基于激光视觉的小截面管道相贯线焊缝特征点提取研究
Extraction of Feature Points of Small Section Pipeline Intersecting Curve Welds Based on Laser Vision
-
摘要: 为了保证相贯线型焊缝特征点提取的质量与高效,以小截面管道正交所构成的相贯线为研究对象,提出一种结合图像感兴趣区域的改进斜率法,从相贯线焊缝的不同方位完成了特征点的提取。首先对含有激光条纹的焊缝图像进行图像差分以及形态学开运算,然后使用轮廓跟踪法对激光条纹进行轮廓框定,再使用灰度重心法提取光条中心线。通过对细化后的图像进行分析,根据水平投影结合逐列搜寻的方式,两次设定出特征点所在的重要区域,最后融合加权斜率法,实现了焊缝特征点的识别。实验结果表明:该方法可有效提取出相贯线焊缝的特征点,有较高的提取精度和效率,适用于实际管道零部件的焊接。Abstract: In order to ensure the quality and efficiency of the extraction of feature points of intersecting curve welds,taking the intersecting curve formed by the orthogonalization of small-section pipes as the study object, a modified slope method combined with the image region of interest was proposed for the extraction of feature points from different orientations of the intersecting curve weld. Firstly, image differencing and morphological opening operations were performed for the weld image with laser stripes. Secondly, contour framing of the laser stripes was carried out by using the contour tracking method, and the centerline of the laser stripes was extracted by using the grey-scale center of gravity method. By analyzing the thined image, the important areas where the feature points were located were set twice according to the horizontal projection combined with the column-by-column search, finally the weighted slope method was used to achieve the identification of the weld feature points. The experimental results show that the method can effectively extract the feature points of the intersecting curve weld with high extraction accuracy and efficiency, and it is suitable for practical pipe component welding.
下载: