机构地区: 广西机电职业技术学院
出 处: 《电焊机》 2010年第3期60-63,共4页
摘 要: 为了在焊缝跟踪系统中准确获取焊缝中心位置,设计了一套基于结构光的V型焊缝中心提取方法。对焊缝图像采用中值滤波去除图像噪声,采用准固定像素个数阈值分割方法对图像进行二值化处理,采用基于二值形态学的边缘检测方法对二值化的图像进行孤点滤波和边缘检测,采用求取边缘上下两个边界点的平均值方法提取结构光的中心线,通过计算坡口截面重心坐标的方法来获取焊缝中心位置信息。实践表明,所采用的方法能够正确地提取焊缝中心位置信息,具有很强的抗干扰性能,能够满足焊缝跟踪系统的实时性要求。 To detect weld seam centre exactly in the seam tracking system,methods of real-time processing V type of groove seam image based on structured light,is present in this paper.The image is denoised through median filtering,and quasi-constant pixel number threshold is applied to the image segmentation,and mathematical morphology is used to the binary image to filter isolated points and to detect edge,and the center line of seam is gotten through calculating the average of two edge pixels,and barycenter of groove section is selected as seam center point at last.The practice has proved that real-time weld groove image can be processed,and weld seam centre is detected exactly with the methods.It can meet the request of the seam tracking system.
关 键 词: 结构光 图像处理 焊缝跟踪 二值形态学 边缘检测
领 域: [金属学及工艺]