Computer Engineering and Applications ›› 2014, Vol. 50 ›› Issue (6): 132-134.

Previous Articles     Next Articles

Tabu search algorithm application in segmentation of insulator infrared image

GONG Lei1, YAO Jiangang1, LI Tangbing2, ZHANG Yan3, LIAO Wei3,WU Yefan3   

  1. 1.School of Electrical & Information Engineering, Hunan University, Changsha 410082, China
    2.Jiangxi Electric Power Research Institute, Nanchang 330006, China
    3.Hunan HDHL Electrical & Information Tech Co., LTD, Changsha 410012, China
  • Online:2014-03-15 Published:2015-05-12

禁忌搜索在绝缘子红外图像分割中的应用

龚  磊1,姚建刚1,李唐兵2,张  彦3,廖  威3,伍也凡3   

  1. 1.湖南大学 电气与信息工程学院,长沙 410082
    2.江西省电力科学研究院,南昌 330006
    3.湖南湖大华龙电气与信息技术有限公司,长沙 410012

Abstract: According to the image segmentation problem of using infrared imaging technique to detect zero resistance insulator in transmission lines, an image segmentation method on the combination of Otsu double thresholds segmentation and tabu search is proposed. This method takes Otsu for fitness function, and avoids getting into the local best by field moving, tabu list and aspiration criterion, at the same time, it runs faster than the basic Otsu double thresholds segmentation. The experimental result shows the validity of this algorithm.

Key words: zero resistance insulator, Otsu, tabu search, infrared image, image segmentation

摘要: 针对利用红外成像技术检测输电线路中零值绝缘子所存在的图像分割问题,提出了一种类间方差(Otsu)双阈值分割和禁忌搜索相结合的图像分割算法。该方法以类间方差为适应度函数,通过领域移动、禁忌表、藐视准则确保算法不陷入局部最优解,同时,运行速度比基本Otsu双阈值分割算法更快。实验结果验证了该算法的有效性。

关键词: 零值绝缘子, 类间方差法, 禁忌搜索, 红外热像, 图像分割