基于计算机视觉的执行器角度识别算法研究  

Research on Algorithm for Angle Recognition of Executors Based on Computer Vision

作　　者：邓柳[1] Deng Liu(ChangjiangPolytechnic,WuHan 430074,China)

机构地区：[1]长江职业学院,湖北武汉430074

出　　处：《湖北成人教育学院学报》2023年第5期92-96,共5页Journal of Hubei Adult Education Institute

基　　金：湖北省教育厅科学技术研究计划指导性项目“基于计算机视觉的汽车空调执行器旋转轴多目标识别及角度检测算法研究”(B2021534)。

摘　　要：针对汽车空调执行器自动参数检测过程中输出轴角度测量难点问题,基于计算机视觉,提出基于轮廓特征找直线并进行角度解算的方法。分步骤阐述了边缘检测、直线检测、坐标变换、象限划分及角度计算公式推导。利用工业相机采集图像,并基于Python-OpenCV编程进行算法验证,能准确计算出输出轴的旋转角度,在验证的10个样本中,测量误差小于0.19%,能为后续自动化检测提供精确的定位信息。Aiming at the difficulty of measuring the angle of the output shaft in the automatic parameter detection process of automotive air conditioning actuators,a method based on computer vision is proposed to find a straight line based on contour features and calculate the angle.Elaborated step by step on edge detection,line detection,coordinate transformation,quadrant division,and derivation of angle calculation formulas.By using an industrial camera to capture images and using Python OpenCV programming for algorithm verification,the rotation angle of the output shaft can be accurately calculated with an error of less than 0.19%,providing accurate positioning information for subsequent automated detection.

关 键 词：执行器 计算机视觉 轮廓特征 霍夫变换 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]