基于Canny边缘特征点的接触网绝缘子识别方法

Identification Method of Catenary Insulator Based on Canny Edge Feature Point

针对使用机器视觉技术对接触网绝缘子状态检测时的绝缘子识别问题,提出一种结合Canny边缘特征和SURF点特征的绝缘子识别算法。该算法首先提取图像边缘特征,然后使用SURF算法在边缘图像上提取特征点,并利用Haar小波对特征点进行描述;对检测出的特征点使用欧氏距离比值法进行初匹配;最后用RANSAC算法消除由噪声等干扰产生的错误匹配,从而实现接触网绝缘子智能识别。实验结果表明,该算法能在有背景干扰、小幅度旋转的目标图像中准确识别出绝缘子,为电气化铁路接触网绝缘子智能清洗的视觉识别定位问题提供了可行参考。

The identification method in contact insulator state detection using machine vision technology is discussed. An insulator recognition algorithm combining Canny edge features and SURF point features is presented. This algorithm firstly extracts image edge features,then uses SURF algorithm to extract feature points on edge images,and uses Haar wavelet to describe feature points,and Euclidean distance ratio method is adopted to match the detected feature points. Finally,the RANSAC algorithm is used to eliminate the error matching caused by noise and other disturbances,so as to realize the intelligent identification of the insulators in the catenary. The test results show that the algorithm can accurately identify insulators in target images with background interference and small rotation,which provides a feasible reference for visual identification and location of insulators in electrified railway catenary.