Weld pool image processing algorithm for seam tracking of welding robot

A weld pool image processing algorithm based passive-light-vision has been studied in this paper. Firstly, we have designed a kind of method to directly capture the welding pool images of Gas Metal Arc Welding (GMAW) by a CCD camera with a narrowband filter. Next, using the median filter and wavelet transform eliminates noise and keeps the details of the image effectively. Then, we have proposed to adopt the threshold image segmentation for detecting the welding pool in the image. The segmentation between the connected components and the noises to include the welding pool with the spots and the block, have been realized by the method to mark the connected pixels. Finally, through the operations of pixel-by-column scanning and pixel-by-line scanning, the groove centerline and the welding torch centerline can be found out correctly and the deviations of the seam are also obtained. The experiment and analysis have illustrated that wavelet transform can effectively filter out the image noise, maintain the details of the image and prevent the boundaries blurred, the T of 180 is the most suitable threshold and the deviation in different conditions can be calculated. This algorithm can be used in the seam tracking of welding robot.