Abstract: It designs and realizes a set of laser vision guided automatic seam tracking system, including overall system structure and key algorithms. A laser vision sensor is installed at the end of an industrial robot. Wavelet transform is used to filter image noise and improved Steger algorithm and Hough transform method are applied to extract the laser stripe center line. Then the position of welding seam is located. A strategy of dual queues is put forward to control the movement of the manipulator, and a series of intermediate points among welding points are obtained by interpolation, so as to realize the automatic and smooth tracking of weld laser visual guide. The experimental results show the system has good tracking accuracy and can meet the industrial requirement.

Key words: laser vision, image processing, weld seam tracking, dual queues

摘要： 设计与实现了一套激光视觉引导的焊缝自动跟踪系统，包括系统的整体硬件构成和关键算法。在工业机器人末端安装激光视觉传感器构成焊缝跟踪系统的硬件部分。采用小波变换滤除焊缝图像噪声，采用改进的Steger算法和Hough变换方法提取激光条纹中心直线，进一步提取出焊缝位置。提出一种双队列控制策略，在采集的焊缝特征点的基础上进一步插值，从而实现激光视觉引导的焊缝自动与平滑跟踪。实验结果表明，该系统具有较好的跟踪精度，能满足工业实际需求。

关键词: 激光视觉, 图像处理, 焊缝跟踪, 双队列