中文 | English

J. Hefei Univ. Tech. (Nat. Sci.)

合肥工业大学学报(自然科学版)

JOURNAL OF HEFEI UNIVERSITY OF TECHNOLOGY (NATURAL SCIENCE)

Competent Authorities: Ministry of Education of the People's Republic of China

Sponsor by: Hefei University of Technology

ISSN 1000-1646, CN 34-1001/N

Location algorithm for battery core insulating medium based on machine vision

Download Full Text

基于机器视觉的电芯绝缘介质定位算法

Journal Information

J. Hefei Univ. Tech. (Nat. Sci.), Apr.2024, Vol.47 No.4: 452-457

DOI: 10.3969/j.issn.1003-5060.2024.04.004

Authors

CHEN Suxin, LUO Lewen, ZHAO Anning

(School of Mechanical Engineering, Hefei University of Technology, Hefei 230009, China)

Abstract and Keywords

Abstract: In order to ensure the accuracy and timeliness of insulating medium location of battery core, this paper 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 experimental 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.

Keywords: machine vision; sub-pixel edge; random sample consensus (RANSAC); visual positioning; line fitting

作者信息

陈甦欣，罗乐文，赵安宁

（合肥工业大学机械工程学院，安徽合肥230009）

摘要和关键词

摘要: 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。

关键词: 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

Funding

安徽省科技重大专项资金资助项目（202103a05020024）

Previous Next

Back to Contents