首页|基于机器视觉的电芯绝缘介质定位算法

基于机器视觉的电芯绝缘介质定位算法

扫码查看
为保证电芯绝缘介质定位的准确性和时效性,文章提出一种基于双线性插值亚像素坐标结合改进随机抽样一致性(random sample consensus,RANSAC)算法的绝缘介质定位算法.对工业采集的图像进行空间滤波、阈值分割等预处理操作,分割出目标并增强特征;运用Canny边缘检测算子检测边缘,选取定位轮廓并根据最小外接矩形分离 4 条边缘直线,用双线性插值公式精确定位边缘直线亚像素坐标;采用部分点先验模型约束RANSAC算法提取4条边缘直线的高质量内点,再用最小二乘法分别拟合 4 条边缘直线并计算出相应偏移量.实验结果表明,该算法能有效保证绝缘介质的定位精度且具有一定的时效性,可以较好地满足实际生产应用的要求.
Location algorithm for battery core insulating medium based on machine vision
In order to ensure the accuracy and timeliness of insulating medium location of battery core,this pa-per proposes an insulating medium location algorithm based on bilinear interpolation sub-pixel coordinates and improved random sample consensus(RANSAC)algorithm.Firstly,the industrial images are preprocessed by spatial filtering and threshold segmentation,etc.,to segment the target and enhance the features.Secondly,the Canny edge detection operator is used to detect the edge,the locating contour is selected,four edge lines are separated according to the minimum circumscribed rectangle,and the sub-pixel coordinates of the edge lines are accurately located by bilinear interpolation formula.Finally,the high-quality interior points of the four edge lines are extracted by RANSAC algorithm constrained by partial point prior model,and then the four edge lines are fitted by least square method and the corresponding offsets are calculated.The experimen-tal results show that the algorithm can effectively ensure the positioning accuracy of insulating medium and has a certain timeliness,which can better meet the requirements of practical production applications.

machine visionsub-pixel edgerandom sample consensus(RANSAC)visual positioningline fitting

陈甦欣、罗乐文、赵安宁

展开 >

合肥工业大学 机械工程学院,安徽 合肥 230009

机器视觉 亚像素边缘 随机抽样一致性(RANSAC) 视觉定位 直线拟合

安徽省科技重大专项资金资助项目

202103a05020024

2024

合肥工业大学学报(自然科学版)
合肥工业大学

合肥工业大学学报(自然科学版)

CSTPCD北大核心
影响因子:0.608
ISSN:1003-5060
年,卷(期):2024.47(4)
  • 13