基于图像色彩特征融合的绝缘子污秽等级检测
作者:
作者单位:

同济大学电子与信息工程学院,同济大学电子与信息工程学院,深圳供电局有限公司,深圳供电局有限公司

作者简介:

通讯作者:

中图分类号:

TP391.4

基金项目:

国家自然科学基金项目(51177109)


Contamination Grades Measurement of Insulators Based on Image Color Feature Fusion
Author:
Affiliation:

College of Electric and Information Engineering, Tongji University,College of Electric and Information Engineering, Tongji University,Shenzhen Power Supply Co., Ltd,Shenzhen Power Supply Co., Ltd

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对绝缘子污秽状态非接触检测问题,提出基于可见光图像RGB(red green blue)和HSI(hue saturation intensity)空间信息特征级融合的污秽等级检测方法.利用最佳熵阈值分割法(OET)提取绝缘子盘面区域,分别在RGB和HSI色彩空间进行特征计算,根据Fisher准则进行特征选择,得到可以有效表征污秽状态的特征量,利用核主元分析(KPCA)对两个色彩空间特征的组合进行降维融合,得到三维融合特征向量,结合概率神经网络(PNN)实现污秽等级识别.实验分析表明,基于核主元分析的图像信息特征级融合能够全面地反映绝缘子污秽状态,与单独利用RGB或HSI特征进行识别相比,其准确率有显著提高,可以实现绝缘子污秽等级的有效识别,为绝缘子污闪防治提供了新的方法.

    Abstract:

    An insulator contamination grades measurement method based on feature level fusion of visible image information in red green blue (RGB) and hue saturation intensity (HSI) color spaces is proposed. Optimal entropic threshold (OET) segmentation algorithm is adopted to segment insulator surface. Features of RGB and HSI color spaces are calculated separately. Meanwhile, feature selection based on Fisher criterion is applied to obtain features which have the ability to represent the contamination grades efficiently. Kernel principal component analysis (KPCA) is adopted to carry out dimensionality reduction fusion of the combination of features and obtain three dimensional fused features. Probabilistic neural network (PNN) is used to identify the contamination grades. The experimental results indicate that the feature level fusion of image information based on KPCA has capability to characterize the contamination grades comprehensively. Compared with recognition using RGB or HSI features solely, the proposed method can obtain higher recognition accuracy and realize the contamination grades recognition effectively. A new method for the prevention of pollution flashover is presented.

    参考文献
    相似文献
    引证文献
引用本文

金立军,张达,段绍辉,姚森敬.基于图像色彩特征融合的绝缘子污秽等级检测[J].同济大学学报(自然科学版),2014,42(10):1611~1617

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2013-07-11
  • 最后修改日期:2014-06-16
  • 录用日期:2014-05-20
  • 在线发布日期: 2014-10-14
  • 出版日期: