基于红外图像匹配的零值绝缘子检测

Zero-insulator detection based on infrared images matching

针对零值绝缘子检测,提出一种SIFT算法与改进RANSAC法相结合的图像匹配检测方法。首先利用SIFT算法与欧式距离实现待测绝缘子串与图像库标准绝缘子串的图像特征提取及粗匹配,然后将马氏距离与RANSAC算法相结合实现特征的精匹配,提出了一种基于数据模型外点率的自适应方法来减少RANSAC算法在检验抽样数据模型上耗费的大量时间。试验结果表明,所提方法能准确地实现待测绝缘子串与图像库相应标准零值绝缘子串的匹配,实现零值绝缘子的准确识别。

A matching method is proposed for zero-insulator detection,which combines the scale invariant feature transform (SIFT) algorithm and an improved random sample consensus (RANSAC) algorithm. Firstly,SIFT algorithm and Euclidean distance function are adopted to extract image features and pre-matching between the testing zero-insulator string image and the standard zero-insulator string image in the image library. Secondly,the mismatching features are wiped out by using RANSAC method combined with Mahalanobis distance algorithm. An adap-tive method based on the‘outers’ statistic rate of sampled digital models is presented to minimize the running time for the validity tests of models. The experimental results show that the proposed method can accurately realize the matching between the tested insulator string and the corresponding standard zero-insulator string in the image library,which achieves precise and prompt detection for the zero-insulator.