基于机器视觉的汽车风挡涂胶轨迹检测研究

Research on detection of automobile windshield coating track based on machine vision

  • 摘要: 为了精确检测汽车挡风玻璃涂胶轨迹宽度,提出了基于HALCON和变步长天牛须搜索算法(variable step beetle antennae search algorithm,VSBAS)的涂胶轨迹检测方法(H-VSBAS)。首先使用HALCON对采集的涂胶轨迹图像进行预处理,然后使用Canny边缘提取算子提取涂胶轨迹边缘,并建立涂胶轨迹数学模型,最后使用VSBAS对模型进行了求解。与人工检测结果对比,实验结果表明H-VSBAS方法测量数据波动小、误判率低,有利于提高汽车挡风玻璃涂胶工位质量检测准确率。

     

    Abstract: In order to accurately detect the width of the glued track of the automobile windshield, this paper proposes a glued track detection method (H-VSBAS) based on HALCON and variable step beetle Antennae search algorithm (VSBAS). Firstly, the collected glue track image is pre-processed by HALCON. Then, the glue track edge is extracted using Canny edge extraction operator. Finally, the mathematical model of the glue trajectory was established and the model was solved using VSBAS. Compared with the results of manual inspection, the experimental results show that the measurement data of the H-VSBAS method has small fluctuations and low false positive rates, which is conducive to improving the quality inspection requirements of automotive windshield coating stations.

     

/

返回文章
返回