论文部分内容阅读
在基于视觉传感的焊缝跟踪系统中,焊缝图像复杂多变,要准确得到焊缝中心线,选取合理高效的处理算法是十分重要的。在详细分析焊缝图像特点基础上,采用先行基于梯度信息的自适应平滑滤波,运用3阶B样条双小波多尺度边缘检测方法,减少了误检漏检率,有效地提高了小波变换在抗噪性能和定位精度上的优越性。在此基础上提取出焊缝中心线,用于焊缝自动跟踪控制。试验结果表明,该方法复杂度适中,处理速度较快,效果良好,能有效地提高焊缝跟踪控制的精度。
In the vision-based seam tracking system, the weld image is complex and changeable. To get the center line of the weld accurately, it is very important to choose a reasonable and efficient processing algorithm. Based on the detailed analysis of weld image characteristics, the adaptive smoothing filter based on gradient information is used in advance and the third-order B-spline double wavelet multiscale edge detection method is adopted to reduce the false negative detection rate and effectively improve the performance of wavelet transform in Noise resistance and positioning accuracy of the superiority. Based on this, the center line of the weld is extracted for the automatic tracking control of the weld. The experimental results show that the proposed method has the advantages of moderate complexity, fast processing speed and good effect, which can effectively improve the accuracy of weld seam tracking control.