摘要
针对电气化铁路接触网非接触式图像检测中绝缘子不良状态的自动识别定位问题,提出一种基于快速鲁棒性特征(speeded-up robust features,SURF)匹配的检测方法。该方法首先通过SURF进行待检测图像中绝缘子的特征提取与匹配;接着对绝缘子进行角度校正及形态学操作等预处理;最后纵向统计绝缘子灰度并根据其灰度极小值分布规律识别和定位其不良状态。实验表明,该方法能较准确快速地识别绝缘子,且对其不良状态的自动识别结果也较为准确,为电气化铁路接触网绝缘安全检测问题提供新的参考。
In allusion to automatic identification and location of defective insulators in overhead contact line of electrified railway by non-contact image detection,a detection method based on feature matching of speeded-up robust features(SURF) is proposed.Firstly,the feature extraction and matching of insulator in the image to be detected are performed by SURF;secondly,the pre-processing of insulator such as angle correction and morphological operation is carried out;finally,longitudinal statistics of insulator grayscale is implemented and according to the regularity of distribution of the minimal value of the grayscale the defective insulator can be identified and located.Experimental results show that using the proposed method the defective insulators can be identified rapidly and accurately,and the automatic identification results of defective conditions of insulators are more accurate.
出处
《电网技术》
EI
CSCD
北大核心
2013年第8期2297-2302,共6页
Power System Technology
基金
国家自然科学基金项目(U1134205
51007074)~~
关键词
图像处理
绝缘子
快速鲁棒性特征算法
不良状态检测
image processing
insulator
speeded-up robust features
defective condition detection