A study on vision-based real-time seam tracking in robotic arc welding

This paper discussed seam tracking technology by computer vision sensing in real time for robot GTAW. An image processing algorithm was presented to extract the seam trajectory and the offset of the torch to the seam in the welded pool images of aluminum alloys with grooves. Also the tracking sequence was analyzed and designed. C++ computer language was used to realize the algorithm. The experimental results showed that the error of real-time image process could meet the requirement of production. Such an algorithm was proved to be feasibility in factual manufacturing