针对运动粒子在具有一定体积的流场中透视成像后易出现的运动重叠问题,研究了粒子图像测速（PIV,particle image velodmetry）技术中近邻粒子的弱刚性运动,提出了应用于PIV系统中的空间粒子运动测量的约束条件（MPMC,movable particle measurement constraint）,并给出其数学表达式。该约束条件基于PIV的近邻性准则并以邻近的粒子团作为匹配对象,利用视平面内相同运动的特征直线具有公共点的性质对前后两帧图像中的粒子进行运动检测。最后,通过仿真实验证明该方法的有效性。     

基于云计算的云找回信息资讯平台的开发与实现

为解决信息时代下的物品丢失问题,特设计出一款基于云计算的云找回信息资讯平台.该平台利用Web技术,巧妙结合Springboot框架、云计算思想下对数据迁移和云数据库的部署将传统的告示形式的失物招领系统转变为网络可视化智能匹配方式,将失主与拾主联系在一起,架起用户之间的桥梁.本文着重阐述系统的总体结构和框架,说明了详细的...     

线算子引导Gabor小波的视网膜血管分割

视网膜血管自动分割能辅助诊断某些眼底疾病和系统性血管疾病。为了提高血管自动分割的效率,因此提出了一种线算子引导Gabor小波的视网膜血管分割方法。利用线算子检测血管方向的最优匹配角,将其作为Gabor小波变换的旋转角构建4个不同尺度的Gabor小波,并提取4维Gabor小波特征,加上两个线强度和预处理后的图像灰度,构建7维特征向量,采用SVM进行分类。与其他基于Gabor小波的方法相比,本方法只需计算最优匹配角所对应方向的Gabor小波特征,大大降低了多尺度Gabor小波特征提取的计算量,此外线算子特征与Gabor小波特征的良好互补性,有利于提高血管与背景的辨别度。在DRIVE眼底数据库上进行实验,其平均准确率、灵敏度及特异性分别为0. 936 1、0. 823 8及0. 955 4,获得了不错的分割性能。     

基于改进匹配追踪算法的化爆地震波信号时频特征提取

通过化爆地震波信号的时频分析可以获取丰富的地下岩层信息,为进一步的化爆地震波特性研究提供支撑。本文中利用爆炸地震波信号的非平稳随机特性,提出一种改进的匹配追踪算法(matching pursuits),该方法能更有效地获取化爆地震波信号的时频信息。该算法首先对地震波信号进行Hibert变换,将其转换成复数信号,获得爆炸地震波信号瞬时频率相位参数,再进行子波分解,从而显著提高了匹配追踪算法的运算速率;用分解后的信号计算其魏格纳威利分布(Wigner Ville distribution),有效地消除了交叉干扰项的影响。将该方法用于实测地震波信号的时频分析,获得了分辨率较高的时频分布图,且运算速率大大提高。

     

基于边缘差异的虚拟视图像质量评价方法

为了降低多视视频中的传输数据量,可适当减少包含纹理图及其对应深度图的多视数量,而在自由立体视频系统的终端采用基于深度图的绘制技术,生成新的虚拟视点。由于不准确的深度图估计、遮挡及合成算法等原因,合成虚拟视的边缘会出现高频噪声。对于这种特有的失真,用一般的评价方法并不能准确反映人眼的视觉感知。该文在分析失真虚拟视与原始视像素差异基础上,对各差异像素进行分类,并分配权重,提出了一种基于视觉加权的边缘差异质量评价方法,对边缘像素施加较高权重。经多视视频序列实验证明,该文方法相比于其它评价方法,能更好地预测人类视觉对虚拟视图像的主观感知。