戴明回归和ROI细化的机械仪表读数技术  

Deming Regression and ROI Refinement of Mechanical Instrument Reading Technology

作　　者：刘继玲 Liu Jiling(Daqing Petrochemical Machinery Factory Co.,Ltd.,Daqing Heilongjiang 163714)

机构地区：[1]大庆石油化工机械厂有限公司,黑龙江大庆163714

出　　处：《中国仪器仪表》2024年第7期71-74,共4页China Instrumentation

摘　　要：针对目前机械仪表在读数时存在的辨识准确度不高、读数速度较慢等难题,本文提出一种以戴明回归与目标区精化为基础的读数方法。利用图象的帧间差异去除指针的摆动。在此基础上,采用区域细分算法,对待辨识仪器的各项指标进行精化。然后利用戴明回归方法进行拟合,得到仪器指示的拟合公式及倾斜度。通过实验来验证该方法的有效性和抗抖性。实验结果显示,本项目提出的新方法单幅影像的平均运算时间缩短189.363秒,并具备抗抖性能。In response to the current difficulties of low identification accuracy and slow reading speed in mechanical instruments,this project intends to study a reading method based on Deming regression and target area refinement.Then,the inter frame differences of the image are used to remove pointer oscillation.On this basis,a regional subdivision algorithm is adopted to refine the various indicators of the instrument to be identified.Then,the Deming regression method was used for fitting,and the fitting formula and inclination indicated by the instrument were obtained.Validate the effectiveness and shake resistance of the method proposed in this project through experiments.The experimental results show that the new method proposed in this project reduces the average operation time of a single image by 189.363 seconds and has anti shake performance.

关 键 词：机械仪表 戴明回归 ROI细化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TH70[自动化与计算机技术—计算机科学与技术]