Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (11): 223-225.

• 工程与应用 • Previous Articles     Next Articles

Research on image segmentation of welding seam by arc welding robot

CAI Guang-yu1,2,CUI Shi-lin2,WU Chang-lin1   

  1. 1.Huazhong University of Science and Technology,Wuhan 430074,China
    2.Nanyang Institute of Technology,Nanyang,Henan 473006,China
  • Received:2007-07-31 Revised:2007-10-09 Online:2008-04-11 Published:2008-04-11
  • Contact: CAI Guang-yu

弧焊机器人焊缝图像分割方法研究

蔡广宇1,2,崔士林2,吴昌林1   

  1. 1.华中科技大学 机械学院,武汉 430074
    2.南阳理工学院,河南 南阳 473006
  • 通讯作者: 蔡广宇

Abstract: Introduced a new method which based on the binary firing frequency matrix of PCNN,it used the two-values matrix of the binary firing frequency matrix to be the final outcome for image segmentation,produced the selection principle of PCNN parameter,reduced the parameter dependence to PCNN,enhanced the effect of image segmentation.Utilized this method to segmentalize the image of oil derrick arc welding robot welding line gets up the good effect.

Key words: oil drilling derrick, PCNN, image segmentation

摘要: 提出了脉冲耦合神经网络(PCNN)图像分割的一种新方法,首次使用点火频率矩阵的二值矩阵作为图像分割的最终结果,给出了在此过程指导下PCNN参数选择原则,降低了PCNN对参数的依赖性,提高了图像分割的效果。将该方法运用于石油井架弧焊机器人焊缝图象的识别中起到很好的效果。

关键词: 石油钻机井架, 脉冲耦合神经网络, 图像分割