Automated seam tracking system based on passive monocular vision for automated linear robotic welding process
Electric arc welding is a complex task that demands a high degree of control in order to meet the international standards for fusion welding. We present a Vision-Based Measurement (VBM) system and evaluate how different conditions and algorithms impact the measuring of beveled edges. The proposed system integrates hardware and software to image the welding plates using a single CMOS camera as visual sensor, run computer vision algorithms on a FPGA (Field Programmable Gate Array) board, controls the robot movements and adjust the weld pattern and welder equipment parameters. A complete prototype, using a commercial linear welding robot is presented. The evaluation of the system as a groove mapping equipment, considering different processing algorithms combined with noise removal and line segment detection techniques, shows the potential of the approach for shop floor operation.