基于图像信息融合的绝缘子污秽状态识别

Recognition of Contamination Grades of Insulators Based on Image Information Fusion

提出基于图像信息决策级融合的绝缘子污秽状态识别方法。对绝缘子图像分别在RGB和HSI色彩空间计算特征量,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,为了提高分类器的运算速度和准确性,利用核主元分析(KPCA)进行特征提取,在RGB和HSI色彩空间各得到一组三维核主元向量,使用径向基神经网络(RBFNN)分别在RGB和HSI色彩空间进行污秽等级识别,利用D-S证据理论对识别结果进行决策级融合,实现绝缘子污秽等级的识别。实验结果表明该方法可以显著提高识别正确率,可为输电线路绝缘子故障诊断提供依据。

An insulator contamination grades recognition method based on decision fusion of image information was proposed. Features of RGB and HS1 color spaces were calculated separately. Meanwhile, feature selection based on Fisher criterion was carried out to obtain features which have the ability to represent the contamination grades efficiently. In order to improve the calculation speed and precision of classifier, kernel principal component analysis （KPCA） was adopted to extract three-dimensional kernel principal features in both RGB and HS1 color spaces. Radial basis function neural network （RBFNN） was used to identify the contamination grades in RGB and HSI color spaces separately. And then, D-S theory was adopted to achieve the decision fusion and realize the high accuracy identification of contamination grades. Results of the experiments indicate that the proposed method can improve the precision of identification significantly and provide basis for fault diagnosis of line insulators.