基于透视校正的指针式仪表读数识别

针对在倾斜拍摄条件下如何正确获取指针式仪表读数的问题,提出了一种基于透视校正的识别方法。采用色值叠加法进行图像增强;采用Otsu算法对图像进行二值化,并通过最大连通域获取仪表表盘区域;采用Hough变换法和最小二乘法进行表盘区域的边界直线的提取;通过透视变换法对表盘区域图像进行校正;利用兴趣区模板提取指针特征,并通过最小二乘法确定指针的偏转角度,用以计算仪表的读数。实验结果表明,所提方法具有较高的准确度和较好的实时性,对在倾斜条件下拍摄的仪表图像进行读数识别具有一定的实用价值。     

基于图像处理的汽车指针式仪表自动检测设计

目前我国汽车行业普遍采用人工检测仪表的方式,传统的肉眼判读方法受人的主观因素和外界环境的影响较大,本论文通过研究一种基于图像处理技术的汽车指针式仪表自动检测方案。利用图像处理技术,通过实现图像二值化,形态学处理与细化等图像预处理。采用计算区域特征与最小二乘法的方法识别并拟合出指针所在的直线,实现汽车仪表的指针检测。这种方法能减少运算量,并能准确地识别出指针直线和待求指针所指示的数值大小。     

基于刻度轮廓拟合的指针式仪表自动识别方法北大核心CSCD

为实现仪表的自动识别,提出基于轮廓的表盘区域检测与基于最小二乘法和刻度点定位的仪表示数识别方法。该算法通过二值化、滤波等预处理方法减少干扰,结合轮廓间的内嵌关系,提取出包含指针和刻度的表盘区域,得到仪表盘刻度轮廓集,并采用随机最小二乘法拟合表盘椭圆。通过分析指针的特性,提出基于EDLines直线检测算法的指针检测方法,完成对表盘内指针的提取与定位。最后根据指针直线方程、刻度编号和量程范围自动完成读数。实验表明,该算法具备较强的抗干扰能力,读数与人工读数误差较小,满足实际精度需求。     

基于YOLOv5和U-net的指针式仪表读数识别方法北大核心CSCD

针对不同背景、距离条件下指针式仪表读数识别准确性低的问题,提出了一种结合YOLOv5和U-net的仪表读数识别方法。首先引入了YOLOv5算法检测并提取仪表区域;其次采用Hough梯度圆检测提取纯仪表盘和U-net分割算法准确分割出指针轮廓,并通过指针细化,加权最小二乘法拟合指针所在直线,根据定位坐标系获取指针方向和偏转角度,最后利用指针的偏转角度计算仪表读数。结果表明:提出的方法检测每张图像的平均耗时为64.511 ms,读数识别的成功率达97%,平均引用误差为0.577%,能快速并准确地识别出指针式仪表示数。     

基于YOLOv4的指针式仪表自动检测和读数方法研究

针对仪表自动检测读数时,由于仪表特征不明显、复杂背景环境等因素造成的仪表检测困难、提取速度慢的问题,提出了一种基于YOLOv4的指针式仪表自动检测和读数方法。首先,利用YOLOv4检测提取了仪表盘区域,采用霍夫变换裁剪了表盘区域;其次,在表盘区域查找了刻度线轮廓,利用最小二乘法拟合了刻度线轮廓直线,得到了指针回转中心;最后,细化指针轮廓,并利用随机采样一致性拟合了指针中心直线,根据指针的回转角度换算得到了仪表读数。实验及研究结果表明:采用指针式仪表自动检测和识别方法的仪表检测精度达到了98.6%,读数的平均基本误差为0.72%,平均识别时间为80.65 ms;同时,该结果也证明了算法的有效性和快速性。     

基于形态学处理的仪表指针提取算法

指针式仪表被广泛应用在工业检测等诸多领域,目前指针式仪表检测朝着自动化和智能化的方向发展。指针特征提取是指针式仪表检测系统中极为关键的技术,针对仪表表盘环境复杂、指针的粗细不一等因素导致的指针特征提取困难问题,提出了基于形态学处理的仪表指针提取算法。首先将获取的图像经过图像增强处理、中值滤波、otsu算法获得干净的二值化图,其次将反转后的二值化图经过形态学处理,最后输出提取结果。实验结果表明:该算法在损失极少量指针长度的情况下能够更为精确有效的提取指针信息,解决“双边缘效应”现象和复杂表盘环境下无关信息对指针特征信息的干扰,从而可以提高仪表检测的精确程度和仪表检测系统的适用性,对指针式仪表检测系统的读数识别研究具有重要意义。     

基于对称性特征的指针仪表识别

指针式仪表在电力行业应用广泛,对指针式仪表读数自动识别是实现电网设备自动化和智能化巡检的基础。通过提取待识别指针图像中的对称性特征,在角度和距离空间中进行投票,得到候选指针对称轴,再结合指针边缘像素点的共线性和指针对称轴线段对应的像素值近似一致性等先验信息,对候选指针进行筛选,并根据指针对称轴的旋转角度计算得到仪表的最终读数。实验结果表明,该方法能够准确定位指针区域并识别仪表示数,且算法耗时很短,能够满足对指针式仪表实时巡检的需求。     

基于单参数同态滤波与全局对比度增强的指针仪表读数识别方法

为解决光照变化、指针阴影对指针式仪表读数识别的影响,提出具有单参数的指数型同态滤波与全局对比度处理的仪表读数识别方法。设计了单参数指数型同态滤波器来增强图像对光照变化的适应性;利用全局对比度图像增强算法来突出表盘信息区域;通过二值化、连通域处理、形态学处理提取指针区域;通过细化处理和累计概率霍夫变换定位指针中心线;获取指针的偏转角度来计算仪表读数。仿真实验表明,所提算法能够在不同光照变化和存在指针阴影的条件下较好地提取指针区域,且读数识别的正确率达到95%以上。     

基于计算机视觉的电测仪表自动识别方法的研究

研究图像处理技术在仪表自动化校验中的应用方案,详细介绍了基于最大似然估计的最小二乘拟合方法来确定指针和刻度线的参数.利用计算机视觉识别技术、信息处理技术和智能仪器设计原理,可从根本上解决电测仪表快速、准确的自动校验问题.     

一种汽车仪表指针帽体与仪表盘压装系统的设计

针对传统汽车仪表指针压制过程中存在的缺陷,设计一种汽车仪表指针自动压装系统,该系统的仪表指针帽体与仪表盘能自动完成压力和间隙的检测等一系列的自动压装过程,对汽车仪表指针进行压制质量自动监控。     

一种基于机器视觉的水表检定装置的研制

研制了一种基于机器视觉的水表检定装置,该检定装置通过设计移动式图像采集平台,单个相机即可完成对多工位的水表指针图像采集,节约了设备成本。采用角度法识别水表指针读数,通过模板匹配校正图像,提出了一种改进的最小二乘法拟合圆心的算法定位指针,利用harris角点检测算法获取针尖点,根据圆心与指针角点形成的连线之间的夹角获得指针的读数。实验表明:该检定装置与人工检定的方法相比,提高了生产效率,且系统的识别正确率在94%以上,具有较高的准确性。     

Water meter pointer reading recognition method based on target-key point detection

With the rapid development of video image technology and fifth-generation mobile network technology, the automatic verification of mechanical water meters has become an increasingly important topic in smart cities. Although much research has been done on this subject, the efficiency and accuracy of existing water meter pointer reading technology can still be improved. This paper proposes a new water meter pointer reading recognition method based on target-key point detection. Our method consists of a target detection module and a key point detection module. The target detection module uses a modified YOLOv4-Tiny network to detect and classify the areas where the dials and pointers are located in water meter images with distinct characteristics. The key point detection module is used to detect the key point of the pointer image. In this module, the structure of the RFB-Net network is improved to introduce multiple layers of low-level feature information, therefore, it can make full use of the information between multi-scale feature layers for key point detection. In addition to, aiming at the problem of dial rotation, a method of establishing a right-angle coordinate system based on key point is proposed to realize pointer reading. The whole method proposed in this paper is compared to the Hough transform feature matching algorithm and traditional machine learning algorithms through experiments which test the detection and recognition of the water meter dial, pointer and key points. The experiment results show that the missed detection rate of the model in this paper is 1.88% and 1.07% for the dial region and the pointer region, respectively. And the accuracy rate reaches 98.68%, the average processing time per image is 0.37 s. This implies that the water meter inspection task is completed quickly and accurately with strong robustness. Thanks to the lightweight algorithm of our approach, the model can also be fully automated and easily deployed on mobile devices.     

基于互操作性通讯协议的多功能电能表设计与实现

要满足具有互操作性通讯协议在表计中的实现,关键是如何在单片机的程序设计中实现面向对象的设计思想。简单介绍在C程序设计中利用结构体基本实现面向对象的设计方法,利用表格查询代替条件判断语句组成的数据寻址方法,使表计的程序设计简单且易于维护。     

基于ICM的精密指针式仪表自动读数方法

针对精密指针式仪表自动读数算法自适应性较差的问题,提出一种基于ICM的精密指针式仪表自动读数方法。该方法基于二值化后仪表图像的噪声信息分布特性,利用ICM点火时序矩阵在图像相邻像素间的并行递进关系,研究和实现图像的腐蚀和膨胀,并设计加权最大类间方差法自适应地计算迭代次数,消除刻度周边噪声,提取到刻度圆弧所在位置。最后根据圆弧极径、极角等信息对刻度区域做极坐标变换输出图像,采用距离法对极坐标变换后图像进行读数判读。实验表明,自动读数结果与实际数值相比误差均小于0.2%,算法稳定可靠。     

变电站指针式仪表检测与识别方法

受限于复杂的电磁环境,变电站中的大量模拟式仪表需要人工读取示数,不利于变电站自动化管理。而目前针对仪表自动读数方法的研究大多基于预先获取到的高质量图像,其中仪表目标位于图像中央且占比较大,仪表表盘与相机平面平行,这需要大量预先的仪表测量与相机标定工作,不能满足实际电站环境下的使用要求。为解决上述问题,提出了一种完整的变电站指针式仪表的自动检测与识别方法。首先利用卷积神经网络模型检测当前视野下仪表目标的包围框位置,计算其距离视野中央的偏离值与图像占比,据此调整相机位置和缩放倍数。通过透视变换消除表盘平面与相机平面偏差造成的仪表图像畸变,通过霍夫变换检测仪表的表盘与指针,完成仪表读数识别。变电站实际测试实验结果表明,本方法最大读数误差仅为1.82%,对于复杂背景下多类别仪表的自动检测与识别任务具有良好的准确性与稳定性,可满足变电站实际应用需求。     

巡检机器人中的指针式仪表读数识别系统

为了解决智能巡检机器人仪表读数识别中易受光照变化影响、识别精度不高等问题,结合高压变电场中常见指针区域的图像特点,建立了指针式仪表读数高精度识别系统。鉴于巡检机器人的室外工作环境,提出了迭代最大类间方差算法,实现了多种光照条件下仪表图像的指针区域提取。经过分析指针转动和图像特性,提出了基于Hough变换的指针角度识别,推导出指针角度与仪表读数的函数关系。该算法较传统Hough变换角度提取法,增加了指针中心线通过表计中心等约束条件,提高了指针角度提取的精度,降低了搜索数据量和搜索时间。通过大量实验验证所建立的表计读数识别系统可实现室外各种光照条件下表计读数识别,获得95%以上的正确识别率。多组鲁棒性实验分析表明,该系统对光照条件、指针宽度、表盘干扰、拍摄角度(不产生指针阴影)具有较好的鲁棒性,但由于拍摄角度而产生指针阴影时,会引起较大的指针中心线提取和角度计算偏差,从而降低仪表读数识别精度。     

A unified approach to form error evaluation

Evaluation of form error is a critical aspect of many manufacturing processes. Machines such as the coordinate measuring machine (CMM) often employ the technique of the least squares form fitting algorithms. While based on sound mathematical principles, it is well known that the method of least squares often overestimates the tolerance zone, causing good parts to be rejected. Many methods have been proposed in efforts to improve upon results obtained via least squares, including those, which result in the minimum zone tolerance value. However, these methods are mathematically complex and often computationally slow for cases where a large number of data points are to be evaluated. Extensive amount of data is generated where measurement equipment such as laser scanners are used for inspection, as well as in reverse engineering applications.In this report, a unified linear approximation technique is introduced for use in evaluating the forms of straightness, flatness, circularity, and cylindricity. Non-linear equation for each form is linearized using Taylor expansion, then solved as a linear program using software written in C++ language. Examples are taken from the literature as well as from data collected on a coordinate measuring machine for comparison with least squares and minimum zone results. For all examples, the new formulations are found to equal or better than the least squares results and provide a good approximation to the minimum zone tolerance.     

基于粒子群优化算法的直线拟合及应用

将粒子群优化算法和传统最小二乘法相结合,采用残差平方和准则、绝对残差绝对值和准则、相对残差绝对值和准则建立了一种基于粒子群优化算法的直线拟合方法,获得了比传统最小二乘法拟合要好得多的估计结果,实验证明了该方法的有效性及高精度性。     

一种处理系统误差的新方法

测量数据处理中影响观测值的因素有2个部分：线性部分和某种干扰因素，干扰因素同观测量的关系是完全未知的，没有理由将其归入误差项，可以将其看成半参数模型中的非参数分量，即用非参数分量表达参数模型不完善的部分。本文首先利用自然样条函数法，找到符合条件的非参数自然插值样条函数；其次利用偏残差法并综合最小二乘法，导出了这种平差方法的解算公式；最后，用一个算例说明了此方法的优越性。     

Research on the uncertainties from different form error evaluation methods by CMM sampling

As a part of the new measurement uncertainty system proposed in the new generation of Geometrical Product Specifications and Verification, the evaluation methods of uncertainties to form errors have been researched in mechanical engineering, which are calculated based on the error propagation principle and statistical concept under certain conditions. In this paper, the evaluation datum is obtained by using both the least squares method and the genetic optimization algorithm. Their computation uncertainties to flatness and roundness were compared with each other using the sample data from a coordinate measurement machine (CMM). The results show that the uncertainties obtained from the genetic algorithm-based method are similar to those from the least squares method according to their evaluation parameters. The evaluation uncertainties from different methods become a little smaller with more sample points. A more significant conclusion is that the evaluation uncertainties from two methods are so small that they almost do not affect the measurement uncertainties to form error, which, in fact, mainly comes from the CMM sampling. Therefore, for the efficiency and simplification of calculation, especially for the cylintricity with more parameters, the uncertainties from evaluation methods can be neglected where the precision is not so strict.