Autonomous Detection of Weld Seam Profiles via a Model of Saliency-Based Visual Attention for Robotic Arc Welding
- 507 Downloads
This paper presents a method of autonomously detecting weld seam profiles from molten pool background in metal active gas (MAG) arc welding using a novel model of saliency-based visual attention. First, a vision sensor based on structured light is employed to capture laser stripes and molten pools simultaneously in the same frame. Second, to effectively detect the weld seam profile from molten pool background for next autonomous guidance of initial welding positions and seam tracking, a model of visual attention based on saliency is proposed. With respect to the enhanced effect of saliency, the proposed model is much better than the classic models in the field. According to the comprehensive saliency map created by the proposed model, the weld seam profile can be extracted after threshold segmentation and clustering are applied to it in turn. Third, different weld seam images are used to demonstrate the robustness of the proposed methodology and last, to evaluate the performance of the proposed method, a measure called profile extraction rate (PER) is computed, which shows that the extracted weld seam profile can basically meet the requirements of seam tracking and the guidance of welding torches.
KeywordsVisual attention Saliency Weld seam detection Gabor filtering Robotic welding
Unable to display preview. Download preview PDF.
- 1.Drews, P., Starke, G.: Welding in the century of information technology. Wel. World, Le Soudage Dans Le Monde 34, 1–20 (1994)Google Scholar
- 2.Trailer: Manufacturer depends on robotic welding to boast production. Weld. J. 74(7), 49–51 (1995)Google Scholar
- 3.Pan, J.: A survey of welding sciences in 21th century. In: Proceedings 9th Chinese Welding Conferences, pp 001–017 (1999)Google Scholar
- 4.Chen, S., Wu, J.: Intelligentized technology for arc welding dynamic process, p 29. Springer-Verlag, LNEE (2009)Google Scholar
- 12.Gao, F., Wang, K.: The Research of Classification Method of Arc Welding Pool Image Based on Invariant Moments. In: Power Engineering and Automation Conference (PEAM), pp 73–76. IEEE, Wuhan, China (2011)Google Scholar
- 13.Wu, M., Wei, L., Xiao, L., Yu, S.: Extract the aluminum alloy MIG welding pool edge with Otsu threshold selection based on the genetic algorithmic. In: Information Science and Engineering (ICISE), 2nd International Conference on, pp 1173–1175 . IEEE, Hangzhou, China (2010)Google Scholar
- 19.Liu, X., Wang, G., Shi, Y.: Image processing of welding seam based on single–stripe laser vision system. In: Proceedings 6th International Conference Intelligent Systems Design and Applications, vol. 2, pp 463–470 (2006)Google Scholar
- 22.Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: Proceedings 19th International Conference Advances in Neural Information Processing Systems, pp 545–552 (2006)Google Scholar
- 24.Fang, Y., Lin, W., Lau, C., Lee, B.: A visual attention model combing top-down and bottom-up mechanisms for salient object detection. In: Proceedings IEEE Acoustics Speech and Signal Processing (ICASSP) Conference, pp 1293–1296 (2011)Google Scholar
- 31.Zhang, Q., Liu, H., Shen, J., Gu, G.: An improved computational approach for salient region detection. J. Comput. 5(7), 1011–1018 (2010)Google Scholar