基于机器视觉的光伏电池位置检测方法

Method for Detecting Photovoltaic Cell Position Based on Machine Vision

太阳能电池片串焊过程中对识别和定位精度要求较高,针对电池片上料过程中位置发生偏转问题,提出了基于机器视觉的图像处理方法。首先,采用中值滤波算法对采集的电池片图像进行平滑去噪,降低图像中一些无效信息对检测和测量的干扰;其次,采用大津法对采集的图像进行阈值分割;第三步,采用边缘检测算子Sobel算子对图像边缘进行粗定位,即像素级定位;最后,采用插值法进行亚像素细分,提出基于匹配法计算电池片偏转角度,基于角点检测法检测电池片是否破损。实验结果表明,在满足精度的同时,基于以上算法能够解决电池片串焊过程中发生的位置偏转、是否破损问题,具有一定的工业意义。

An image processing method based on machine vision is proposed in this paper.Firstly,the median filtering algorithm is used to smooth and reduce the noise of the collected battery images,which reduces the interference of some invalid information in the image detection and measurement.Secondly,the OTSU method is used to perform threshold segmentation on the acquired images.In the third step,the edge detection operator Sobel operator is used to perform coarse positioning on the edge of the image,that is pixel-level positioning.Finally,the sub-pixel subdivision is performed by interpolation method.The deflection angle of the battery is calculated based on the matching method.The corner detection method is used to detect whether the battery piece is damaged.