Robust welding seam tracking using image seam extraction

摘要

Extracting single pixel wide paths is the core image processing problem in many vision basednwelding seam tracking applications. Traditional techniques such as edge detection and imagenthinning may not be effective for solving this problem on low quality welding images polluted bynprocess noises. Based on the understanding of the prior knowledge about the welding images,nwe present in this paper a welding seam tracking method using the image seam extractionntechnique. Owing to its optimisation nature, the proposed method is robust to strong image noisesncaused by environmental factors such as uneven illumination, light interferences and weldingnspatters. In addition, the proposed method is of low time complexity and is highly adaptive tondifferent types of welding images. Experimental results on a variety of welding images validate theneffectiveness and efficiency of the proposed method.