基于拉东变换和模糊增强的结构光焊缝跟踪图像处理

Image processing in welding seam tracking with structurelight based on Radon transform and fuzzy-enhancement

针对激光结构光引导焊缝跟踪过程中图像特点,首先对图像进行多角度拉东变换,然后找到变换后的图像中的激光条纹所对应奇异点,保持该奇异点附近点像素值不变,削弱该奇异点远点像素值,再进行拉东逆变换复原图像;最后采用模糊增强法对复原后的图像进行处理,可以获得清晰且少噪声的结构光图像.结果表明,该方法效果良好,抗干扰性较强,耗时较少,适合于激光视觉焊缝跟踪过程.

According to the image characteristics in weld seam tracking based on laser structured light,multi-angle Radon transform is used first,and then the singular point in the transformed corresponding to the laser stripe in the original image is found,keep the pixels value unchanged near the singular point and decrease the pixels value far from the singular point,after that inverse radon transform is carried out to recover original image. Finally,fuzzy enhancement method is used to get clear structured image with little noise. This method can bring good effects,and the anti-disturbance performance is well,it costs little additionally,therefore it is suitable for seam tracking based on laser vision.