摘要
在基于结构光视觉的激光拼焊焊缝表面质量检测系统中,需要准确获得焊缝结构光条纹中心线和特征点的位置。由于焊接过程中的各种噪声干扰,使得焊缝图像复杂多变,因此选择合理高效的图像处理算法是非常重要的。针对这一问题,对结构光视觉焊缝质量检测系统图像处理方法进行了深入研究。在图像预处理中,首先通过开窗处理来获得兴趣区域,采用中值滤波去除图像噪声。在结构光条纹中心线提取过程中,提出了一种新的模板法获得了条纹的边界并用几何中心法提取了条纹中心线;最后,使用斜率分析法提取了特征点。试验表明,该方法具有较高的特征点检测可靠性,并且运算速度快、抗干扰能力强,具有较高实用价值。
In the seam surface quality visual inspection system of tailored blanks laser welding,the main purpose of image processing is to extract the centerline of structured light stripe and the feature points.On the further study of image processing method of seam quality inspection system,presents a reasonable and efficient image processing method for seam quality inspection system.In the image preprocessing,the paper uses adding window operation to obtain the region of interest and adopts median filter to remove the noise interference.In the image postprocessing,it used a template to detect the edges of the structured light stripe,and then applies geometrical center method to extracting the centerline of structured light stripe,after that,the author uses slope analysis to detect the feature points.The experiment results demonstrate that the proposed method,which has the advantages of higher reliability and stronger anti-interference ability,lays a foundation for the realization of on-line inspection of seam surface quality visual inspection system.
出处
《机械设计与制造》
北大核心
2011年第3期156-158,共3页
Machinery Design & Manufacture
基金
辽宁省自然科学基金项目(20092082)
关键词
激光拼焊
焊缝图像
结构光条纹
Tailored blanks laser welding
Seam image
Structured light stripe
