绝缘子串红外图像中绝缘子盘面和钢帽区域的自动提取方法

Algorithm Research on Automatically Extracting the Disks and Steel Caps Area of Insulator from Infrared Image of an Insulator String

提出了一种新的绝缘子串红外图像中绝缘子盘面和钢帽区域自动提取方法:通过红外图像预处理、特征提取、角度校正和区域提取4个步骤实现自动提取。该方法首先将现场拍摄的绝缘子红外图像进行灰度化处理、去噪、二值化;然后从二值图像中提取反映绝缘子的特征集合;通过特征集对二值图进行角度校正;最后通过区域提取中的特定算法提取出绝缘子的盘面和钢帽区域。该方法经过了某220 kV变电站的实验验证,证实了提取结果的正确性和实用性。

A new method to automatically extract the disks and steel caps area of insulator from infrared image is proposed： via infrared image preprocessing, feature extraction, angle correction and regional extraction to achieve the purpose. This method first makes insulator infrared image captured gray scene processing, noise reduction and binarization; then extracts the feature set related insulator from the binary image; corrects the angle of the binary image through the feature sets; finally extracts the disks and steel caps area through the specific algorithm of regional extraction. After the verification experiments of the method to some 220 kV substations, the validity and usefulness of the extraction results are confirmed.